I have graduated from MIT EECS and my homepage has been moved. This page is no longer maintained

I am a graduate student at MIT and a member of NLP group at CSAIL.

My research advisor is Prof. Regina Barzilay.

I can be contacted at (first name)(last name)@csail.mit.edu.


Publications

I have graduated from MIT EECS and my homepage has been moved.

Interpretable Neural Models for Natural Language Processing  Phd Thesis
Tao Lei. MIT, Feburary 2017
[ Paper ] [ Slides ]
 
Style Transfer from Non-Parallel Text by Cross-Alignment  NIPS 2017
Tianxiao Shen, Tao Lei, Regina Barzilay and Tommi Jaakkola
[ Paper ] [ Slides ] [ Code ]
 
Training RNNs as Fast as CNNs  Technical report
Tao Lei, Yu Zhang and Yoav Artzi
[ Paper ] [ Code ]
 
Deriving Neural Architectures from Sequence and Graph Kernels  ICML 2017
Tao Lei*, Wengong Jin*, Regina Barzilay and Tommi Jaakkola (*: Equal contribution)
[ Paper ] [ Code ]
 
Rationalizing Neural Predictions  EMNLP 2016
Tao Lei, Regina Barzilay and Tommi Jaakkola
[ Paper ] [ Slides ] [ Code ]
 
Learning to Refine Text Based Recommendations  EMNLP 2016
Youyang Gu, Tao Lei, Regina Barzilay and Tommi Jaakkola
[ Paper ] [ Code ]
 
Semi-supervised Question Retrieval with Gated Convolutions  NAACL 2016
Tao Lei, Hrishikesh Joshi, Regina Barzilay, Tommi Jaakkola, Katerina Tymoshenko, Alessandro Moschitti and Lluís Màrquez
[ Paper ] [ Slides (keynote) ] [ Slides (pdf) ] [ Code ]
 
Making Dependency Labeling Simple, Fast and Accurate  NAACL 2016
Tianxiao Shen, Tao Lei and Regina Barzilay
[ Paper ] [ Code ]
 
Molding CNNs for Text: Non-linear, Non-consecutive Convolutions  EMNLP 2015
Tao Lei, Regina Barzilay and Tommi Jaakkola.
[ Paper ] [ Poster ] [ Code ]
 
High-Order Low-Rank Tensors for Semantic Role Labeling  NAACL 2015
Tao Lei, Yuan Zhang, Lluís Màrquez, Alessandro Moschitti and Regina Barzilay.
[ Paper ] [ Slides ] [ Code ]
 
Exploring Compositional Architectures and Word Vector Representations for Prepositional Phrase Attachment  TACL 2014
Yonatan Belinkov, Tao Lei, Regina Barzilay and Amir Globerson.
[ Paper ] [ Data ]
 
Greed is Good if Randomized: New Inference for Dependency Parsing  EMNLP 2014
Yuan Zhang*, Tao Lei*, Regina Barzilay and Tommi Jaakkola. (*: Equal contribution)
[ Paper ] [ Proof ] [ Slides ] [ Code ]
 
Low-Rank Tensors for Scoring Dependency Structures  ACL 2014  [Best student paper]
Tao Lei, Yu Xin, Yuan Zhang, Regina Barzilay and Tommi Jaakkola.
[ Paper ] [ Slides ] [ Code ]
 
Steps to Excellence: Simple Inference with Refined Scoring of Dependency Trees  ACL 2014
Yuan Zhang, Tao Lei, Regina Barzilay, Tommi Jaakkola and Amir Globerson
[ Paper ] [ Slides ] [ Code ]
 
From Natural Language Specifications to Program Input Parsers  ACL 2013
Tao Lei, Fan Long, Regina Barzilay and Martin Rinard.
[ Paper ] [ Slides ] [ Code & Data ]
 
Learning High-Level Planning from Text  ACL 2012
S.R.K. Branavan, Nate Kushman, Tao Lei and Regina Barzilay.
[ Paper ] [ Code & Data ]
 
A Pattern Tree-based Approach to Learning URL Normalization Rules  WWW 2010
Tao Lei, Rui Cai, Jiang-Ming Yang, Yan Ke, Xiaodong Fan and Lei Zhang.
[ Paper ]