A constraint-based lexicalist account of the subject/object attachment preference

When a noun phrase could either be the object of the preceding verb or the subject of a new clause or a sentence complement, readers and listeners show a strong preference to parse the noun phrase as the object of the verb. This can result in clear garden paths for sentences such asThe student read the book was stolen andWhile the student read the book was stolen. Even when the verb does not permit a noun phrase complement, soem processing difficulty is still found. This has led some theorists to propose models in which initial attachments are lexically blind, with lexical information subsequently used as a filter to evaluate and revise initial analyses. In contrast, we show that these results emerge naturally from constraint-based lexicalist models. We present a modeling experiment with a simple recurrent network that was trained to predict upcoming complements for a sample of verbs taken from the Penn Treebank corpus. The model exhibits an boject bias and it aloo shows effects of verb frequency which are similar to those found in the psycholinguistic literature.

[1]  K. Rayner,et al.  Making and correcting errors during sentence comprehension: Eye movements in the analysis of structurally ambiguous sentences , 1982, Cognitive Psychology.

[2]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[3]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[4]  Donald Mitchell,et al.  Lexical guidance in human parsing: Locus and processing characteristics. , 1987 .

[5]  T. Bever,et al.  The relation between linguistic structure and associative theories of language learning—A constructive critique of some connectionist learning models , 1988, Cognition.

[6]  Don C. Mitchell,et al.  Verb guidance and other lexical effects in parsing , 1989 .

[7]  Lyn Frazier,et al.  Against lexical generation of syntax , 1989 .

[8]  Steven Abney,et al.  A computational model of human parsing , 1989 .

[9]  James L. McClelland,et al.  A distributed, developmental model of word recognition and naming. , 1989, Psychological review.

[10]  Yoav Shoham,et al.  Nonmonotonic Reasoning and Causation , 1990, Cogn. Sci..

[11]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[12]  J. Henderson,et al.  Use of verb information in syntactic parsing: evidence from eye movements and word-by-word self-paced reading. , 1990, Journal of experimental psychology. Learning, memory, and cognition.

[13]  Steven P. Abney,et al.  Parsing arguments: Phrase structure and argument structure as determinants of initial parsing decisions. , 1991 .

[14]  Edward Gibson,et al.  A computational theory of human linguistic processing: memory limitations and processing breakdown , 1991 .

[15]  Bradley L. Pritchett.  Grammatical Competence and Parsing Performance , 1992 .

[16]  Susan M. Garnsey,et al.  Verb-usage knowledge in sentence comprehension , 1992 .

[17]  Beatrice Santorini,et al.  Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[18]  M. Tanenhaus,et al.  Verb-specific constraints in sentence processing: Separating effects of lexical preference from garden-paths. , 1993 .

[19]  Maryellen C. MacDonald,et al.  The lexical nature of syntactic ambiguity resolution , 1994 .

[20]  Susan M. Garnsey,et al.  Semantic Influences On Parsing: Use of Thematic Role Information in Syntactic Ambiguity Resolution , 1994 .