Speech and Language Processing. Daniel Jurafsky & James H. Martin. Copyright c© 2016. All
rights reserved. Draft of August 7, 2017.
CHAPTER
2 Regular Expressions, TextNormalization, Edit Distance
User: You are like my father in some ways.
ELIZA: WHAT RESEMBLANCE DO YOU SEE
User: You are not very aggressive but I think you don’t want me to notice that.
ELIZA: WHAT MAKES YOU THINK I AM NOT VERY AGGRESSIVE
User: You don’t argue with me.
ELIZA: WHY DO YOU THINK I DON’T ARGUE WITH YOU
User: You are afraid of me.
ELIZA: DOES IT PLEASE YOU TO BELIEVE I AM AFRAID OF YOU
Weizenbaum (1966)
The dialogue above is from ELIZA, an early natural language processing sys-ELIZA
tem that could carry on a limited conversation with a user by imitating the responses
of a Rogerian psychotherapist (Weizenbaum, 1966). ELIZA is a surprisingly simple
program that uses pattern matching to recognize phrases like “You are X” and trans-
late them into suitable outputs like “What makes you think I am X?”. This simple
technique succeeds in this domain because ELIZA doesn’t actually need to know
anything to mimic a Rogerian psychotherapist. As Weizenbaum notes, this is one
of the few dialogue genres where listeners can act as if they know nothing of the
world. Eliza’s mimicry of human conversation was remarkably successful: many
people who interacted with ELIZA came to believe that it really understood them
and their problems, many continued to believe in ELIZA’s abilities even after the
program’s operation was explained to them (Weizenbaum, 1976), and even today
such chatbots are a fun diversion.chatbots
Of course modern conversational agents are much more than a diversion; they
can answer questions, book flights, or find restaurants, functions for which they rely
on a much more sophisticated understanding of the user’s intent, as we will see in
Chapter 29. Nonetheless, the simple pattern-based methods that powered ELIZA
and other chatbots play a crucial role in natural language processing.
We’ll begin with the most important tool for describing text patterns: the regular
expression. Regular expressions can be used to specify strings we might want to
extract from a document, from transforming “You are X” in Eliza above, to defining
strings like $199 or $24.99 for extracting tables of prices from a document.
We’ll then turn to a set of tasks collectively called text normalization, in whichtextnormalization
regular expressions play an important part. Normalizing text means converting it
to a more convenient, standard form. For example, most of what we are going to
do with language relies on first separating out or tokenizing words from running
text, the task of tokenization. English words are often separated from each othertokenization
by whitespace, but whitespace is not always sufficient. New York and rock ’n’ roll
are sometimes treated as large words despite the fact that they contain spaces, while
sometimes we’ll need to separate I’m into the two words I and am. For processing
tweets or texts we’ll need to tokenize emoticons like 🙂 or hashtags like #nlproc.
Some languages, like Chinese, don’t have spaces between words, so word tokeniza-
tion becomes more difficult.
2 CHAPTER 2 • REGULAR EXPRESSIONS, TEXT NORMALIZATION, EDIT DISTANCE
Another part of text normalization is lemmatization, the task of determininglemmatization
that two words have the same root, despite their surface differences. For example,
the words sang, sung, and sings are forms of the verb sing. The word sing is the
common lemma of these words, and a lemmatizer maps from all of these to sing.
Lemmatization is essential for processing morphologically complex languages like
Arabic. Stemming refers to a simpler version of lemmatization in which we mainlystemming
just strip suffixes from the end of the word. Text normalization also includes sen-
tence segmentation: breaking up a text into individual sentences, using cues likesentencesegmentation
periods or exclamation points.
Finally, we’ll need to compare words and other strings. We’ll introduce a metric
called edit distance that measures how similar two strings are based on the number
of edits (insertions, deletions, substitutions) it takes to change one string into the
other. Edit distance is an algorithm with applications throughout language process-
ing, from spelling correction to speech recognition to coreference resolution.
2.1 Regular Expressions
SIR ANDREW: Her C’s, her U’s and her T’s: why that?
Shakespeare, Twelfth Night
One of the unsung successes in standardization in computer science has been the
regular expression (RE), a language for specifying text search strings. This prac-regularexpression
tical language is used in every computer language, word processor, and text pro-
cessing tools like the Unix tools grep or Emacs. Formally, a regular expression is
an algebraic notation for characterizing a set of strings. They are particularly use-
ful for searching in texts, when we have a pattern to search for and a corpus ofcorpus
texts to search through. A regular expression search function will search through the
corpus, returning all texts that match the pattern. The corpus can be a single docu-
ment or a collection. For example, the Unix command-line tool grep takes a regular
expression and returns every line of the input document that matches the expression.
A search can be designed to return every match on a line, if there are more than
one, or just the first match. In the following examples we underline the exact part of
the pattern that matches the regular expression and show only the first match. We’ll
show regular expressions delimited by slashes but note that slashes are not part of
the regular expressions.
2.1.1 Basic Regular Expression Patterns
The simplest kind of regular expression is a sequence of simple characters. To search
for woodchuck, we type /woodchuck/. The expression /Buttercup/ matches any
string containing the substring Buttercup; grepwith that expression would return the
line I’m called little Buttercup. The search string can consist of a single character
(like /!/) or a sequence of characters (like /urgl/).
RE Example Patterns Matched
/woodchucks/ “interesting links to woodchucks and lemurs”
/a/ “Mary Ann stopped by Mona’s”
/!/ “You’ve left the burglar behind again!” said Nori
Figure 2.1 Some simple regex searches.
2.1 • REGULAR EXPRESSIONS 3
Regular expressions are case sensitive; lower case /s/ is distinct from upper
case /S/ (/s/ matches a lower case s but not an upper case S). This means that
the pattern /woodchucks/ will not match the string Woodchucks. We can solve this
problem with the use of the square braces [ and ]. The string of characters inside the
braces specifies a disjunction of characters to match. For example, Fig. 2.2 shows
that the pattern /[wW]/ matches patterns containing either w or W.
RE Match Example Patterns
/[wW]oodchuck/ Woodchuck or woodchuck “Woodchuck”
/[abc]/ ‘a’, ‘b’, or ‘c’ “In uomini, in soldati”
/[1234567890]/ any digit “plenty of 7 to 5”
Figure 2.2 The use of the brackets [] to specify a disjunction of characters.
The regular expression /[1234567890]/ specified any single digit. While such
classes of characters as digits or letters are important building blocks in expressions,
they can get awkward (e.g., it’s inconvenient to specify
/[ABCDEFGHIJKLMNOPQRSTUVWXYZ]/
to mean “any capital letter”). In cases where there is a well-defined sequence asso-
ciated with a set of characters, the brackets can be used with the dash (-) to specify
any one character in a range. The pattern /[2-5]/ specifies any one of the charac-range
ters 2, 3, 4, or 5. The pattern /[b-g]/ specifies one of the characters b, c, d, e, f, or
g. Some other examples are shown in Fig. 2.3.
RE Match Example Patterns Matched
/[A-Z]/ an upper case letter “we should call it ‘Drenched Blossoms’ ”
/[a-z]/ a lower case letter “my beans were impatient to be hoed!”
/[0-9]/ a single digit “Chapter 1: Down the Rabbit Hole”
Figure 2.3 The use of the brackets [] plus the dash – to specify a range.
The square braces can also be used to specify what a single character cannot be,
by use of the caret ˆ. If the caret ˆ is the first symbol after the open square brace [,
the resulting pattern is negated. For example, the pattern /[ˆa]/ matches any single
character (including special characters) except a. This is only true when the caret
is the first symbol after the open square brace. If it occurs anywhere else, it usually
stands for a caret; Fig. 2.4 shows some examples.
RE Match (single characters) Example Patterns Matched
/[ˆA-Z]/ not an upper case letter “Oyfn pripetchik”
/[ˆSs]/ neither ‘S’ nor ‘s’ “I have no exquisite reason for’t”
/[ˆ\.]/ not a period “our resident Djinn”
/[eˆ]/ either ‘e’ or ‘ˆ’ “look up ˆ now”
/aˆb/ the pattern ‘aˆb’ “look up aˆ b now”
Figure 2.4 Uses of the caret ˆ for negation or just to mean ˆ. We discuss below the need to escape the period
by a backslash.
How can we talk about optional elements, like an optional s in woodchuck and
woodchucks? We can’t use the square brackets, because while they allow us to say
“s or S”, they don’t allow us to say “s or nothing”. For this we use the question mark
/?/, which means “the preceding character or nothing”, as shown in Fig. 2.5.
We can think of the question mark as meaning “zero or one instances of the
previous character”. That is, it’s a way of specifying how many of something that
4 CHAPTER 2 • REGULAR EXPRESSIONS, TEXT NORMALIZATION, EDIT DISTANCE
RE Match Example Patterns Matched
/woodchucks?/ woodchuck or woodchucks “woodchuck”
/colou?r/ color or colour “colour”
Figure 2.5 The question mark ? marks optionality of the previous expression.
we want, something that is very important in regular expressions. For example,
consider the language of certain sheep, which consists of strings that look like the
following:
baa!
baaa!
baaaa!
baaaaa!
. . .
This language consists of strings with a b, followed by at least two a’s, followed
by an exclamation point. The set of operators that allows us to say things like “some
number of as” are based on the asterisk or *, commonly called the Kleene * (gen-Kleene *
erally pronounced “cleany star”). The Kleene star means “zero or more occurrences
of the immediately previous character or regular expression”. So /a*/ means “any
string of zero or more as”. This will match a or aaaaaa, but it will also match Off
Minor since the string Off Minor has zero a’s. So the regular expression for matching
one or more a is /aa*/, meaning one a followed by zero or more as. More complex
patterns can also be repeated. So /[ab]*/ means “zero or more a’s or b’s” (not
“zero or more right square braces”). This will match strings like aaaa or ababab or
bbbb.
For specifying multiple digits (useful for finding prices) we can extend /[0-9]/,
the regular expression for a single digit. An integer (a string of digits) is thus
/[0-9][0-9]*/. (Why isn’t it just /[0-9]*/?)
Sometimes it’s annoying to have to write the regular expression for digits twice,
so there is a shorter way to specify “at least one” of some character. This is the
Kleene +, which means “one or more of the previous character”. Thus, the expres-Kleene +
sion /[0-9]+/ is the normal way to specify “a sequence of digits”. There are thus
two ways to specify the sheep language: /baaa*!/ or /baa+!/.
One very important special character is the period (/./), a wildcard expression
that matches any single character (except a carriage return), as shown in Fig. 2.6.
RE Match Example Matches
/beg.n/ any character between beg and n begin, beg’n, begun
Figure 2.6 The use of the period . to specify any character.
The wildcard is often used together with the Kleene star to mean “any string of
characters”. For example, suppose we want to find any line in which a particular
word, for example, aardvark, appears twice. We can specify this with the regular
expression /aardvark.*aardvark/.
Anchors are special characters that anchor regular expressions to particular placesAnchors
in a string. The most common anchors are the caret ˆ and the dollar sign $. The caret
ˆ matches the start of a line. The pattern /ˆThe/ matches the word The only at the
start of a line. Thus, the caret ˆ has three uses: to match the start of a line, to in-
dicate a negation inside of square brackets, and just to mean a caret. (What are the
contexts that allow grep or Python to know which function a given caret is supposed
to have?) The dollar sign $ matches the end of a line. So the pattern $ is a useful
2.1 • REGULAR EXPRESSIONS 5
pattern for matching a space at the end of a line, and /ˆThe dog\.$/ matches a
line that contains only the phrase The dog. (We have to use the backslash here since
we want the . to mean “period” and not the wildcard.)
There are also two other anchors: \b matches a word boundary, and \B matches
a non-boundary. Thus, /\bthe\b/ matches the word the but not the word other.
More technically, a “word” for the purposes of a regular expression is defined as any
sequence of digits, underscores, or letters; this is based on the definition of “words”
in programming languages. For example, /\b99\b/ will match the string 99 in
There are 99 bottles of beer on the wall (because 99 follows a space) but not 99 in
There are 299 bottles of beer on the wall (since 99 follows a number). But it will
match 99 in $99 (since 99 follows a dollar sign ($), which is not a digit, underscore,
or letter).
2.1.2 Disjunction, Grouping, and Precedence
Suppose we need to search for texts about pets; perhaps we are particularly interested
in cats and dogs. In such a case, we might want to search for either the string cat or
the string dog. Since we can’t use the square brackets to search for “cat or dog” (why
can’t we say /[catdog]/?), we need a new operator, the disjunction operator, alsodisjunction
called the pipe symbol |. The pattern /cat|dog/ matches either the string cat or
the string dog.
Sometimes we need to use this disjunction operator in the midst of a larger se-
quence. For example, suppose I want to search for information about pet fish for
my cousin David. How can I specify both guppy and guppies? We cannot simply
say /guppy|ies/, because that would match only the strings guppy and ies. This
is because sequences like guppy take precedence over the disjunction operator |.Precedence
To make the disjunction operator apply only to a specific pattern, we need to use the
parenthesis operators ( and ). Enclosing a pattern in parentheses makes it act like
a single character for the purposes of neighboring operators like the pipe | and the
Kleene*. So the pattern /gupp(y|ies)/ would specify that we meant the disjunc-
tion only to apply to the suffixes y and ies.
The parenthesis operator ( is also useful when we are using counters like the
Kleene*. Unlike the | operator, the Kleene* operator applies by default only to
a single character, not to a whole sequence. Suppose we want to match repeated
instances of a string. Perhaps we have a line that has column labels of the form
Column 1 Column 2 Column 3. The expression /Column [0-9]+ */ will not
match any number of columns; instead, it will match a single column followed by
any number of spaces! The star here applies only to the space that precedes it,
not to the whole sequence. With the parentheses, we could write the expression
/(Column [0-9]+ *)*/ to match the word Column, followed by a number and
optional spaces, the whole pattern repeated any number of times.
This idea that one operator may take precedence over another, requiring us to
sometimes use parentheses to specify what we mean, is formalized by the operator
precedence hierarchy for regular expressions. The following table gives the orderoperatorprecedence
of RE operator precedence, from highest precedence to lowest precedence.
Parenthesis ()
Counters * + ? {}
Sequences and anchors the ˆmy end$
Disjunction |
Thus, because counters have a higher precedence than sequences,
6 CHAPTER 2 • REGULAR EXPRESSIONS, TEXT NORMALIZATION, EDIT DISTANCE
/the*/ matches theeeee but not thethe. Because sequences have a higher prece-
dence than disjunction, /the|any/ matches the or any but not theny.
Patterns can be ambiguous in another way. Consider the expression /[a-z]*/
when matching against the text once upon a time. Since /[a-z]*/ matches zero or
more letters, this expression could match nothing, or just the first letter o, on, onc,
or once. In these cases regular expressions always match the largest string they can;
we say that patterns are greedy, expanding to cover as much of a string as they can.greedy
There are, however, ways to enforce non-greedy matching, using another mean-non-greedy
ing of the ? qualifier. The operator *? is a Kleene star that matches as little text as*?
possible. The operator +? is a Kleene plus that matches as little text as possible.+?
2.1.3 A Simple Example
Suppose we wanted to write a RE to find cases of the English article the. A simple
(but incorrect) pattern might be:
/the/
One problem is that this pattern will miss the word when it begins a sentence
and hence is capitalized (i.e., The). This might lead us to the following pattern:
/[tT]he/
But we will still incorrectly return texts with the embedded in other words (e.g.,
other or theology). So we need to specify that we want instances with a word bound-
ary on both sides:
/\b[tT]he\b/
Suppose we wanted to do this without the use of /\b/. We might want this since
/\b/ won’t treat underscores and numbers as word boundaries; but we might want
to find the in some context where it might also have underlines or numbers nearby
(the or the25). We need to specify that we want instances in which there are no
alphabetic letters on either side of the the:
/[ˆa-zA-Z][tT]he[ˆa-zA-Z]/
But there is still one more problem with this pattern: it won’t find the word the
when it begins a line. This is because the regular expression [ˆa-zA-Z], which
we used to avoid embedded instances of the, implies that there must be some single
(although non-alphabetic) character before the the. We can avoid this by specify-
ing that before the the we require either the beginning-of-line or a non-alphabetic
character, and the same at the end of the line:
/(ˆ|[ˆa-zA-Z])[tT]he([ˆa-zA-Z]|$)/
The process we just went through was based on fixing two kinds of errors: false
positives, strings that we incorrectly matched like other or there, and false nega-false positives
tives, strings that we incorrectly missed, like The. Addressing these two kinds offalse negatives
errors comes up again and again in implementing speech and language processing
systems. Reducing the overall error rate for an application thus involves two antag-
onistic efforts:
• Increasing precision (minimizing false positives)
• Increasing recall (minimizing false negatives)
2.1 • REGULAR EXPRESSIONS 7
2.1.4 A More Complex Example
Let’s try out a more significant example of the power of REs. Suppose we want to
build an application to help a user buy a computer on the Web. The user might want
“any machine with more than 6 GHz and 500 GB of disk space for less than $1000”.
To do this kind of retrieval, we first need to be able to look for expressions like 6
GHz or 500 GB or Mac or $999.99. In the rest of this section we’ll work out some
simple regular expressions for this task.
First, let’s complete our regular expression for prices. Here’s a regular expres-
sion for a dollar sign followed by a string of digits:
/$[0-9]+/
Note that the $ character has a different function here than the end-of-line function
we discussed earlier. Regular expression parsers are in fact smart enough to realize
that $ here doesn’t mean end-of-line. (As a thought experiment, think about how
regex parsers might figure out the function of $ from the context.)
Now we just need to deal with fractions of dollars. We’ll add a decimal point
and two digits afterwards:
/$[0-9]+\.[0-9][0-9]/
This pattern only allows $199.99 but not $199. We need to make the cents
optional and to make sure we’re at a word boundary:
/\b$[0-9]+(\.[0-9][0-9])?\b/
How about specifications for processor speed? Here’s a pattern for that:
/\b[0-9]+ *(GHz|[Gg]igahertz)\b/
Note that we use / */ to mean “zero or more spaces” since there might always
be extra spaces lying around. We also need to allow for optional fractions again (5.5
GB); note the use of ? for making the final s optional:
/\b[0-9]+(\.[0-9]+)? *(GB|[Gg]igabytes?)\b/
2.1.5 More Operators
Figure 2.7 shows some aliases for common ranges, which can be used mainly to
save typing. Besides the Kleene * and Kleene + we can also use explicit numbers as
counters, by enclosing them in curly brackets. The regular expression /{3}/ means
“exactly 3 occurrences of the previous character or expression”. So /a\.{24}z/
will match a followed by 24 dots followed by z (but not a followed by 23 or 25 dots
followed by a z).
RE Expansion Match First Matches
\d [0-9] any digit Party of 5
\D [ˆ0-9] any non-digit Blue moon
\w [a-zA-Z0-9_] any alphanumeric/underscore Daiyu
\W [ˆ\w] a non-alphanumeric !!!!
\s [ \r\t\n\f] whitespace (space, tab)
\S [ˆ\s] Non-whitespace in Concord
Figure 2.7 Aliases for common sets of characters.
8 CHAPTER 2 • REGULAR EXPRESSIONS, TEXT NORMALIZATION, EDIT DISTANCE
A range of numbers can also be specified. So /{n,m}/ specifies from n to m
occurrences of the previous char or expression, and /{n,}/ means at least n occur-
rences of the previous expression. REs for counting are summarized in Fig. 2.8.
RE Match
* zero or more occurrences of the previous char or expression
+ one or more occurrences of the previous char or expression
? exactly zero or one occurrence of the previous char or expression
{n} n occurrences of the previous char or expression
{n,m} from n to m occurrences of the previous char or expression
{n,} at least n occurrences of the previous char or expression
Figure 2.8 Regular expression operators for counting.
Finally, certain special characters are referred to by special notation based on the
backslash (\) (see Fig. 2.9). The most common of these are the newline characterNewline
\n and the tab character \t. To refer to characters that are special themselves (like
., *, [, and \), precede them with a backslash, (i.e., /\./, /\*/, /\[/, and /\\/).
RE Match First Patterns Matched
\* an asterisk “*” “K*A*P*L*A*N”
\. a period “.” “Dr. Livingston, I presume”
\? a question mark “Why don’t they come and lend a hand?”
\n a newline
\t a tab
Figure 2.9 Some characters that need to be backslashed.
2.1.6 Regular Expression Substitution, Capture Groups, and ELIZA
An important use of regular expressions is in substitutions. For example, the substi-substitution
tution operator s/regexp1/pattern/ used in Python and in Unix commands like
vim or sed allows a string characterized by a regular expression to be replaced by
another string:
s/colour/color/
It is often useful to be able to refer to a particular subpart of the string matching
the first pattern. For example, suppose we wanted to put angle brackets around all
integers in a text, for example, changing the 35 boxes to the <35> boxes. We’d
like a way to refer to the integer we’ve found so that we can easily add the brackets.
To do this, we put parentheses ( and ) around the first pattern and use the number
operator \1 in the second pattern to refer back. Here’s how it looks:
s/([0-9]+)/<\1>/
The parenthesis and number operators can also specify that a certain string or
expression must occur twice in the text. For example, suppose we are looking for
the pattern “the Xer they were, the Xer they will be”, where we want to constrain
the two X’s to be the same string. We do this by surrounding the first X with the
parenthesis operator, and replacing the second X with the number operator \1, as
follows:
/the (.*)er they were, the \1er they will be/
2.1 • REGULAR EXPRESSIONS 9
Here the \1 will be replaced by whatever string matched the first item in paren-
theses. So this will match The bigger they were, the bigger they will be but not The
bigger they were, the faster they will be.
This use of parentheses to store a pattern in memory is called a capture group.capture group
Every time a capture group is used (i.e., parentheses surround a pattern), the re-
sulting match is stored in a numbered register. If you match two different sets ofregister
parentheses, \2 means whatever matched the second capture group. Thus
/the (.*)er they (.*), the \1er we \2/
will match The faster they ran, the faster we ran but not The faster they ran, the
faster we ate. Similarly, the third capture group is stored in \3, the fourth is \4, and
so on.
Parentheses thus have a double function in regular expressions; they are used to
group terms for specifying the order in which operators should apply, and they are
used to capture something in a register. Occasionally we might want to use parenthe-
ses for grouping, but don’t want to capture the resulting pattern in a register. In that
case we use a non-capturing group, which is specified by putting the commandsnon-capturinggroup
?: after the open paren, in the form (?: pattern ).
/(?:some|a few) (people|cats) like some \1/
will match some cats like some people but not some people like some a few.
Substitutions and capture groups are very useful in implementing simple chat-
bots like ELIZA (Weizenbaum, 1966). Recall that ELIZA simulates a Rogerian
psychologist by carrying on conversations like the following:
User1: Men are all alike.
ELIZA1: IN WHAT WAY
User2: They’re always bugging us about something or other.
ELIZA2: CAN YOU THINK OF A SPECIFIC EXAMPLE
User3: Well, my boyfriend made me come here.
ELIZA3: YOUR BOYFRIEND MADE YOU COME HERE
User4: He says I’m depressed much of the time.
ELIZA4: I AM SORRY TO HEAR YOU ARE DEPRESSED
ELIZA works by having a series or cascade of regular expression substitutions
each of which matches and changes some part of the input lines. The first substitu-
tions change all instances of my to YOUR, and I’m to YOU ARE, and so on. The next
set of substitutions matches and replaces other patterns in the input. Here are some
examples:
s/.* I’M (depressed|sad) .*/I AM SORRY TO HEAR YOU ARE \1/
s/.* I AM (depressed|sad) .*/WHY DO YOU THINK YOU ARE \1/
s/.* all .*/IN WHAT WAY/
s/.* always .*/CAN YOU THINK OF A SPECIFIC EXAMPLE/
Since multiple substitutions can apply to a given input, substitutions are assigned
a rank and applied in order. Creating patterns is the topic of Exercise 2.3, and we
return to the details of the ELIZA architecture in Chapter 29.
2.1.7 Lookahead assertions
Finally, there will be times when we need to predict the future: look ahead in the
text to see if some pattern matches, but not advance the match cursor, so that we can
then deal with the pattern if it occurs.
10 CHAPTER 2 • REGULAR EXPRESSIONS, TEXT NORMALIZATION, EDIT DISTANCE
These lookahead assertions make use of the (? syntax that we saw in the previ-lookahead
ous section for non-capture groups. The operator (?= pattern) is true if pattern
occurs, but is zero-width, i.e. the match pointer doesn’t advance. The operatorzero-width
(?! pattern) only returns true if a pattern does not match, but again is zero-width
and doesn’t advance the cursor. Negative lookahead is commonly used when we
are parsing some complex pattern but want to rule out a special case. For example
suppose we want to match, at the beginning of a line, any single word that doesn’t
start with ”Volcano”. We can use negative lookahead to do this:
/(ˆ?!Volcano)[A-Za-z]+/
2.2 Words and Corpora
Before we talk about processing words, we need to decide what counts as a word.
Let’s start by looking at a corpus (plural corpora), a computer-readable collectioncorpus
corpora of text or speech. For example the Brown corpus is a million-word collection of sam-
ples from 500 written texts from different genres (newspaper, fiction, non-fiction,
academic, etc.), assembled at Brown University in 1963–64 (Kučera and Francis,
1967). How many words are in the following Brown sentence?
He stepped out into the hall, was delighted to encounter a water brother.
This sentence has 13 words if we don’t count punctuation marks as words, 15
if we count punctuation. Whether we treat period (“.”), comma (“,”), and so on as
words depends on the task. Punctuation is critical for finding boundaries of things
(commas, periods, colons) and for identifying some aspects of meaning (question
marks, exclamation marks, quotation marks). For some tasks, like part-of-speech
tagging or parsing or speech synthesis, we sometimes treat punctuation marks as if
they were separate words.
The Switchboard corpus of telephone conversations between strangers was col-
lected in the early 1990s; it contains 2430 conversations averaging 6 minutes each,
totaling 240 hours of speech and about 3 million words (Godfrey et al., 1992). Such
corpora of spoken language don’t have punctuation but do introduce other compli-
cations with regard to defining words. Let’s look at one utterance from Switchboard;
an utterance is the spoken correlate of a sentence:utterance
I do uh main- mainly business data processing
This utterance has two kinds of disfluencies. The broken-off word main- isdisfluency
called a fragment. Words like uh and um are called fillers or filled pauses. Shouldfragment
filled pause we consider these to be words? Again, it depends on the application. If we are
building a speech transcription system, we might want to eventually strip out the
disfluencies.
But we also sometimes keep disfluencies around. Disfluencies like uh or um
are actually helpful in speech recognition in predicting the upcoming word, because
they may signal that the speaker is restarting the clause or idea, and so for speech
recognition they are treated as regular words. Because people use different disflu-
encies they can also be a cue to speaker identification. In fact Clark and Fox Tree
(2002) showed that uh and um have different meanings. What do you think they are?
Are capitalized tokens like They and uncapitalized tokens like they the same
word? These are lumped together in some tasks (speech recognition), while for part-
of-speech or named-entity tagging, capitalization is a useful feature and is retained.
2.3 • TEXT NORMALIZATION 11
How about inflected forms like cats versus cat? These two words have the same
lemma cat but are different wordforms. A lemma is a set of lexical forms havinglemma
the same stem, the same major part-of-speech, and the same word sense. The word-
form is the full inflected or derived form of the word. For morphologically complexwordform
languages like Arabic, we often need to deal with lemmatization. For many tasks in
English, however, wordforms are sufficient.
How many words are there in English? To answer this question we need to
distinguish two ways of talking about words. Types are the number of distinct wordsword type
in a corpus; if the set of words in the vocabulary is V , the number of types is the
vocabulary size |V |. Tokens are the total number N of running words. If we ignoreword token
punctuation, the following Brown sentence has 16 tokens and 14 types:
They picnicked by the pool, then lay back on the grass and looked at the stars.
When we speak about the number of words in the language, we are generally
referring to word types.
Corpus Tokens = N Types = |V |
Shakespeare 884 thousand 31 thousand
Brown corpus 1 million 38 thousand
Switchboard telephone conversations 2.4 million 20 thousand
COCA 440 million 2 million
Google N-grams 1 trillion 13 million
Figure 2.10 Rough numbers of types and tokens for some corpora. The largest, the Google
N-grams corpus, contains 13 million types, but this count only includes types appearing 40 or
more times, so the true number would be much larger.
Fig. 2.10 shows the rough numbers of types and tokens computed from some
popular English corpora. The larger the corpora we look at, the more word types
we find, and in fact this relationship between the number of types |V | and number
of tokens N is called Herdan’s Law (Herdan, 1960) or Heaps’ Law (Heaps, 1978)Herdan’s Law
Heaps’ Law after its discoverers (in linguistics and information retrieval respectively). It is shown
in Eq. 2.1, where k and β are positive constants, and 0 < β < 1.
|V |= kNβ (2.1)
The value of β depends on the corpus size and the genre, but at least for the
large corpora in Fig. 2.10, β ranges from .67 to .75. Roughly then we can say that
the vocabulary size for a text goes up significantly faster than the square root of its
length in words.
Another measure of the number of words in the language is the number of lem-
mas instead of wordform types. Dictionaries can help in giving lemma counts; dic-
tionary entries or boldface forms are a very rough upper bound on the number of
lemmas (since some lemmas have multiple boldface forms). The 1989 edition of the
Oxford English Dictionary had 615,000 entries.
2.3 Text Normalization
Before almost any natural language processing of a text, the text has to be normal-
ized. At least three tasks are commonly applied as part of any normalization process:
1. Segmenting/tokenizing words from running text
12 CHAPTER 2 • REGULAR EXPRESSIONS, TEXT NORMALIZATION, EDIT DISTANCE
2. Normalizing word formats
3. Segmenting sentences in running text.
In the next sections we walk through each of these tasks.
2.3.1 Unix tools for crude tokenization and normalization
Let’s begin with an easy, if somewhat naive version of word tokenization and nor-
malization (and frequency computation) that can be accomplished solely in a single
UNIX command-line, inspired by Church (1994). We’ll make use of some Unix
commands: tr, used to systematically change particular characters in the input;
sort, which sorts input lines in alphabetical order; and uniq, which collapses and
counts adjacent identical lines.
For example let’s begin with the complete words of Shakespeare in one textfile,
sh.txt. We can use tr to tokenize the words by changing every sequence of non-
alphabetic characters to a newline (’A-Za-z’ means alphabetic, the -c option com-
plements to non-alphabet, and the -s option squeezes all sequences into a single
character):
tr -sc ’A-Za-z’ ’\n’ < sh.txt
The output of this command will be:
THE
SONNETS
by
William
Shakespeare
From
fairest
creatures
We
...
Now that there is one word per line, we can sort the lines, and pass them to uniq
-c which will collapse and count them:
tr -sc ’A-Za-z’ ’\n’ < sh.txt | sort | uniq -c
with the following output:
1945 A
72 AARON
19 ABBESS
25 Aaron
6 Abate
1 Abates
5 Abbess
6 Abbey
3 Abbot
...
Alternatively, we can collapse all the upper case to lower case:
tr -sc ’A-Za-z’ ’\n’ < sh.txt | tr A-Z a-z | sort | uniq -c
whose output is
2.3 • TEXT NORMALIZATION 13
14725 a
97 aaron
1 abaissiez
10 abandon
2 abandoned
2 abase
1 abash
14 abate
3 abated
3 abatement
...
Now we can sort again to find the frequent words. The -n option to sort means
to sort numerically rather than alphabetically, and the -r option means to sort in
reverse order (highest-to-lowest):
tr -sc ’A-Za-z’ ’\n’ < sh.txt | tr A-Z a-z | sort | uniq -c | sort -n -r
The results show that the most frequent words in Shakespeare, as in any other
corpus, are the short function words like articles, pronouns, prepositions:
27378 the
26084 and
22538 i
19771 to
17481 of
14725 a
13826 you
12489 my
11318 that
11112 in
...
Unix tools of this sort can be very handy in building quick word count statistics
for any corpus.
2.3.2 Word Tokenization and Normalization
The simple UNIX tools above were fine for getting rough word statistics but more
sophisticated algorithms are generally necessary for tokenization, the task of seg-tokenization
menting running text into words, and normalization, the task of putting words/tokensnormalization
in a standard format.
While the Unix command sequence just removed all the numbers and punctu-
ation, for most NLP applications we’ll need to keep these in our tokenization. We
often want to break off punctuation as a separate token; commas are a useful piece of
information for parsers, periods help indicate sentence boundaries. But we’ll often
want to keep the punctuation that occurs word internally, in examples like m.p.h,,
Ph.D.. AT&T, cap’n. Special characters and numbers will need to be kept in prices
($45.55) and dates (01/02/06); we don’t want to segment that price into separate to-
kens of “45” and “55”. And there are URLs (http://www.stanford.edu), Twitter
hashtags (#nlproc), or email addresses (someone@cs.colorado.edu).
Number expressions introduce other complications as well; while commas nor-
mally appear at word boundaries, commas are used inside numbers in English, every
three digits: 555,500.50. Languages, and hence tokenization requirements, differ
14 CHAPTER 2 • REGULAR EXPRESSIONS, TEXT NORMALIZATION, EDIT DISTANCE
on this; many continental European languages like Spanish, French, and German, by
contrast, use a comma to mark the decimal point, and spaces (or sometimes periods)
where English puts commas, for example, 555 500,50.
A tokenizer can also be used to expand clitic contractions that are marked byclitic
apostrophes, for example, converting what’re to the two tokens what are, and
we’re to we are. A clitic is a part of a word that can’t stand on its own, and can only
occur when it is attached to another word. Some such contractions occur in other
alphabetic languages, including articles and pronouns in French (j’ai, l’homme).
Depending on the application, tokenization algorithms may also tokenize mul-
tiword expressions like New York or rock ’n’ roll as a single token, which re-
quires a multiword expression dictionary of some sort. Tokenization is thus inti-
mately tied up with named entity detection, the task of detecting names, dates, and
organizations (Chapter 20).
One commonly used tokenization standard is known as the Penn Treebank to-
kenization standard, used for the parsed corpora (treebanks) released by the Lin-Penn Treebanktokenization
guistic Data Consortium (LDC), the source of many useful datasets. This standard
separates out clitics (doesn’t becomes does plus n’t), keeps hyphenated words to-
gether, and separates out all punctuation:
Input: “The San Francisco-based restaurant,” they said, “doesn’t charge $10”.
Output: “ The San Francisco-based restaurant , ” they
said , “ does n’t charge $ 10 ” .
Tokens can also be normalized, in which a single normalized form is chosen for
words with multiple forms like USA and US or uh-huh and uhhuh. This standard-
ization may be valuable, despite the spelling information that is lost in the normal-
ization process. For information retrieval, we might want a query for US to match a
document that has USA; for information extraction we might want to extract coherent
information that is consistent across differently-spelled instances.
Case folding is another kind of normalization. For tasks like speech recognitioncase folding
and information retrieval, everything is mapped to lower case. For sentiment anal-
ysis and other text classification tasks, information extraction, and machine transla-
tion, by contrast, case is quite helpful and case folding is generally not done (losing
the difference, for example, between US the country and us the pronoun can out-
weigh the advantage in generality that case folding provides).
In practice, since tokenization needs to be run before any other language pro-
cessing, it is important for it to be very fast. The standard method for tokeniza-
tion/normalization is therefore to use deterministic algorithms based on regular ex-
pressions compiled into very efficient finite state automata. Carefully designed de-
terministic algorithms can deal with the ambiguities that arise, such as the fact that
the apostrophe needs to be tokenized differently when used as a genitive marker (as
in the book’s cover), a quotative as in ‘The other class’, she said, or in clitics like
they’re. We’ll discuss this use of automata in Chapter 3.
2.3.3 Word Segmentation in Chinese: the MaxMatch algorithm
Some languages, including Chinese, Japanese, and Thai, do not use spaces to mark
potential word-boundaries, and so require alternative segmentation methods. In Chi-
nese, for example, words are composed of characters known as hanzi. Each charac-hanzi
ter generally represents a single morpheme and is pronounceable as a single syllable.
Words are about 2.4 characters long on average. A simple algorithm that does re-
2.3 • TEXT NORMALIZATION 15
markably well for segmenting Chinese, and often used as a baseline comparison for
more advanced methods, is a version of greedy search called maximum match-
ing or sometimes MaxMatch. The algorithm requires a dictionary (wordlist) of themaximummatching
language.
The maximum matching algorithm starts by pointing at the beginning of a string.
It chooses the longest word in the dictionary that matches the input at the current
position. The pointer is then advanced to the end of that word in the string. If
no word matches, the pointer is instead advanced one character (creating a one-
character word). The algorithm is then iteratively applied again starting from the
new pointer position. Fig. 2.11 shows a version of the algorithm.
function MAXMATCH(sentence, dictionary D) returns word sequence W
if sentence is empty
return empty list
for i← length(sentence) downto 1
firstword = first i chars of sentence
remainder = rest of sentence
if InDictionary(firstword, D)
return list(firstword, MaxMatch(remainder,dictionary) )
# no word was found, so make a one-character word
firstword = first char of sentence
remainder = rest of sentence
return list(firstword, MaxMatch(remainder,dictionary D) )
Figure 2.11 The MaxMatch algorithm for word segmentation.
MaxMatch works very well on Chinese; the following example shows an appli-
cation to a simple Chinese sentence using a simple Chinese lexicon available from
the Linguistic Data Consortium:
Input: 他特别喜欢北京烤鸭 “He especially likes Peking duck”
Output: 他 特别 喜欢 北京烤鸭
He especially likes Peking duck
MaxMatch doesn’t work as well on English. To make the intuition clear, we’ll
create an example by removing the spaces from the beginning of Turing’s famous
quote “We can only see a short distance ahead”, producing “wecanonlyseeashortdis-
tanceahead”. The MaxMatch results are shown below.
Input: wecanonlyseeashortdistanceahead
Output: we canon l y see ash ort distance ahead
On English the algorithm incorrectly chose canon instead of stopping at can,
which left the algorithm confused and having to create single-character words l and
y and use the very rare word ort.
The algorithm works better in Chinese than English, because Chinese has much
shorter words than English. We can quantify how well a segmenter works using a
metric called word error rate. We compare our output segmentation with a perfectword error rate
hand-segmented (‘gold’) sentence, seeing how many words differ. The word error
rate is then the normalized minimum edit distance in words between our output and
the gold: the number of word insertions, deletions, and substitutions divided by the
length of the gold sentence in words; we’ll see in Section 2.4 how to compute edit
distance. Even in Chinese, however, MaxMatch has problems, for example dealing
16 CHAPTER 2 • REGULAR EXPRESSIONS, TEXT NORMALIZATION, EDIT DISTANCE
with unknown words (words not in the dictionary) or genres that differ a lot from
the assumptions made by the dictionary builder.
The most accurate Chinese segmentation algorithms generally use statistical se-
quence models trained via supervised machine learning on hand-segmented training
sets; we’ll introduce sequence models in Chapter 10.
2.3.4 Lemmatization and Stemming
Lemmatization is the task of determining that two words have the same root, despite
their surface differences. The words am, are, and is have the shared lemma be; the
words dinner and dinners both have the lemma dinner. Representing a word by its
lemma is important for web search, since we want to find pages mentioning wood-
chucks if we search for woodchuck. This is especially important in morphologically
complex languages like Russian, where for example the word Moscow has different
endings in the phrases Moscow, of Moscow, from Moscow, and so on. Lemmatizing
each of these forms to the same lemma will let us find all mentions of Moscow. The
lemmatized form of a sentence like He is reading detective stories would thus be He
be read detective story.
How is lemmatization done? The most sophisticated methods for lemmatization
involve complete morphological parsing of the word. Morphology is the study of
the way words are built up from smaller meaning-bearing units called morphemes.morpheme
Two broad classes of morphemes can be distinguished: stems—the central mor-stem
pheme of the word, supplying the main meaning— and affixes—adding “additional”affix
meanings of various kinds. So, for example, the word fox consists of one morpheme
(the morpheme fox) and the word cats consists of two: the morpheme cat and the
morpheme -s. A morphological parser takes a word like cats and parses it into the
two morphemes cat and s, or a Spanish word like amaren (‘if in the future they
would love’) into the morphemes amar ‘to love’, 3PL, and future subjunctive. We’ll
introduce morphological parsing in Chapter 3.
The Porter Stemmer
While using finite-state transducers to build a full morphological parser is the most
general way to deal with morphological variation in word forms, we sometimes
make use of simpler but cruder chopping off of affixes. This naive version of mor-
phological analysis is called stemming, and one of the most widely used stemmingstemming
algorithms is the simple and efficient Porter (1980) algorithm. The Porter stemmerPorter stemmer
applied to the following paragraph:
This was not the map we found in Billy Bones’s chest, but
an accurate copy, complete in all things-names and heights
and soundings-with the single exception of the red crosses
and the written notes.
produces the following stemmed output:
Thi wa not the map we found in Billi Bone s chest but an
accur copi complet in all thing name and height and sound
with the singl except of the red cross and the written note
The algorithm is based on series of rewrite rules run in series, as a cascade, incascade
which the output of each pass is fed as input to the next pass; here is a sampling of
the rules:
ATIONAL → ATE (e.g., relational→ relate)
2.4 • MINIMUM EDIT DISTANCE 17
ING → ε if stem contains vowel (e.g., motoring→ motor)
SSES → SS (e.g., grasses→ grass)
Detailed rule lists for the Porter stemmer, as well as code (in Java, Python, etc.)
can be found on Martin Porter’s homepage; see also the original paper (Porter, 1980).
Simple stemmers can be useful in cases where we need to collapse across differ-
ent variants of the same lemma. Nonetheless, they do tend to commit errors of both
over- and under-generalizing, as shown in the table below (Krovetz, 1993):
Errors of Commission Errors of Omission
organization organ European Europe
doing doe analysis analyzes
numerical numerous noise noisy
policy police sparse sparsity
2.3.5 Sentence Segmentation
Sentence segmentation is another important step in text processing. The most use-Sentencesegmentation
ful cues for segmenting a text into sentences are punctuation, like periods, question
marks, exclamation points. Question marks and exclamation points are relatively
unambiguous markers of sentence boundaries. Periods, on the other hand, are more
ambiguous. The period character “.” is ambiguous between a sentence boundary
marker and a marker of abbreviations like Mr. or Inc. The previous sentence that
you just read showed an even more complex case of this ambiguity, in which the final
period of Inc. marked both an abbreviation and the sentence boundary marker. For
this reason, sentence tokenization and word tokenization may be addressed jointly.
In general, sentence tokenization methods work by building a binary classifier
(based on a sequence of rules or on machine learning) that decides if a period is part
of the word or is a sentence-boundary marker. In making this decision, it helps to
know if the period is attached to a commonly used abbreviation; thus, an abbrevia-
tion dictionary is useful.
State-of-the-art methods for sentence tokenization are based on machine learning
and are introduced in later chapters.
2.4 Minimum Edit Distance
Much of natural language processing is concerned with measuring how similar two
strings are. For example in spelling correction, the user typed some erroneous
string—let’s say graffe–and we want to know what the user meant. The user prob-
ably intended a word that is similar to graffe. Among candidate similar words,
the word giraffe, which differs by only one letter from graffe, seems intuitively
to be more similar than, say grail or graf, which differ in more letters. Another
example comes from coreference, the task of deciding whether two strings such as
the following refer to the same entity:
Stanford President John Hennessy
Stanford University President John Hennessy
Again, the fact that these two strings are very similar (differing by only one word)
seems like useful evidence for deciding that they might be coreferent.
18 CHAPTER 2 • REGULAR EXPRESSIONS, TEXT NORMALIZATION, EDIT DISTANCE
Edit distance gives us a way to quantify both of these intuitions about string sim-
ilarity. More formally, the minimum edit distance between two strings is definedminimum editdistance
as the minimum number of editing operations (operations like insertion, deletion,
substitution) needed to transform one string into another.
The gap between intention and execution, for example, is 5 (delete an i, substi-
tute e for n, substitute x for t, insert c, substitute u for n). It’s much easier to see
this by looking at the most important visualization for string distances, an alignmentalignment
between the two strings, shown in Fig. 2.12. Given two sequences, an alignment is
a correspondence between substrings of the two sequences. Thus, we say I aligns
with the empty string, N with E, and so on. Beneath the aligned strings is another
representation; a series of symbols expressing an operation list for converting the
top string into the bottom string: d for deletion, s for substitution, i for insertion.
I N T E * N T I O N
| | | | | | | | | |
* E X E C U T I O N
d s s i s
Figure 2.12 Representing the minimum edit distance between two strings as an alignment.
The final row gives the operation list for converting the top string into the bottom string: d for
deletion, s for substitution, i for insertion.
We can also assign a particular cost or weight to each of these operations. The
Levenshtein distance between two sequences is the simplest weighting factor in
which each of the three operations has a cost of 1 (Levenshtein, 1966)—we assume
that the substitution of a letter for itself, for example, t for t, has zero cost. The Lev-
enshtein distance between intention and execution is 5. Levenshtein also proposed
an alternative version of his metric in which each insertion or deletion has a cost of
1 and substitutions are not allowed. (This is equivalent to allowing substitution, but
giving each substitution a cost of 2 since any substitution can be represented by one
insertion and one deletion). Using this version, the Levenshtein distance between
intention and execution is 8.
2.4.1 The Minimum Edit Distance Algorithm
How do we find the minimum edit distance? We can think of this as a search task, in
which we are searching for the shortest path—a sequence of edits—from one string
to another.
n t e n t i o n i n t e c n t i o n i n x e n t i o n
del ins subst
i n t e n t i o n
Figure 2.13 Finding the edit distance viewed as a search problem
The space of all possible edits is enormous, so we can’t search naively. However,
lots of distinct edit paths will end up in the same state (string), so rather than recom-
puting all those paths, we could just remember the shortest path to a state each time
we saw it. We can do this by using dynamic programming. Dynamic programmingdynamicprogramming
2.4 • MINIMUM EDIT DISTANCE 19
is the name for a class of algorithms, first introduced by Bellman (1957), that apply
a table-driven method to solve problems by combining solutions to sub-problems.
Some of the most commonly used algorithms in natural language processing make
use of dynamic programming, such as the Viterbi and forward algorithms (Chap-
ter 9) and the CKY algorithm for parsing (Chapter 12).
The intuition of a dynamic programming problem is that a large problem can
be solved by properly combining the solutions to various sub-problems. Consider
the shortest path of transformed words that represents the minimum edit distance
between the strings intention and execution shown in Fig. 2.14.
n t e n t i o n
i n t e n t i o n
e t e n t i o n
e x e n t i o n
e x e n u t i o n
e x e c u t i o n
delete i
substitute n by e
substitute t by x
insert u
substitute n by c
Figure 2.14 Path from intention to execution.
Imagine some string (perhaps it is exention) that is in this optimal path (whatever
it is). The intuition of dynamic programming is that if exention is in the optimal
operation list, then the optimal sequence must also include the optimal path from
intention to exention. Why? If there were a shorter path from intention to exention,
then we could use it instead, resulting in a shorter overall path, and the optimal
sequence wouldn’t be optimal, thus leading to a contradiction.
The minimum edit distance algorithm was named by Wagner and Fischer (1974)minimum editdistance
but independently discovered by many people (summarized later, in the Historical
Notes section of Chapter 9).
Let’s first define the minimum edit distance between two strings. Given two
strings, the source string X of length n, and target string Y of length m, we’ll define
D(i, j) as the edit distance between X [1..i] and Y [1.. j], i.e., the first i characters of X
and the first j characters of Y . The edit distance between X and Y is thus D(n,m).
We’ll use dynamic programming to compute D(n,m) bottom up, combining so-
lutions to subproblems. In the base case, with a source substring of length i but an
empty target string, going from i characters to 0 requires i deletes. With a target
substring of length j but an empty source going from 0 characters to j characters
requires j inserts. Having computed D(i, j) for small i, j we then compute larger
D(i, j) based on previously computed smaller values. The value of D(i, j) is com-
puted by taking the minimum of the three possible paths through the matrix which
arrive there:
D[i, j] = min
D[i−1, j]+del-cost(source[i])
D[i, j−1]+ ins-cost(target[ j]))
D[i−1, j−1]+ sub-cost(source[i], target[ j])
If we assume the version of Levenshtein distance in which the insertions and
deletions each have a cost of 1 (ins-cost(·) = del-cost(·) = 1), and substitutions have
a cost of 2 (except substitution of identical letters have zero cost), the computation
for D(i, j) becomes:
20 CHAPTER 2 • REGULAR EXPRESSIONS, TEXT NORMALIZATION, EDIT DISTANCE
D[i, j] = min
D[i−1, j]+1
D[i, j−1]+1
D[i−1, j−1]+
{
2; if source[i] 6= target[ j]
0; if source[i] = target[ j]
(2.2)
The algorithm is summarized in Fig. 2.15; Fig. 2.16 shows the results of applying
the algorithm to the distance between intention and execution with the version of
Levenshtein in Eq. 2.2.
function MIN-EDIT-DISTANCE(source, target) returns min-distance
n←LENGTH(source)
m←LENGTH(target)
Create a distance matrix distance[n+1,m+1]
# Initialization: the zeroth row and column is the distance from the empty string
D[0,0] = 0
for each row i from 1 to n do
D[i,0]←D[i-1,0] + del-cost(source[i])
for each column j from 1 to m do
D[0,j]←D[0, j-1] + ins-cost(target[j])
# Recurrence relation:
for each row i from 1 to n do
for each column j from 1 to m do
D[i, j]←MIN( D[i−1, j] + del-cost(source[i]),
D[i−1, j−1] + sub-cost(source[i], target[j]),
D[i, j−1] + ins-cost(target[j]))
# Termination
return D[n,m]
Figure 2.15 The minimum edit distance algorithm, an example of the class of dynamic
programming algorithms. The various costs can either be fixed (e.g., ∀x, ins-cost(x) = 1)
or can be specific to the letter (to model the fact that some letters are more likely to be in-
serted than others). We assume that there is no cost for substituting a letter for itself (i.e.,
sub-cost(x,x) = 0).
Knowing the minimum edit distance is useful for algorithms like finding poten-
tial spelling error corrections. But the edit distance algorithm is important in another
way; with a small change, it can also provide the minimum cost alignment between
two strings. Aligning two strings is useful throughout speech and language process-
ing. In speech recognition, minimum edit distance alignment is used to compute
the word error rate (Chapter 31). Alignment plays a role in machine translation, in
which sentences in a parallel corpus (a corpus with a text in two languages) need to
be matched to each other.
To extend the edit distance algorithm to produce an alignment, we can start by
visualizing an alignment as a path through the edit distance matrix. Figure 2.17
shows this path with the boldfaced cell. Each boldfaced cell represents an alignment
of a pair of letters in the two strings. If two boldfaced cells occur in the same row,
there will be an insertion in going from the source to the target; two boldfaced cells
in the same column indicate a deletion.
2.4 • MINIMUM EDIT DISTANCE 21
Src\Tar # e x e c u t i o n
# 0 1 2 3 4 5 6 7 8 9
i 1 2 3 4 5 6 7 6 7 8
n 2 3 4 5 6 7 8 7 8 7
t 3 4 5 6 7 8 7 8 9 8
e 4 3 4 5 6 7 8 9 10 9
n 5 4 5 6 7 8 9 10 11 10
t 6 5 6 7 8 9 8 9 10 11
i 7 6 7 8 9 10 9 8 9 10
o 8 7 8 9 10 11 10 9 8 9
n 9 8 9 10 11 12 11 10 9 8
Figure 2.16 Computation of minimum edit distance between intention and execution with
the algorithm of Fig. 2.15, using Levenshtein distance with cost of 1 for insertions or dele-
tions, 2 for substitutions.
Figure 2.17 also shows the intuition of how to compute this alignment path. The
computation proceeds in two steps. In the first step, we augment the minimum edit
distance algorithm to store backpointers in each cell. The backpointer from a cell
points to the previous cell (or cells) that we came from in entering the current cell.
We’ve shown a schematic of these backpointers in Fig. 2.17, after a similar diagram
in Gusfield (1997). Some cells have multiple backpointers because the minimum
extension could have come from multiple previous cells. In the second step, we
perform a backtrace. In a backtrace, we start from the last cell (at the final row andbacktrace
column), and follow the pointers back through the dynamic programming matrix.
Each complete path between the final cell and the initial cell is a minimum distance
alignment. Exercise 2.7 asks you to modify the minimum edit distance algorithm to
store the pointers and compute the backtrace to output an alignment.
# e x e c u t i o n
# 0 1 2 3 4 5 6 7 8 9
i 1 ↖←↑ 2 ↖←↑ 3 ↖←↑ 4 ↖←↑ 5 ↖←↑ 6 ↖←↑ 7 ↖ 6 ← 7 ← 8
n 2 ↖←↑ 3 ↖←↑ 4 ↖←↑ 5 ↖←↑ 6 ↖←↑ 7 ↖←↑ 8 ↑ 7 ↖←↑ 8 ↖ 7
t 3 ↖←↑ 4 ↖←↑ 5 ↖←↑ 6 ↖←↑ 7 ↖←↑ 8 ↖ 7 ←↑ 8 ↖←↑ 9 ↑ 8
e 4 ↖ 3 ← 4 ↖← 5 ← 6 ← 7 ←↑ 8 ↖←↑ 9 ↖←↑ 10 ↑ 9
n 5 ↑ 4 ↖←↑ 5 ↖←↑ 6 ↖←↑ 7 ↖←↑ 8 ↖←↑ 9 ↖←↑ 10 ↖←↑ 11 ↖↑ 10
t 6 ↑ 5 ↖←↑ 6 ↖←↑ 7 ↖←↑ 8 ↖←↑ 9 ↖ 8 ← 9 ← 10 ←↑ 11
i 7 ↑ 6 ↖←↑ 7 ↖←↑ 8 ↖←↑ 9 ↖←↑ 10 ↑ 9 ↖ 8 ← 9 ← 10
o 8 ↑ 7 ↖←↑ 8 ↖←↑ 9 ↖←↑ 10 ↖←↑ 11 ↑ 10 ↑ 9 ↖ 8 ← 9
n 9 ↑ 8 ↖←↑ 9 ↖←↑ 10 ↖←↑ 11 ↖←↑ 12 ↑ 11 ↑ 10 ↑ 9 ↖ 8
Figure 2.17 When entering a value in each cell, we mark which of the three neighboring
cells we came from with up to three arrows. After the table is full we compute an alignment
(minimum edit path) by using a backtrace, starting at the 8 in the lower-right corner and
following the arrows back. The sequence of bold cells represents one possible minimum cost
alignment between the two strings.
While we worked our example with simple Levenshtein distance, the algorithm
in Fig. 2.15 allows arbitrary weights on the operations. For spelling correction, for
example, substitutions are more likely to happen between letters that are next to
each other on the keyboard. We’ll discuss how these weights can be estimated in
Ch. 5. The Viterbi algorithm, for example, is an extension of minimum edit distance
that uses probabilistic definitions of the operations. Instead of computing the “mini-
22 CHAPTER 2 • REGULAR EXPRESSIONS, TEXT NORMALIZATION, EDIT DISTANCE
mum edit distance” between two strings, Viterbi computes the “maximum probabil-
ity alignment” of one string with another. We’ll discuss this more in Chapter 9.
2.5 Summary
This chapter introduced a fundamental tool in language processing, the regular ex-
pression, and showed how to perform basic text normalization tasks including
word segmentation and normalization, sentence segmentation, and stemming.
We also introduce the important minimum edit distance algorithm for comparing
strings. Here’s a summary of the main points we covered about these ideas:
• The regular expression language is a powerful tool for pattern-matching.
• Basic operations in regular expressions include concatenation of symbols,
disjunction of symbols ([], |, and .), counters (*, +, and {n,m}), anchors
(ˆ, $) and precedence operators ((,)).
• Word tokenization and normalization are generally done by cascades of
simple regular expressions substitutions or finite automata.
• The Porter algorithm is a simple and efficient way to do stemming, stripping
off affixes. It does not have high accuracy but may be useful for some tasks.
• The minimum edit distance between two strings is the minimum number of
operations it takes to edit one into the other. Minimum edit distance can be
computed by dynamic programming, which also results in an alignment of
the two strings.
Bibliographical and Historical Notes
Kleene (1951) and (1956) first defined regular expressions and the finite automaton,
based on the McCulloch-Pitts neuron. Ken Thompson was one of the first to build
regular expressions compilers into editors for text searching (Thompson, 1968). His
editor ed included a command “g/regular expression/p”, or Global Regular Expres-
sion Print, which later became the Unix grep utility.
Text normalization algorithms has been applied since the beginning of the field.
One of the earliest widely-used stemmers was Lovins (1968). Stemming was also
applied early to the digital humanities, by Packard (1973), who built an affix-stripping
morphological parser for Ancient Greek. Currently a wide variety of code for tok-
enization and normalization is available, such as the Stanford Tokenizer (http://
nlp.stanford.edu/software/tokenizer.shtml) or specialized tokenizers for
Twitter (O’Connor et al., 2010), or for sentiment (http://sentiment.christopherpotts.
net/tokenizing.html). See Palmer (2012) for a survey of text preprocessing.
While the max-match algorithm we describe is commonly used as a segmentation
baseline in languages like Chinese, higher accuracy algorithms like the Stanford
CRF segmenter, are based on sequence models; see Tseng et al. (2005) and Chang
et al. (2008). NLTK is an essential tool that offers both useful Python libraries
(http://www.nltk.org) and textbook descriptions (Bird et al., 2009). of many
algorithms including text normalization and corpus interfaces.
For more on Herdan’s law and Heaps’ Law, see Herdan (1960, p. 28), Heaps
(1978), Egghe (2007) and Baayen (2001); Yasseri et al. (2012) discuss the relation-
ship with other measures of linguistic complexity. For more on edit distance, see the
http://nlp.stanford.edu/software/tokenizer.shtml
http://nlp.stanford.edu/software/tokenizer.shtml
http://sentiment.christopherpotts.net/tokenizing.html
http://sentiment.christopherpotts.net/tokenizing.html
http://www.nltk.org
EXERCISES 23
excellent Gusfield (1997). Our example measuring the edit distance from ‘intention’
to ‘execution’ was adapted from Kruskal (1983). There are various publicly avail-
able packages to compute edit distance, including Unix diff and the NIST sclite
program (NIST, 2005).
In his autobiography Bellman (1984) explains how he originally came up with
the term dynamic programming:
“...The 1950s were not good years for mathematical research. [the]
Secretary of Defense ...had a pathological fear and hatred of the word,
research... I decided therefore to use the word, “programming”. I
wanted to get across the idea that this was dynamic, this was multi-
stage... I thought, let’s ... take a word that has an absolutely precise
meaning, namely dynamic... it’s impossible to use the word, dynamic,
in a pejorative sense. Try thinking of some combination that will pos-
sibly give it a pejorative meaning. It’s impossible. Thus, I thought
dynamic programming was a good name. It was something not even a
Congressman could object to.”
Exercises
2.1 Write regular expressions for the following languages.
1. the set of all alphabetic strings;
2. the set of all lower case alphabetic strings ending in a b;
3. the set of all strings from the alphabet a,b such that each a is immedi-
ately preceded by and immediately followed by a b;
2.2 Write regular expressions for the following languages. By “word”, we mean
an alphabetic string separated from other words by whitespace, any relevant
punctuation, line breaks, and so forth.
1. the set of all strings with two consecutive repeated words (e.g., “Hum-
bert Humbert” and “the the” but not “the bug” or “the big bug”);
2. all strings that start at the beginning of the line with an integer and that
end at the end of the line with a word;
3. all strings that have both the word grotto and the word raven in them
(but not, e.g., words like grottos that merely contain the word grotto);
4. write a pattern that places the first word of an English sentence in a
register. Deal with punctuation.
2.3 Implement an ELIZA-like program, using substitutions such as those described
on page 9. You may choose a different domain than a Rogerian psychologist,
if you wish, although keep in mind that you would need a domain in which
your program can legitimately engage in a lot of simple repetition.
2.4 Compute the edit distance (using insertion cost 1, deletion cost 1, substitution
cost 1) of “leda” to “deal”. Show your work (using the edit distance grid).
2.5 Figure out whether drive is closer to brief or to divers and what the edit dis-
tance is to each. You may use any version of distance that you like.
2.6 Now implement a minimum edit distance algorithm and use your hand-computed
results to check your code.
24 CHAPTER 2 • REGULAR EXPRESSIONS, TEXT NORMALIZATION, EDIT DISTANCE
2.7 Augment the minimum edit distance algorithm to output an alignment; you
will need to store pointers and add a stage to compute the backtrace.
2.8 Implement the MaxMatch algorithm.
2.9 To test how well your MaxMatch algorithm works, create a test set by remov-
ing spaces from a set of sentences. Implement the Word Error Rate metric (the
number of word insertions + deletions + substitutions, divided by the length
in words of the correct string) and compute the WER for your test set.
Exercises 25
Baayen, R. H. (2001). Word frequency distributions.
Springer.
Bellman, R. (1957). Dynamic Programming. Princeton Uni-
versity Press.
Bellman, R. (1984). Eye of the Hurricane: an autobiogra-
phy. World Scientific Singapore.
Bird, S., Klein, E., and Loper, E. (2009). Natural Language
Processing with Python. O’Reilly.
Chang, P.-C., Galley, M., and Manning, C. D. (2008). Opti-
mizing Chinese word segmentation for machine translation
performance. In Proceedings of ACL Statistical MT Work-
shop, pp. 224–232.
Church, K. W. (1994). Unix for Poets. Slides from 2nd EL-
SNET Summer School and unpublished paper ms.
Clark, H. H. and Fox Tree, J. E. (2002). Using uh and um in
spontaneous speaking. Cognition, 84, 73–111.
Egghe, L. (2007). Untangling Herdan’s law and Heaps’ law:
Mathematical and informetric arguments. JASIST, 58(5),
702–709.
Godfrey, J., Holliman, E., and McDaniel, J. (1992).
SWITCHBOARD: Telephone speech corpus for research
and development. In ICASSP-92, San Francisco, pp. 517–
520.
Gusfield, D. (1997). Algorithms on Strings, Trees, and Se-
quences: Computer Science and Computational Biology.
Cambridge University Press.
Heaps, H. S. (1978). Information retrieval. Computational
and theoretical aspects. Academic Press.
Herdan, G. (1960). Type-token mathematics. The Hague,
Mouton.
Kleene, S. C. (1951). Representation of events in nerve nets
and finite automata. Tech. rep. RM-704, RAND Corpora-
tion. RAND Research Memorandum.
Kleene, S. C. (1956). Representation of events in nerve
nets and finite automata. In Shannon, C. and McCarthy,
J. (Eds.), Automata Studies, pp. 3–41. Princeton University
Press.
Krovetz, R. (1993). Viewing morphology as an inference
process. In SIGIR-93, pp. 191–202.
Kruskal, J. B. (1983). An overview of sequence compari-
son. In Sankoff, D. and Kruskal, J. B. (Eds.), Time Warps,
String Edits, and Macromolecules: The Theory and Prac-
tice of Sequence Comparison, pp. 1–44. Addison-Wesley.
Kučera, H. and Francis, W. N. (1967). Computational Anal-
ysis of Present-Day American English. Brown University
Press, Providence, RI.
Levenshtein, V. I. (1966). Binary codes capable of correcting
deletions, insertions, and reversals. Cybernetics and Con-
trol Theory, 10(8), 707–710. Original in Doklady Akademii
Nauk SSSR 163(4): 845–848 (1965).
Lovins, J. B. (1968). Development of a stemming algo-
rithm. Mechanical Translation and Computational Lin-
guistics, 11(1–2), 9–13.
NIST (2005). Speech recognition scoring toolkit (sctk) ver-
sion 2.1. http://www.nist.gov/speech/tools/.
O’Connor, B., Krieger, M., and Ahn, D. (2010). Tweetmotif:
Exploratory search and topic summarization for twitter. In
ICWSM.
Packard, D. W. (1973). Computer-assisted morphological
analysis of ancient Greek. In Zampolli, A. and Calzolari,
N. (Eds.), Computational and Mathematical Linguistics:
Proceedings of the International Conference on Computa-
tional Linguistics, Pisa, pp. 343–355. Leo S. Olschki.
Palmer, D. (2012). Text preprocessing. In Indurkhya, N.
and Damerau, F. J. (Eds.), Handbook of Natural Language
Processing, pp. 9–30. CRC Press.
Porter, M. F. (1980). An algorithm for suffix stripping. Pro-
gram, 14(3), 130–127.
Thompson, K. (1968). Regular expression search algorithm.
Communications of the ACM, 11(6), 419–422.
Tseng, H., Chang, P., Andrew, G., Jurafsky, D., and Man-
ning, C. D. (2005). Conditional random field word seg-
menter. In Proceedings of the Fourth SIGHAN Workshop
on Chinese Language Processing.
Wagner, R. A. and Fischer, M. J. (1974). The string-to-string
correction problem. Journal of the Association for Comput-
ing Machinery, 21, 168–173.
Weizenbaum, J. (1966). ELIZA – A computer program for
the study of natural language communication between man
and machine. Communications of the ACM, 9(1), 36–45.
Weizenbaum, J. (1976). Computer Power and Human Rea-
son: From Judgement to Calculation. W.H. Freeman and
Company.
Yasseri, T., Kornai, A., and Kertész, J. (2012). A practical
approach to language complexity: a wikipedia case study.
PloS one, 7(11).
http://www.nist.gov/speech/tools/
Regular Expressions, Text Normalization, Edit Distance
Regular Expressions
Basic Regular Expression Patterns
Disjunction, Grouping, and Precedence
A Simple Example
A More Complex Example
More Operators
Regular Expression Substitution, Capture Groups, and ELIZA
Lookahead assertions
Words and Corpora
Text Normalization
Unix tools for crude tokenization and normalization
Word Tokenization and Normalization
Word Segmentation in Chinese: the MaxMatch algorithm
Lemmatization and Stemming
Sentence Segmentation
Minimum Edit Distance
The Minimum Edit Distance Algorithm
Summary
Bibliographical and Historical Notes
Exercises