Ling7800: Advanced Computational Linguistics: Lexical Semantics
Spring 2010
Time and Location: Monday/Wednesday 11-12:15, Hellems 291, begining Jan 20, MUEN D 424, ICS small conference room (4th floor of MUEN, to the right)
Assessment: Presentation of two papers, two homeworks and a term project.
Office Hours: Monday 2:30-3:30 and Wednesday 3-4
Instructor:
Martha Palmer
Textbook: Semantic Role Labeling (eBook),
Martha Palmer, Daniel Gildea, Nianwen Xue, In
Synthesis Lectures on Human
Language Technologies , ed., Graeme Hirst, Morgan & Claypool, 2010.
ISBN: 9781598298321
Theme
One of the great challenges of Natural Language
Processing is the multitude of choices that language gives us for
expressing the same thing in different ways. This is obviously true when
taking other languages into consideration - the same thought can be
expressed in English, French, Chinese or Russian, with widely varying
results. But it is also true when considering a single language such as
English. Light verb constructions, nominalizations, idioms, slang,
paraphrases, and synonyms all give us myriads of alternatives for "coining
a phrase."
With respect to other languages, one solution that has
been often touted is that of an "interlingua:" a universal, language neutral
semantic representation that all languages could be mapped onto. This
approach has an immediate appeal, since it would obviate the need for
specific translation systems for every possible pair of languages.
Instead, it would only be necessary to build systems for each individual
language that can produce the interlingua representation from an analysis
of the sentences in the language, and that can generate fluent sentences
from interlingua representations. As desirable as this may seem, and in
spite of the tremendous effort that has gone into this quest, the
realization of a suitable "interlingua" has proven to be elusive.
The students in this course will be encouraged to form their own opinion of the
feasibility of hand-crafted semantic representations, as opposed to more
automatic techniques that are purely statistical. We will
explore in depth alternative styles of semantic representations, and
compare and contrast their contributions to finding a useful, common
semantic representation that can bridge lexical and structural gaps both
mono-lingually and multi-lingually. We will look particularly closely at
semantic role labeling as an instance of automatically assigning semantic
representations. We will also explore alternative
styles of semantic annotations and their cross-linguistic application.
Suggested Schedule and Readings - Open to Modification
Introduction and Module 1: the Lexical Semantics of Verbs - Chap 1
- Jan 11 Natural Language Processing, a case study - Pundit
- Jan 13, Case Theory and Schedule Planning
Fillmore, C. J. 1968 "The Case for Case" in E. Bach and R.T. Harms, eds.
Universals in Linguistic Theory, 1-88. New York: Holt,
Rinehart and Winston. Section 3. paper and
slides
- Jan 20, Lexical Conceptual Structure
Jackendoff, R.S. 1976 Towards an Explanatory Semantic Representation, Linguistic Inquiry, 7:1, pp. 89-150. paper Second half paper
and slides
- Jan 25, Proto-roles
Dowty D.R 1991 Thematic Proto-Roles and Argument Selection. Language 67: 547-619 sections 1-7 paper and slides
- Jan 27 Levin Classes
Levin, B. English Verb Classes: A Preliminary Classification Introduction,MIT Press, pp. 1-23, 1990., paper and slides
Homework 1 is due
Module 2: Available Lexical Resources - Chap 2
- Feb 1 FrameNet
Fillmore, Charles J. and Atkins, B. T. S. (1998): FrameNet and lexicographic relevance, Proceedings of the First International Conference on Language Resources and Evaluation, Granada, Spain.(The quality of the print may be compromised, as the paper was scanned; as such, it is also a very large file.) paper on this page
Fillmore et al 2001 "Building a large lexical databank which provides deep
semantics"
Available at:
FrameNet
Fillmore, C.J. 1977 Scenes-and-Frames Semantics in Fundamental Studies in
Computer Science: Linguistics Structures Processing, Ed. Antonio Zampolli,
pp. 55-81 paper on this page .
- Feb 3 VerbNet Travis Rood
Karin Kipper, Anna Korhonen, Neville Ryant, and Martha Palmer. Extending VerbNet with Novel Verb Classes. Fifth International Conference on Language Resources and Evaluation (LREC 2006). Genoa, Italy. June, 2006.
papers
Karin Kipper, Anna Korhonen, Neville Ryant, and Martha Palmer. Extensive Classifications of English verbs. Proceedings of the 12th EURALEX International Congress. Turin, Italy. September, 2006.
- Feb 8 PropBank: Claire Bonial
Martha Palmer, Dan Gildea, Paul Kingsbury, The Proposition Bank: An Annotated Corpus of Semantic Roles, Computational Linguistics, 31:1 , pp. 71-105, March, 2005.
paper
- Feb 10 Semlink and Hierarchical Sense Distinctions
Martha Palmer, Hoa Dang and Christiane Fellbaum,
Making Fine-grained and Coarse-grained sense distinctions, both manually
and automatically, Journal of Natural Language Engineering,
draft and slides
- Feb 15 Homework 1 Review
- Feb 17 Applications - Entailments Ifeyinwa Okoye
Rodney Nielsen, Wayne Ward, Jim Martin,
Recognizing Entailment in Intelligent Tutoring Systems, JNLE, 2007.
- Feb 22
Verbs for BioInformatics, guest lecturers:
Karin Verspoor and Kevin Bretonnel Cohen
Homework 2 is due
Module 3: Representations of Events - Student Presentations Begin
- Feb 24, part A Event Semantics I Will Corvey
Davidson D. 1967. "The Logical Form of Action Sentences" Reprinted in Davidson
D: Essays on Actions and Events, Oxford University Press
(1980) paper
- Feb 24, part B Event Semantics II Claire Bonial
Parsons T. 1990 Events in Semantics of English . MIT Press, Boston
paper and
Slides
- March 1, part A The Generative Lexicon Ashwini Vaidya
Pustejovsky, The Generative Lexicon
Pustejovsky J 1991, The Generative Lexicon, ComputationaI Linguistics, Volume 17, Number 4, December. Paper
- March 1, part B Event Structure and TimeBank Keith Mertz
Pustejovsky, J., Castaqo, J., Ingria, R., Saurm, R., Gaizauskas, R.,
Setzer, A. and Katz, G. TimeML: Robust Specification of Event and
Temporal Expressions in Text. In Proceedings of the Fifth International
Workshop on Computational Semantics (IWCS-5), 2003
paper
- March 3 Building Verb Meanings Tim O'Gorman
Rappaport M. and B.Levin 1998 "Building Verb Meanings" in Butt, Geuder,
eds. The Projection of Arguments: Lexical and Compositional
Factors, CSLI Publications paper
- March 8 Cognitive Semantics James Foster
Talmy, L., Toward a Cognitive Semantics - Volume 2: Typology and Process in Concept Structuring (Language, Speech, and Communication), Chapter 1 Lexicalization Patterns
here and
slides
- March 10 The role of null arguments in converting from a Hindi dependency treebank to a phrase structure treebank Ashwini Vaidya and Archna Bhattia
- March 15a LCS as an Interlingua Sam Perdue
slides
Dorr, Bonnie, Eduard Hovy and Lori Levin,(2004)
Machine Translation: Interlingual Methods , Encyclopedia of Language and
Linguistics 2nd edition" Brown, Keith (eds.).
- March 15b Event Coreference Will Corvey,
slides
Event Coreference for Information Extraction, Humphreys et al, 1997
- March 17 Semantic Features and Verb Classes
Oliver Culo, Katrin Erk, Sebastian Pado and Sabine Schulte im Walde.
Comparing and Combining Semantic Verb Classifications.
Language Resources and Evaluation 42(3), 2008
- March 22, 24 Spring Break
Module 4: Automatic Semantic Role Labeling - Chap 3
- March 29 Machine Learning Lee Becker, Shumin Wu
Tom M. Mitchell, 2006, Machine Learning Department technical report CMU-ML-06-108, Carnegie Mellon University,
The Discipline of Machine Learning
- March 31 Machine Learning continued
Slides
- April 5, 7 Automatic Semantic Role Labeling Chapters 3 & 4
Slides
- Machine Learning Resources/Links
Dan Klein's Machine
Learning for Natural Language Processing: New Developments and Challenges
(slides and video)
Michael Collins tutorial on NLP
Introduction to Machine Learning, S V N Vishwanathan
Weka, a collection of machine learning algorithms for data mining tasks.
Orange, Open source data visualization and analysis for novice and experts. Data mining through visual programming or Python scripting.
Videos of Andrew Ng's Stanford ML course
Noah Smith's course titled Language and Statistics,
at CMU
- April 12 Statistical Methods for doing semantics guest lecturer:
Karin Verspoor
P. D. Turney and P. Pantel (2010)
"From Frequency to Meaning: Vector Space Models of Semantics" ,
Journal of Artificial Intelligence Research, Volume 37, pages 141-188. and
slides.
- April 14 Granularity Issues
Szu-ting Yi; Edward Loper; Martha Palmer
Can Semantic Roles Generalize Across Genres?, NAACL-2007. - Ashwini Vaidya
Paola Merlo and Lonneke van der Plas,
Abstraction and Generalisation in Semantic Role Labels: PropBank, VerbNet or both?
Parameterized Action Representations, Travis Rood
Karin Kipper and Martha Palmer,(2000),
Representation of Actions as an Interlingua,
Proceedings of the Third Workshop on Applied Interlinguas,
held in conjunction with ANLP-NAACL 2000.
Module 5. Prelimnary Student Project Presentations Continued
- April 19 Ifeyinwa Okoye
Dmitry Davidov; Ari Rappoport,
Classification of Semantic Relationships between Nominals Using Pattern Clusters
- April 21 Claire Bonial
Sag, I., Baldwin, T. Bond, F., Copestake, A., Flickinger, D. 2002.
Multiword expressions: A pain in the neck for NLP.
In Proceedings of Intelligent Text processing Computational Linguistics (CICLING 2002), p. 1-15, Mexico City, Mexico.
- Sam Perdue
Chikara Hashimoto, Sadao Kurohashi, 2007.
Construction of Domain Dictionary for Fundamental Vocabulary ACL2007, Prague, the Czech Republic.
- April 26 Keith Mertz,
Chapter 5 of
Steven Bethard, 2007,
Finding Event, Temporal and Causal Structure in Text:
A Machine Learning Approach, , Ph.D. Thesis, University of Colorado.
- Tim O'Gorman
Cohen, Kevin Bretonnel, Martha Palmer, and Lawrence Hunter.
"Nominalization and Alternations in Biomedical Language"
PLoS ONE 3(9). September, 2008. p. 1-21.
- April 28 James Foster
Roberto Navigli, Meaningful Clustering of Senses Helps Boost Word Sense Disambiguation Performance, In the Proceedings of ACL2006, Sydney, Australia paper
Module Last. Project Presentations
- Final Exam Time: Monday, May 3, 4:00 p.m. - 8:00 p.m.
ICS Large Conference Room (D430/428)
Module Extra. Possible Additional Paper Presentations
Additional Semantic Role Labeling papers from book bib
Innovative Approaches to SRL
- ACL-09
Beqat Zapirain; Eneko Agirre; Llums M`rquez,
Generalizing over Lexical Features: Selectional Preferences for Semantic Role Classification
Weiwei Sun; Zhifang Sui; Meng Wang
Prediction of Thematic Rank for Structured Semantic Role Labeling
- EMNLP-09
Hai Zhao; Wenliang Chen; Chunyu Kit
Semantic Dependency Parsing of NomBank and PropBank: An Efficient Integrated Approach via a Large-scale Feature Selection
- CoNLL-08
Richard Johansson; Pierre Nugues,
Dependency-based Syntactic Semantic Analysis with PropBank and NomBank
- EMNLP-08
BEST Paper Award
Hoifung Poon; Pedro Domingos,
Unsupervised Semantic Parsing
- COLING-04
V Punyakanok, D Roth, W Yih, D Zimak,
Semantic role labeling via integer linear programming inference
- SWiRL
Mihai Surdeanu, Lluis Marquez, Xavier Carreras, and Pere R. Comas.
Combination Strategies for Semantic Role Labeling.
Journal of Artificial Intelligence Research 29 (2007).
Applications of SRL
Induction of Semantic Relations
WSD
- EMNLP-08
Zhi Zhong; Hwee Tou Ng; Yee Seng Chan
Word Sense Disambiguation Using OntoNotes: An Empirical Study
-
Navigli, Roberto and Paola Velardi and Alessandro Cucchiarelli and Francesca Neri. ``Extending and Enriching WordNet with OntoLearn" In: Proceedings of the Second Global WordNet Conference , pp. 279-284, Brno, Czech Republic, January 20-23, 2004. paper
NAACL03 Workshop on Text Meaning
HLT-NAACL 2003 ACL Anthology Web Page
W03-0902:Schubert L, Tong M. "Extracting and Evaluating General World Knowledge from the
Brown Corpus" in Proceedings of the NLT-NAACL 2003 Workshop.
Proceedings of the HLT-NAACL 2003 Workshop on Text Meaning
W03-0901:Clark P, Harrison P., and J. Thomson "A Knowledge-Driven Approach to Text Meaning Processing", in Proceedings of the HLT-NAACL 2003 Workshop on Text Meaning. slides