Natural Language

Natural Language is one of the crucial aspects of human intelligence that has been studied extensively in Artificial Intelligence Research. In recent years, there has been a resurgence in research in language understanding and processing fueled by technologies such as search, question answering and interactive drama.

What is all the excitement about? How do we make computers interpret human language, how does it work, how is it applied, what research is ongoing to improve it? We'll discuss a range of topics such as representation, acquisition, syntax, semantics and different learning methods for the same. The class will be run as a senior undergraduate / graduate research class, with a mix of lectures, paper readings, in-class discussions, and hands-on projects.

Recommended Texts (Optional):

Understanding Language Understanding: Computational Models of Reading Edited by Ashwin Ram and Kenneth Moorman
Natural Language Understanding. Benjamin/Cummings, 2ed, James Allen.

Projects:

Sep 18: Project 1 due : Assignment 1 (2 weeks) (Solutions)
Oct 1: Term Project brainstorm open
Oct 5: Project 2 due : Assignment 2 (2 weeks) (Solutions)
Oct 6: Term Project teaming open
Oct 18: Term Project proposal due
Nov 4: Term Project 1st milestone due (2 weeks)
Nov 20: Term Project 2nd milestone due (3 weeks)
Nov 25 - Dec 4: Term Project presentations
Dec 11: Term Project final paper due (including final milestones and project submission)

Project Paper Template: doc
Class Blog: http://fall08nlgt.blogspot.com

Schedule:

Foundations	Foundations
Tue Aug 19 Introduction	Thu Aug 21 Introduction
Foundations	Foundations
Tue Aug 26 Paper 1: Scripts, Plans, Goals, and Understanding: An Inquiry into Human Knowledge Structures (Ch 1-2) Authors: Robert P Abelson, Roger C Schank ch1 ch2 Presentation: Anupreet Walia ppt Critique: Anushree Venkatesh ppt Paper 2: Language Analysis and Understanding, in Survey of the State of the Art in Human Language Technology (1997) Section 3.1, 3.2, 3.6, 3.7 ch 3 Presentation: Sneha Chandrababu Critique: Gagan Malik	Thu Aug 28 Paper 1: Natural Language Processing in Information Retrieval, Google inc. Author: Thorsten Brants pdf Presentation: Steven Crain pdf Critique: Anupreet Walia Critique Paper 2: Ontologies in Support of Problem Solving, In Staab, S. and Studer, R., editor, Handbook on Ontologies in Information Systems, International Handbooks on Information Systems. Springer, In press. Authors: M. Crubezy and M. A. Musen pdf Presentation: Alejandro Dominguez Critique: Purna Mehta
Language Models	Parsing
Tue Sep 2 Paper 1: A study of smoothing methods for language models applied to ad hoc information retrieval, In 24th ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'01), 2001. Authors: C. Zhai and J. Lafferty pdf Presentation:Anushree Venkatesh pdf Critique: Nicholas Marquez Paper 2: A language modeling approach to predicting reading difficulty. In Proceedings of the HLT/NAACL 2004 Conference. Boston. Authors: K. Collins-Thompson and J. Callan pdf Presentation: Neha Deodhar Critique: Anupreet Walia Critique	Thu Sep 4 Paper 1: Grammars and Parsing (Chapter 3) Author: James Allen PDF Presentation: Travis Gockel PPT Critique: Alejandro Dominguez Paper 2: Features and Augmented Grammars (Chapter 4) Author: James Allen PDF Presentation: Anupreet Walia ppt Critique: Anushree Venkatesh pdf
Parsing	Parsing
Tue Sep 9 Paper 1: Generating Typed Dependency Parses from Phrase Structure Parses. 5th International Conference on Language Resources and Evaluation (LREC 2006), pp. 449-454. Author: Marie-Catherine de Marneffe, Bill MacCartney, and Christopher D. Manning pdf Presentation: Sneha Chandrababu Critique: Neha Deodhar Paper 2: A robust parsing algorithm for link grammars. Proceedings of the Fourth International Workshop on Parsing Technologies, Prague, September, 1995 Authors: Dennis Grinberg, John Lafferty and Daniel Sleator. 1995. pdf Presentation: Madhav Deshpande Critique: Aninda Ray	Thu Sep 11 Paper 1: Sentence Processing in Understanding: Interaction and Integration of Knowledge Sources Authors: Kavi Mahesh, Kurt P. Eiselt, and Jennifer K. Holbrook PDF Presentation: Aninda Ray Critique: Nitisha Warkari Paper 2: Computing Semantic Similarity between Skill Statements for Approximate Matching , HLT-NAACL 2007. Authors: Pan, Feng, Farrell, Robert pdf Presentation: Alejandro Dominguez Critique: Mugdha Jamsandekar
Ambiguity Resolution	Knowledge Representation
Tue Sep 16 Paper 1: Unsupervised word sense disambiguation rivaling supervised methods. ACL 95 Author: David Yarowsky pdf Presentation: Ruchir Gupta Critique: Ajay Choudhari Paper 2: Scaling to Very Very Large Corpora for Natural Language Disambiguation. ACL 2001 Authors: Michele Banko and Eric Brill pdf Presentation: Ajay Choudhari Critique: Nihar Gadkari	Thu Sep 18 Paper 1: Capturing the Contents of Complex Narratives Authors: Eric Domeshek, Eric Jones, and Ashwin Ram PDF Presentation: Bryan Wiltgen Critique: Travis Gockel PDF Paper 2: Methodologies for the Reliable Construction of Ontological Knowledge Author: Eduard Hovy pdf Presentation: Nitin Kumar Critique: Akshay Phadke
Semantics	Semantics
Tue Sep 23 Paper 1: A Connectionist Model of Narrative Comprehension Authors: Mark C. Langston, Tom Trabasso, and Joseph P. Magliano PDF Presentation: Samantha Misra Critique: Bryan Wiltgen Paper 2: The Proposition Bank: An Annotated Corpus of Semantic Roles, Computational Linguistics , December, 2003. Authors: Martha Palmer, Dan Gildea, Paul Kingsbury pdf Presentation: Purna Mehta Critique: Steven Crain pdf	Thu Sep 25 Paper 1: Towards Robust Semantic Role Labeling, Computational Linguistics Authors: Sameer Pradhan, Wayne Ward and James H. Martin pdf Presentation: Nihar Gadkari Critique: Chien-Ming Huang Paper 2: The Theory Underlying Concept Maps and How to Construct and Use Them , Technical Report IHMC CmapTools Authors: Joseph D. Novak & Alberto J. Cañas pdf Presentation: Gagan Malik Critique: Travis GockelPDF
Semantics	Tagging and Shallow Parsing
Tue Sep 30 Paper 1: Semantic taxonomy induction from heterogenous evidence. Proceedings of COLING/ACL 2006, Sydney. (ACL Best Paper Award) Authors: Rion Snow, Dan Jurafsky, and Andrew Y. Ng pdf Presentation: Mugdha Jamsandekar Critique: Madhav Deshpande Paper 2: Learning concept hierarchies from text corpora using formal concept analysis , Journal of Artificial Intelligence Research, 2005 Authors: P Cimiano, A Hotho, S Staab pdf Presentation: Bryan Wiltgen Critique: Nicholas Marquez	Thu Oct 2 Paper 1:Shallow Semantic Parsing using Support Vector Machiens Authors: Sameer Pradhan, Wayne Ward, Kadri Hacioglu, James H. Martin, Dan Jurafsky pdf Presentation: Neha Deodhar Critique: Akshay Phadke Paper 2: The Talent System: TEXTRACT Architecture and Data Model (2004), Natural Language Engineering 10 (3/4): 307–326. Authors: Mary S. Neff, Roy J. Byrd and Branimir K. Boguraev PDF Presentation: Neha Kharsikar Critique: Gagan Malik
Retrieval	Memory
Tue Oct 7 Paper 1: Scaling Spreading Activation for Information Retrieval Authors: Anthony Francis, Mark Devaney, Juan Santamaria, Ashwin Ram pdf Presentation: Ajay Choudhari Critique: Ajay Choudhari Paper 2: Modern Information Retrieval: A Brief Overview. In IEEE Data Engineering Bulletin 24(4), pages 35-43, 2001. Author: Amit Singhal pdf Presentation: Samantha Misra Critique: Vighnesh Venkatesan	Thu Oct 9 Paper 1: Retrieval from Episodic Memory by Inferencing and Disambiguation Authors: Trent E. Lange and Charles M. Wharton pdf Presentation: Madhav Deshpande Critique: Nitisha Paper 2: A capacity theory of comprehension: Individual differences in working memory. Psychological Review, Vol 99(1), Jan 1992. pp. 122-149. Authors: Just, Marcel A., Carpenter, Patricia A. PDF Presentation: Karan Mehra Critique: Neha Deodhar
	Comprehension
Tue Oct 14 Fall Break	Thu Oct 16 Paper 1: The Acquisition of Reading Comprehension Skill, The Science of Reading: A Handbook, 2008 Authors: Charles A. Perfetti, Nicole Landi, Jane Oakhill PDF Presentation: Karan Mehra Critique: Ruchir Gupta Paper 2: Recency preference in the human sentence processing mechanism , Cognition. 1996 Apr;59(1):23-59 Authors: Gibson E, Pearlmutter N, Canseco-Gonzalez E, Hickok G. PDF Presentation: Aniket Patil pdf Critique: Sneha Chandrababu
Contextualization/Meta-reasoning	Novelty
Tue Oct 21 Paper 1: Three Computer-Based Models of Storytelling: BRUTUS, MINSTREL and MEXICA Author: Rafael Pérez y Pérez, Mike Sharples PDF Presentation: Nitisha Warkari Critique: Karan Mehra Paper 2: On the intersection of Story Understanding and Learning Authors: Michael T. Cox and Ashwin Ram PDF Presentation: Akshay Phadke Critique: Samantha Misra	Thu Oct 23 Paper 1: Creativity in Reading: Understanding Novel Concepts Authors: Kenneth Moorman and Ashwin Ram PDF Presentation: Harikrishnappt Critique: Bryan Wiltgen Paper 2: Story Planning as Exploratory Creativity: Techniques for Expanding the Narrative Search Space Authors: Mark Riedl and R. Michael Young pdf Presentation: Nicholas Marquez Critique: Aninda Ray
Summarization	Categorization/Extraction
Tue Oct 28 Paper 1: Single Document Summarization Using Natural Language Processing Authors: J. Jagadeesh and Vasudeva Varma pdf Presentation: Mugdha Jamsandekar Critique: Abhinav Karhu Paper 2: LexRank: Graph-based Lexical Centrality as Salience in Text Summarization ", Journal of Artificial Intelligence Research (JAIR) , 2004, 22:457-479 Authors: Gunes Erkan and Dragomir Radev pdf Presentation: Chien-Ming Huang Critique: Steven Crain pdf	Thu Oct 30 Paper 1: Machine Learning in Automated Text Categorisation (1999) Author: Fabrizio Sebastiani pdf Presentation: Aninda Ray Critique: Vighnesh Venkatesan Paper 2: Discovering Semantic Biomedical Relations utilizing the Web , ACM Transactions on Knowledge Discovery from Data, 2(1):3, 2008 Authors: Saurav Sahay, Sougata Mukherjea, Eugene Agichtein, Ernest Garcia, Sham Navathe and Ashwin Ram pdf Presentation: Nitin Kumar> Critique: Neha Kharsikar
Industrial Applications and Product Reviews	HealthCare 2.0/Enterprise 2.0
Tue Nov 4 Paper 1: Semantic Wave 2008 Report: Industry Roadmap to Web 3.0 & Multibillion Dollar Market Opportunities, Project10X Author: Mills Davis pdf Presentation: Neha Kharsikar Critique: Nitin Kumar Analysis of Powerset, Hakia and True Knowledge technologies Presentation: Purna Mehta Critique: Aniket Patil pdf Analysis of 'News At Seven',FeedHub and Open Calais technologies Presentation: Nitisha Warkari Critique: Harikrishna ppt	Thu Nov 6 Paper 1: The emerging Web 2.0 social software: an enabling suite of sociable technologies in health and health care education , Health Info Libr J. 2007 Mar;24(1):2-23 Authors: Kamel Boulos MN, Wheeler S pdf Presentation: Aniket Patil pdf Critique: Aniket Patil Paper 2: Semantic Search, WWW2003 Authors: R. Guha, Rob McCool and Eric Miller pdf Presentation: Chien-Ming Huang Critique:
Interactive Drama	Conversational Agents
Tue Nov 11 Paper 1: Natural Language Understanding in Façade: Surface-text Processing, TIDSE 04 Authors: Michael Mateas, Andrew Stern pdf Presentation: Vighnesh Venkatesan Critique: Ruchir Gupta Paper 2: Interactive Storytelling with Literary Feelings, ACII 07 Authors: David Pizzi, Fred Charles, Jean-Luc Lugrin and Marc Cavazza pdf Presentation: Abhinav Karhu Critique: Mugdha Jamsandekar	Thu Nov 13 Paper 1: Cobot in LambdaMOO: A Social Statistics Agent, AAAI 2000 Authors: Charles Lee Isbell, Jr., Michael Kearns, Dave Kormann, Satinder Singh and Peter Stone pdf Presentation: Harikrishna ppt Critique: Madhav Deshpande Paper 2: EMERGING TECHNOLOGIES Bots as Language Learning Tools Authors: Luke Fryer, Rollo Carpenter pdf Presentation: Akshay Phadke Critique: Abhinav Karhu
Question Answering	Intelligent Interfaces/Personalization
Tue Nov 18 Paper 1: Structured Retrieval for Question Answering , Proceedings of the 30th Annual International ACM SIGIR Conference on Research & Development on Information Retrieval. Authors: Bilotti, Matthew, Paul Ogilvie, Jamie Callan and Eric Nyberg pdf Presentation: Anushree Venkatesh Critique: Purna Mehta Paper 2: Finding the Right Facts in the Crowd: Factoid Question Answering over Social Media . WWW2008 Authors: Jiang Bian, Yandong Liu, Eugene Agichtein, Hongyuan Zha pdf Presentation: Steven Crain pdf Critique: Chien-Ming Huang	Thu Nov 20 Paper 1: User Interfaces and Visualization, a textbook chapter in Modern Information Retrieval, edited by Ricardo Baeza-Yates and Berthier Ribeiro-Neto Author: Marti Hearst pdf Presentation: Nihar Gadkari Critique: Samantha Misra Paper 2: Personalized Web Exploration with Task Models, WWW08 Authors: Jae-wook Ahn, Peter Brusilovsky, Daqing He, Jonathan Grady, Qi Li pdf Presentation: Abhinav Karhu Critique: Nitin Kumar
Term Project Work Time
Tue Nov 25	Thu Nov 27 Thanksgiving Holiday
Term Project Presentations	Term Project Presentations
Tue Dec 2 Project 2: PUN - Pun Understanding in NLP BY Anushree Venkatesh, Anupreet Walia, Ruchir Gupta Project 3: Understanding Stories represented as Unstructured Data BY Sneha Chandrababu, Abhinav Karhu, Madhav Deshpande Project 4: Lyrics based Music Recommendation System BY Neha Deodhar, Karan Mehra, Gagan Malik Project 5: Medical conversation tagging BY Alejandro Dominguez	Thu Dec 4 Project 1: Feature Based Product Summarization for Online Reviews BY Ajay Choudhari, Nihar Gadkari, Nitin Kumar, Purna Mehta Project 2: Movie Recommendation System BY Aninda Ray, MUgdha Jamsandekar, Nitisha Warkari Project 3: Book Summarization BY Steven Crain, Travis Gockel, Chien-Ming Huang, Alex Marquez, Bryan Wiltgen Project 4: Stock Price Prediction BY Samantha Misra, Harikrishna, Vighnesh