UC Merced Proceedings of the Annual Meeting of the Cognitive Science Society Title Modeling Attachment Decisions with a Probabilistic Parser : The Case of Head Final Structures

We describe an incremental, two-stage probabilistic model of human parsing for German. The model is broad coverage, i.e., it assigns sentence structure to previously unseen text with high accuracy. It also makes incremental predictions of the attachment decisions for PP attachment ambiguities. We test the model against reading time data from the literature and find that it makes correct predictions for verb second sentences; however, the model is not able to account for reading times data for verb final structures because attachment preferences in our training data do not match those determined experimentally. We argue that this points to more general limitations with our type of probabilistic model when it comes to realizing processing strategies that are independent of the data the parsing model is trained on.

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

[2]  Helmut Schmid,et al.  LoPar: Design and Implementation , 2000 .

[3]  Helmut Feldweg,et al.  GermaNet - a Lexical-Semantic Net for German , 1997 .

[4]  Mirella Lapata,et al.  Evaluating and Combining Approaches to Selectional Preference Acquisition , 2003, EACL.

[5]  J. Trueswell.  THE ROLE OF LEXICAL FREQUENCY IN SYNTACTIC AMBIGUITY RESOLUTION , 1996 .

[6]  Yuki Kamide,et al.  Incremental Pre-Head Attachment in Japanese Parsing. , 1999 .

[7]  Daniel Jurafsky,et al.  A Probabilistic Model of Lexical and Syntactic Access and Disambiguation , 1996, Cogn. Sci..

[8]  M. Brysbaert,et al.  Modifier Attachment in Sentence Parsing: Evidence from Dutch , 1996 .

[9]  Sabine Schulte im Walde.  A Subcategorisation Lexicon for German Verbs induced from a Lexicalised PCFG , 2002, LREC.

[10]  Mats Rooth,et al.  Structural Ambiguity and Lexical Relations , 1991, ACL.

[11]  Lars Konieczny,et al.  The Role of Lexical Heads in Parsing: Evidence from German , 1997 .

[12]  Martin Volk,et al.  Exploiting the WWW as a corpus to resolve PP attachment ambiguities , 2001 .

[13]  Frank Keller,et al.  Probabilistic Parsing for German Using Sister-Head Dependencies , 2003, ACL.

[14]  P. Frasconi,et al.  Learning first-pass structural attachment preferences with dynamic grammars and recursive neural networks , 2003, Cognition.

[15]  M W Crocker,et al.  Wide-Coverage Probabilistic Sentence Processing , 2000, Journal of psycholinguistic research.

[16]  Wojciech Skut,et al.  An Annotation Scheme for Free Word Order Languages , 1997, ANLP.

[17]  Stephen Clark,et al.  Class-based probability estimation using a semantic hierarchy , 2001, HTL 2001.

[18]  Frank Keller,et al.  Using the Web to Obtain Frequencies for Unseen Bigrams , 2003, CL.

[19]  Susan M. Garnsey,et al.  The Contributions of Verb Bias and Plausibility to the Comprehension of Temporarily Ambiguous Sentences , 1997 .

[20]  John Hale,et al.  A Probabilistic Earley Parser as a Psycholinguistic Model , 2001, NAACL.