Abstract

This work has been motivated by two long term goals: to understand how humans learn language and to build programs that can understand language. Using a representation that makes the relevant features explicit is a prerequisite for successful learning and understanding. Therefore, I chose to represent relations between individual words explicitly in my model. Lexical attraction is defined as the likelihood of such relations. I introduce a new class of probabilistic language models named lexical attraction models which can represent long distance relations between words and I formalize this new class of models using information theory. Within the

Citations

7320	Introduction to Algorithms - CORMEN, LEISERSON, et al. - 1985
6517	Elements of Information Theory - Cover, Thomas - 1991
5662	Probabilistic reasoning in intelligent systems: networks of plausible inference - Pearl - 1988
4409	CE: A Mathematical Theory of Communication - Shannon - 1948
1027	Aspects of the Theory of Syntax - Chomsky - 1965
883	Graph Theory - Harary - 1969
874	Error bounds for convolutional codes and an asymptotically optimum decoding algorithm - Viterbi - 1967
666	An introduction to hidden Markov models - Rabiner, Juang - 1986
556	A comprehensive grammar of the English language - Quirk, Greenbaum, et al. - 1985
540	Class-based n-gram models of natural language - Brown, Pietra, et al. - 1992
496	Statistical Language Learning - Charniak - 1993
422	An Inequality and Associated Maximization Technique in Statistical Estimation of a Markov Process - Baum - 1972
396	New Statistical Parser Based on Bigram Lexical De-pendencies - Collins - 2006
351	Syntactic Structures - Chomsky - 1957
324	Statistical Parsing with a Context-Free Grammar and Word Statistics - Charniak - 1997
317	SJ: The estimation of stochastic context-free grammars using the INSIDE-OUTSIDE algorithm. Computer Speech and Language - Lari, Young - 1990
313	Parsing english with a link grammar - Sleator, Temperley - 1993
296	Dependency Syntax: Theory and Practice - Melcuk - 1988
287	Statistical Decision-Tree Models for Parsing - Magerman - 1995
279	Prediction and entropy of printed english - SHANNON - 1951
240	Inside-Outside Reestimation from Partially Bracketed Corpora - Pereira, Schabes - 1992
232	Trainable Grammars for Speech Recognition - Baker - 1979
110	Bayesian Learning of Probabilistic Language Models - Stolcke - 1994
102	Dependency Systems and Phrase-Structure Systems - Gaifman - 1965
82	Two experiments on learning probabilistic dependency grammars from corpora - Carroll, Charniak - 1992
78	Unsupervised Language Acquisition - Marcken - 1996
60	Building Probabilistic Models for Natural Language - Chen - 1996
56	A probabilistic parsing method for sentence disambiguation - Fujisaki - 1989
49	Markov source modeling of text generation - Jelinek - 1985
41	A Model of Lexical Attraction and Repulsion - Beeferman, Berger, et al.
38	Robust Stochastic Parsing Using the Inside-Outside Algorithm - Briscoe, Waegner - 1992
33	Similarity-based approaches to natural language processing - Lee - 1997
29	Generating a grammar for statistical training - Sharman, Jelinek, et al. - 1990
24	Learning probabilistic dependency grammars from labeled text - Carroll, Charniak - 1992
17	Distibutional similarity, phase transitions and hierarchical clustering - Pereira, Tishby - 1992
6	Computer Models of Thought and - Schank, Colby - 1973
2	On the unsupervised acquisition of phrase-structure grammars - Marcken - 1995