Corpus-Based Lexical Acquisition For Semantic Parsing

Building accurate and e cient natural language processing (NLP) systems is an important and di cult problem. There has been increasing interest in automating this process. The lexicon, or the mapping from words to meanings, is one component that is typically di cult to update and that changes from one domain to the next. Therefore, automating the acquisition of the lexicon is an important task in automating the acquisition of NLP systems. This proposal describes a system, Wolfie (WOrd Learning From Interpreted Examples), that learns a lexicon from input consisting of sentences paired with representations of their meanings. Preliminary experimental results show that this system can learn correct and useful mappings. The correctness is evaluated by comparing a known lexicon to one learned from the training input. The usefulness is evaluated by examining the e ect of using the lexicon learned by Wolfie to assist a parser acquisition system, where previously this lexicon had to be hand-built. Future work in the form of extensions to the algorithm, further evaluation, and possible applications is discussed.

[1]  T. Regier.  Learning Spatial Concepts Using a Partially-structured Connectionist Architecture \above" Lm Tr Figure 1: Learning to Associate Scenes with Spatial Terms , 1991 .

[2]  Bernard Mérialdo,et al.  Tagging English Text with a Probabilistic Model , 1994, CL.

[3]  Kenneth Ward Church,et al.  Word Association Norms, Mutual Information, and Lexicography , 1989, ACL.

[4]  Barbara Landau,et al.  Where's what and what's where: The language of objects in space , 1994 .

[5]  Jeffrey Mark Siskind,et al.  Naive physics, event perception, lexical semantics, and language acquisition , 1992 .

[6]  Sharon C. Salveter.  Inferring Conceptual Graphs , 1979, Cogn. Sci..

[7]  Jeffrey Mark Siskind,et al.  Lexical Acquisition in the Presence of Noise and Homonymy , 1994, AAAI.

[8]  James L. McClelland,et al.  Mechanisms of Sentence Processing: Assigning Roles to Constituents of Sentences , 1986 .

[9]  Michael Lebowitz,et al.  Experiments with incremental concept formation: UNIMEM , 2004, Machine Learning.

[10]  LebowitzMichael.  Experiments with Incremental Concept Formation , 1987 .

[11]  Matthew W. Crocker,et al.  Mechanisms for Sentence Processing , 1996 .

[12]  Ellen Riloff,et al.  Automatically Constructing a Dictionary for Information Extraction Tasks , 1993, AAAI.

[13]  Chris Mellish,et al.  Natural Language Processing in PROLOG , 1989 .

[14]  Patrick Suppes,et al.  Complexity Issues in Robotic Machine Learning of Natural Language , 1992 .

[15]  Mallory Selfridge.  A Computer Model of Child Language Learning , 1986, Artif. Intell..

[16]  C. L. Baker,et al.  The Logical problem of language acquisition , 1984 .

[17]  Pat Langley.  Simplicity and Representation Change in Grammar Induction , 1995 .

[18]  Christoph M. Hoffmann,et al.  Pattern Matching in Trees , 1982, JACM.

[19]  Naftali Tishby,et al.  Algebraic learning of statistical associations for language acquisition , 1994, Comput. Speech Lang..

[20]  Andreas Stolcke.  Learning Feature-based Semantics with Simple Recurrent Networks , 1990 .

[21]  Steven Pinker,et al.  Resolving a learnability paradox in the acquisition of the verb lexicon. , 1989 .

[22]  John R. Anderson,et al.  Induction of Augmented Transition Networks , 1977, Cogn. Sci..

[23]  Richard Granger,et al.  FOUL-UP: A Program that Figures Out Meanings of Words from Context , 1977, IJCAI.

[24]  Martin Kay,et al.  Text-Translation Alignment , 1993, Comput. Linguistics.

[25]  Steven L. Lytinen,et al.  The Ups and Downs of Lexical Acquisition , 1994, AAAI.

[26]  R. Kazman.  Simulating the Child's Acquisition of the Lexicon and Syntax—Experiences With Babel , 1994 .

[27]  Robert C. Berwick,et al.  The acquisition of syntactic knowledge , 1985 .

[28]  Fumiyo Fukumoto.  Representation and Acquisition of Verbal Polysemy , 1995 .

[29]  Eugene Charniak,et al.  Statistical language learning , 1997 .

[30]  George A. Miller,et al.  Introduction to WordNet: An On-line Lexical Database , 1990 .

[31]  Masahiko Haruno.  A Case Frame Learning Method for Japanese Polysemous Verbs , 1995 .

[32]  Michael J. Pazzani,et al.  A Lexical Based Semantic Bias for Theory Revision , 1995, ICML.

[33]  Carl de Marcken.  Acquiring a Lexicon from Unsegmented Speech , 1995, ACL.

[34]  Risto Miikkulainen,et al.  Subsymbolic natural language processing - an integrated model of scripts, lexicon, and memory , 1993, Neural network modeling and connectionism.

[35]  P. Langley,et al.  Concept formation in structured domains , 1991 .

[36]  E. Markman,et al.  When it is better to receive than to give: Syntactic and conceptual constraints on vocabulary growth , 1994 .

[37]  Eric Brill,et al.  Automatic Grammar Induction and Parsing Free Text: A Transformation-Based Approach , 1993, ACL.

[38]  Michael R. Brent,et al.  Automatic Acquisition of Subcategorization Frames from Tagged Text , 1991, HLT.

[39]  John M. Zelle,et al.  Using inductive logic programming to automate the construction of natural language parsers , 1996 .

[40]  Raymond J. Mooney,et al.  Learning Semantic Grammars with Constructive Inductive Logic Programming , 1993, AAAI.

[41]  Robert C. Berwick,et al.  Learning Word Meanings From Examples , 1983, IJCAI.

[42]  Ellen M. Markman,et al.  Constraints on word meaning in early language acquisition , 1994 .

[43]  Uri Zernik,et al.  Lexical acquisition: Exploiting on-line resources to build a lexicon. , 1991 .

[44]  J. G. Wolff,et al.  Cognitive development as optimisation , 1987 .