To support incremental interpretation, any model of human sentence processing must not only process the sentence incrementally, it must to some degree restrict the number of analyses which it produces for any sentence prefix. Deterministic parsing takes the extreme position that there can only be one analysis for any sentence prefix. Experiments with an incremental statistical parser show that performance is severely degraded when the search for the most probable parse is pruned to only the most probable analysis after each prefix. One method which has been extensively used to address the difficulty of deterministic parsing is lookahead, where information about a bounded number of subsequent words is used to decide which analyses to pursue. We simulate the effects of lookahead by summing probabilities over possible parses for the lookahead words and using this sum to choose which parse to pursue. We find that a large improvement is achieved with one word lookahead, but that more lookahead results in relatively small additional improvements. This suggests that one word lookahead is sufficient, but that other modifications to our left-corner parsing model could make deterministic parsing more effective.
[1]
Beatrice Santorini,et al.
Building a Large Annotated Corpus of English: The Penn Treebank
,
1993,
CL.
[2]
James Henderson.
Inducing History Representations for Broad Coverage Statistical Parsing
,
2003,
HLT-NAACL.
[3]
Heekuck Oh,et al.
Neural Networks for Pattern Recognition
,
1993,
Adv. Comput..
[4]
Adwait Ratnaparkhi,et al.
A Maximum Entropy Model for Part-Of-Speech Tagging
,
1996,
EMNLP.
[5]
Giovanni Soda,et al.
Wide Coverage Incremental Parsing by Learning Attachment Preferences
,
2001,
AI*IA.
[6]
Mitchell P. Marcus,et al.
A theory of syntactic recognition for natural language
,
1979
.
[7]
Eugene Charniak,et al.
A Maximum-Entropy-Inspired Parser
,
2000,
ANLP.
[8]
Rens Bod.
An efficient implementation of a new DOP model
,
2003,
EACL.
[9]
Bob Carpenter,et al.
Probabilistic Parsing using Left Corner Language Models
,
1997,
IWPT.
[10]
Thorsten Brants,et al.
Probabilistic Parsing and Psychological Plausibility
,
2000,
COLING.
[11]
Michael Collins,et al.
Head-Driven Statistical Models for Natural Language Parsing
,
2003,
CL.