COMP6714: Information Retrieval & Web Search
Introduction to
Information Retrieval
Lecture 2: Preprocessing
1
COMP6714: Information Retrieval & Web Search
Plan for this lecture
§ Preprocessing to form the term vocabulary
§ Documents
§ Tokenization
§ What terms do we put in the index?
2
COMP6714: Information Retrieval & Web Search
Recall the basic indexing pipeline
Tokenizer
Token stream. Friends Romans Countrymen
Linguistic
modules
Modified tokens. friend roman countryman
Indexer
Inverted index.
friend
roman
countryman
2 4
2
13 16
1
Documents to
be indexed.
Friends, Romans, countrymen.
3
COMP6714: Information Retrieval & Web Search
Parsing a document
§ What format is it in?
§ pdf/word/excel/html?
§ What language is it in?
§ What character set is in use?
Each of these is a classification problem
But these tasks are often done heuristically …
Sec. 2.1
4
COMP6714: Information Retrieval & Web Search
Complications: Format/language
§ Documents being indexed can include docs from
many different languages
§ A single index may have to contain terms of several
languages.
§ Sometimes a document or its components can
contain multiple languages/formats
§ French email with a German pdf attachment.
§ What is a unit document?
§ A file?
§ An email? (Perhaps one of many in an mbox.)
§ An email with 5 attachments?
§ A group of files (PPT or LaTeX as HTML pages)
Sec. 2.1
5
COMP6714: Information Retrieval & Web Search
Introduction to
Information Retrieval
Tokens
6
COMP6714: Information Retrieval & Web Search
Tokenization
§ Input: “Friends, Romans and Countrymen”
§ Output: Tokens
§ Friends
§ Romans
§ Countrymen
§ A token is an instance of a sequence of characters
§ Each such token is now a candidate for an index
entry, after further processing
§ Described below
§ But what are valid tokens to emit?
Sec. 2.2.1
7
COMP6714: Information Retrieval & Web Search
Tokenization
§ Issues in tokenization:
§ Finland’s capital à
Finland? Finlands? Finland’s?
§ How about O’Neal?
§ Hewlett-Packard à Hewlett and Packard as two
tokens?
§ state-of-the-art: break up hyphenated sequence.
§ co-education
§ lowercase, lower-case, lower case ?
§ San Francisco: one token or two?
§ York University? New York University?
Sec. 2.2.1
8
COMP6714: Information Retrieval & Web Search
Numbers
§ 3/20/91 Mar. 20, 1991 20/3/91
§ 55 B.C.
§ B-52
§ My PGP key is 324a3df234cb23e
§ (800) 234-2333
§ Often have embedded spaces
§ Older IR systems may not index numbers
§ But often very useful: think about things like looking up error
codes/stacktraces on the web
§ Will often index “meta-data” separately
§ Creation date, format, etc.
Sec. 2.2.1
9
COMP6714: Information Retrieval & Web Search
Tokenization: language issues
§ French
§ L’ensemble à one token or two?
§ L ? L’ ? Le ?
§ Want l’ensemble to match with un ensemble
§ Until at least 2003, it didn’t on Google
§ Internationalization!
§ German noun compounds are not segmented
§ Lebensversicherungsgesellschaftsangestellter
§ ‘life insurance company employee’
§ German retrieval systems benefit greatly from a compound splitter
module
§ Can give a 15% performance boost for German
Sec. 2.2.1
10
COMP6714: Information Retrieval & Web Search
Tokenization: language issues
§ Chinese and Japanese have no spaces between
words:
§ 莎拉波娃现在居住在美国东南部的佛罗里达。
§ Not always guaranteed a unique tokenization
§ Further complicated in Japanese, with multiple
alphabets intermingled
§ Dates/amounts in multiple formats
フォーチュン500社は情報不足のため時間あた$500K(約6,000万円)
Katakana Hiragana Kanji Romaji
End-user can express query entirely in hiragana!
Sec. 2.2.1
南京市长江大桥
11
COMP6714: Information Retrieval & Web Search
Tokenization: language issues
§ Arabic (or Hebrew) is basically written right to left,
but with certain items like numbers written left to
right
§ Words are separated, but letter forms within a word
form complex ligatures
§ ← → ← → ← start
§ ‘Algeria achieved its independence in 1962 after 132
years of French occupation.’
§ With Unicode, the surface presentation is complex, but the
stored form is straightforward
Sec. 2.2.1
12
COMP6714: Information Retrieval & Web Search
Introduction to
Information Retrieval
Terms
The things indexed in an IR system
13
COMP6714: Information Retrieval & Web Search
Stop words
§ With a stop list, you exclude from the dictionary
entirely the commonest words. Intuition:
§ They have little semantic content: the, a, and, to, be
§ There are a lot of them: ~30% of postings for top 30 words
§ But the trend is away from doing this:
§ Good compression techniques (lecture 5) means the space for
including stopwords in a system is very small
§ Good query optimization techniques (lecture 7) mean you pay little
at query time for including stop words.
§ You need them for:
§ Phrase queries: “King of Denmark”
§ Various song titles, etc.: “Let it be”, “To be or not to be”
§ “Relational” queries: “flights to London” vs. “flights from London”
Sec. 2.2.2
14
COMP6714: Information Retrieval & Web Search
Normalization to terms
§ We need to “normalize” words in indexed text as
well as query words into the same form
§ We want to match U.S.A. and USA
§ Result is terms: a term is a (normalized) word type,
which is an entry in our IR system dictionary
§ We most commonly implicitly define equivalence
classes of terms by, e.g.,
§ deleting periods to form a term
§ U.S.A., USA à USA
§ deleting hyphens to form a term
§ anti-discriminatory, antidiscriminatory à antidiscriminatory
Sec. 2.2.3
15
COMP6714: Information Retrieval & Web Search
Normalization: other languages
§ Accents: e.g., French résumé vs. resume.
§ Umlauts: e.g., German: Tuebingen vs. Tübingen
§ Should be equivalent
§ Most important criterion:
§ How are your users like to write their queries for these
words?
§ Even in languages that standardly have accents, users
often may not type them
§ Often best to normalize to a de-accented term
§ Tuebingen, Tübingen, Tubingen è Tubingen
Sec. 2.2.3
16
COMP6714: Information Retrieval & Web Search
Normalization: other languages
§ Normalization of things like date forms
§ 7月30日 vs. 7/30
§ Japanese use of kana vs. Chinese characters
§ Tokenization and normalization may depend on the
language and so is intertwined with language
detection
§ Crucial: Need to “normalize” indexed text as well as
query terms into the same form
Morgen will ich in MIT …
Is this
German “mit”?
Sec. 2.2.3
17
COMP6714: Information Retrieval & Web Search
Case folding
§ Reduce all letters to lower case
§ exception: upper case in mid-sentence?
§ e.g., General Motors
§ Fed vs. fed
§ SAIL vs. sail
§ Often best to lower case everything, since
users will use lowercase regardless of
‘correct’ capitalization…
§ Google example:
§ Query C.A.T.
§ #1 result is for “cat” (well, Lolcats) not
Caterpillar Inc.
Sec. 2.2.3
18
COMP6714: Information Retrieval & Web Search
Normalization to terms
§ An alternative to equivalence classing is to do
asymmetric expansion
§ An example of where this may be useful
§ Enter: window Search: window, windows
§ Enter: windows Search: Windows, windows, window
§ Enter: Windows Search: Windows
§ Potentially more powerful, but less efficient
Sec. 2.2.3
19
COMP6714: Information Retrieval & Web Search
Thesauri and soundex
§ Do we handle synonyms and homonyms?
§ E.g., by hand-constructed equivalence classes
§ car = automobile color = colour
§ We can rewrite to form equivalence-class terms
§ When the document contains automobile, index it under car-
automobile (and vice-versa)
§ Or we can expand a query
§ When the query contains automobile, look under car as well
§ What about spelling mistakes?
§ One approach is soundex, which forms equivalence classes
of words based on phonetic heuristics
§ More in later lectures
20
COMP6714: Information Retrieval & Web Search
Introduction to
Information Retrieval
Lemmatization and Stemming
21
COMP6714: Information Retrieval & Web Search
Lemmatization
§ Reduce inflectional/variant forms to base form
§ E.g.,
§ am, are, is à be
§ car, cars, car’s, cars’ à car
§ the boy’s cars are different colors à the boy car be
different color
§ Lemmatization implies doing “proper” reduction to
dictionary headword form
Sec. 2.2.4
22
COMP6714: Information Retrieval & Web Search
Stemming
§ Reduce terms to their “roots” before indexing
§ “Stemming” suggest crude affix chopping
§ language dependent
§ e.g., automate(s), automatic, automation all reduced to
automat.
for example compressed
and compression are both
accepted as equivalent to
compress.
for exampl compress and
compress ar both accept
as equival to compress
Sec. 2.2.4
23
COMP6714: Information Retrieval & Web Search
Porter’s algorithm
§ Commonest algorithm for stemming English
§ Results suggest it’s at least as good as other stemming
options
§ Conventions + 5 phases of reductions
§ phases applied sequentially
§ each phase consists of a set of commands
§ sample convention: Of the rules in a compound command,
select the one that applies to the longest suffix.
Sec. 2.2.4
COMP6714: Information Retrieval & Web Search
Typical rules in Porter
§ s ®
§ sses ® ss
§ ies ® i
§ ational ® ate
§ tional ® tion
§ Weight of word sensitive rules
§ (m>1) EMENT →
§ replacement → replac
§ cement → cement
Sec. 2.2.4
COMP6714: Information Retrieval & Web Search
Other stemmers
§ Other stemmers exist, e.g., Lovins stemmer
§ http://www.comp.lancs.ac.uk/computing/research/stemming/general/lovins.htm
§ Single-pass, longest suffix removal (about 250 rules)
§ Full morphological analysis – at most modest
benefits for retrieval
§ Do stemming and other normalizations help?
§ English: very mixed results. Helps recall for some queries but
harms precision on others
§ E.g., operative (dentistry) ⇒ oper
§ Definitely useful for Spanish, German, Finnish, …
§ 30% performance gains for Finnish!
Sec. 2.2.4
26
COMP6714: Information Retrieval & Web Search
Language-specificity
§ Many of the above features embody transformations
that are
§ Language-specific and
§ Often, application-specific
§ These are “plug-in” addenda to the indexing process
§ Both open source and commercial plug-ins are
available for handling these
Sec. 2.2.4
27
COMP6714: Information Retrieval & Web Search
Dictionary entries – first cut
ensemble.french
時間.japanese
MIT.english
mit.german
guaranteed.english
entries.english
sometimes.english
tokenization.english
These may be
grouped by
language (or
not…).
More on this in
ranking/query
processing.
Sec. 2.2
28
COMP6714: Information Retrieval & Web Search
Resources for today’s lecture
§ IIR 2
§ MG 3.6, 4.3; MIR 7.2
§ Porter’s stemmer:
http://www.tartarus.org/~martin/PorterStemmer/
29
http://www.tartarus.org/~martin/PorterStemmer/