CSE 291: Advanced Stastitical Natural Language Processing

Term: Spring Qtr 2017
Instructor: Ndapa Nakashole
Lecture: Tuesday and Thursday 3:30pm-4:50pm, EBU3B 2154
Credits: 4
Office Hours: Tuesday and Thursday 4:50pm-5.30pm



Course Description

This is a research-oriented course on statistical natural language processing (NLP). The course will focus on understanding and extending state-of-the-art machine learning algorithms for a series of important topics in NLP. The course involves reading and discussing current research papers. This course assumes background in basic machine learning. Prior NLP experience is helpful, but not required.



Course Format

Class Project

For the class project, your task is to write a 4-6 page paper, written by you alone, to extend a past NLP research contribution.
Pick a NLP paper among class readings or any paper from NLP and ML conferences.
Formatting: Please use the ACL 2017 style files. Papers longer than 6 pages of the ACL 2017 format will not be considered.
Your class paper should describe:

Recommended texts are:

[J&M] 3rd edition free chapters online
[M&S] is free online.

Syllabus (Tentative, subject to substantial change!)
Date Topic/Readings Discussion Leader(s) Homework
Apr 6 Introduction
J&M Chapter 1 Ndapa
Representation Learning for NLP
Apr 11 Goldberg, JAIR 2016 A Primer on Neural Network Models for NLP. Sections (3 and 5) only Ndapa
Mikolov et al., NIPS 2013 Distributed Representations of Words and Phrases and their Compositionality
Le and Mikolov, ICML 2014 Distributed Representations of Sentences and Documents
Machine Reading, QA, & Textual Entailment
Apr 13 Sukhbaatar et al., NIPS 2015 End-To-End Memory Networks Ndapa
Herman et al., NIPS 2015 Teaching Machines to Read and Comprehend
Mitchell et al., AAAI 2015 Never-Ending Learning
Apr 18 Shwartz et al., ACL 2016 Improving Hypernymy Detection with an an Integrated Path-based and ... Ndapa
Grycner, et al., EMNLP 2015 RELLY: Inferring Hypernym Relationships Between Relational Phrases
Apr 20 Serban et al., ACL 2016 Generating Factoid Questions With ... Ndapa
Iyyer et al., EMNLP 2014 A Neural Network for Factoid Question Answering over ...
Rajpurkar et al., EMNLP 2016 SQuAD: 100,000+ Questions for Machine Comprehension of Text
Apr 25 Bowman, et al., ACL 2016 A Fast Unified Model for Parsing and Sentence Understanding Ndapa
Kiros et al., NIPS 2015 Skip-Thought Vectors
Apr 27 Neelakatan, et al., ACL 2015 Compositional Vector Space Models for Knowledge Base Completion Ndapa
Weston et al., EMNLP 2013 Connecting Language and Knowledge Bases with ...
Part-of-Speech Tagging, NER, Morphology, & Phonology
May 2 Ling et al., EMNLP 2015 Finding Function in Form: Compositional Character Models for ...
Chiu and Nichols, TACL 2016 Named Entity Recognition with Bidirectional LSTM-CNNs
May 4 Soricut and Och, NAACL 2015 Unsupervised Morphology Induction Using Word Embeddings
Tsvetkov et al., NAACL 2016 Polyglot Neural Language Models: A Case Study in ...
Cross-lingual Projection
May 9 Hermann et al., ACL 2014 Multilingual Models for Compositional Distributed Semantic
Lazaridou et al., ACL 2015 Delving into Cross-Space Mapping for Zero-Shot Learning
Sentiment Analysis, & Social Media
May 11 Irsoy and Cardie, ACL 2014 Opinion Mining with Deep Recurrent Neural Networks
Turney, ACL 2002 Thumbs Up or Thumbs Down? Semantic Orientation Applied ...
Eisenstein, NAACL 2013 What to do about bad language on the internet
Machine Translation
May 16 Bahdanau et al., ICLR 2015 Neural Machine Translation by Jointly Learning to Align and Translate
Vinyals et al., NIPS 2015 Grammar as a Foreign Language
Sutskever, et al., NIPS 2014 Sequence to Sequence Learning with Neural Networks
May 18 Chung et al., ACL 2016 A Character-Level Decoder without Explicit Segmentation ...
Jean et al., ACL 2015 On Using Very Large Target Vocabulary for Neural Machine Translation
Johnson, et al., arxiv 2016 Enabling Zero-Shot Translation
Structured Prediction
May 23 Collins, EMNLP 2002 Theory and Experiments with Perceptron Algorithms
Collins, ACL 1998 Three Generative, Lexicalised Models for Statistical Parsing
Compositional Semantics, & Parsing
May 25 Zettlemoyer and Collins, UAI 2005 Structured Classification with Probabilistic Categorial Grammars
Steedman, 1996 A Very Short Introduction to CCG
Liang, CACM 2016 (Optional) Learning Executable Semantic Parsers for NLU
May 30 Zettlemoyer and Collins, EMNLP 2007 Online Learning of Relaxed CCG Grammars for ...
Dong and Lapata, 1996 Language to Logical Form with Neural Attention
Jun 1 Xu et al., ICML 2015 Neural Image Caption Generation with ...
Ortiz et al., NAACL 2015 Learning to Interpret and Describe Abstract Scenes
Mei et al., AAAI 2016 Mapping of Navigational Instructions to Action Sequences
Jun 5 Class presentations