Axiomatic Attribution for Deep Networks Axiomatic Attribution for Deep Networks Mukund Sundararajan * 1 Ankur Taly * 1 Qiqi Yan * 1 Abstract We study the problem of attributing the pre- diction of a deep network to its input features, a problem previously studied by several other works. We identify two fundamental axioms— Sensitivity and […]
BERT Rediscovers the Classical NLP Pipeline Ian Tenney1 Dipanjan Das1 Ellie Pavlick1,2 1Google Research 2Brown University {iftenney,dipanjand,epavlick}@google.com Abstract Pre-trained text encoders have rapidly ad- vanced the state of the art on many NLP tasks. We focus on one such model, BERT, and aim to quantify where linguistic informa- tion is captured within the network. We
CS计算机代考程序代写 deep learning AI B tree BERT Rediscovers the Classical NLP Pipeline Read More »
Journal of Machine Learning Research 21 (2020) 1-67 Submitted 1/20; Revised 6/20; Published 6/20 Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer Colin Raffel∗ Noam Shazeer∗ Adam Roberts∗ Katherine Lee∗ Sharan Narang Michael Matena Yanqi Zhou Wei Li Peter J. Liu Google, Mountain View, CA 94043, USA Editor: Ivan Titov Abstract Transfer
Published as a conference paper at ICLR 2019 WHAT DO YOU LEARN FROM CONTEXT? PROBING FOR SENTENCE STRUCTURE IN CONTEXTUALIZED WORD REPRESENTATIONS Ian Tenney,∗1 Patrick Xia,2 Berlin Chen,3 Alex Wang,4 Adam Poliak,2 R. Thomas McCoy,2 Najoung Kim,2 Benjamin Van Durme,2 Samuel R. Bowman,4 Dipanjan Das,1 and Ellie Pavlick1,5 1Google AI Language, 2Johns Hopkins University, 3Swarthmore
Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond Mikel Artetxe University of the Basque Country (UPV/EHU)∗ mikel. Holger Schwenk Facebook AI Research Abstract We introduce an architecture to learn joint multilingual sentence representations for 93 languages, belonging to more than 30 different families and written in 28 different scripts. Our system uses a
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 1870–1879 Vancouver, Canada, July 30 – August 4, 2017. c©2017 Association for Computational Linguistics https://doi.org/10.18653/v1/P17-1171 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 1870–1879 Vancouver,
arXiv:1510.03055v2 [cs.CL] 7 Jan 2016 ar X iv :1 51 0. 03 05 5v 2 [ cs .C L ] 7 J an 2 01 6 A Diversity-Promoting Objective Function for Neural Conversation Models Jiwei Li1∗ Michel Galley2 Chris Brockett2 Jianfeng Gao2 Bill Dolan2 1Stanford University, Stanford, CA, USA 2Microsoft Research, Redmond, WA, USA {mgalley,chrisbkt,jfgao,billdol}@microsoft.com
OF WIKIPEDIA: KNOWLEDGE-POWERED CONVERSATIONAL AGENTS Emily Dinan∗, Stephen Roller∗, Kurt Shuster∗, Angela Fan, Michael Auli, Jason Weston Facebook AI Research {edinan,roller,kshuster,angelafan,michaelauli,jase}@fb.com ABSTRACT In open-domain dialogue intelligent agents should exhibit the use of knowledge, however there are few convincing demonstrations of this to date. The most popu- lar sequence to sequence models typically “generate and hope”
Generating Visual Explanations Lisa Anne Hendricks1 Zeynep Akata2 Marcus Rohrbach1,3 Jeff Donahue1 Bernt Schiele2 Trevor Darrell1 1UC Berkeley EECS, CA, United States 2Max Planck Institute for Informatics, Saarbrücken, Germany 3ICSI, Berkeley, CA, United States Abstract. Clearly explaining a rationale for a classification decision to an end-user can be as important as the decision itself. Existing
CS388 Natural Language Processing: Final Project Final Report Due Date: Friday, December 10 at 6:59pm CST Collaboration You are free to work on this project in teams of two (encouraged) or individually. Indi- vidual projects can be less ambitious but should not be less complete: a half-implemented system does not make a good project outcome.
CS计算机代考程序代写 deep learning CS388 Natural Language Processing: Final Project Read More »