Download:
|
by John M. Zelle, Raymond J. Mooney
In Wermter, S., Riloff, E., & Scheler, G. (Eds.), Connectionist, Statistical, and Symbolic Approaches to Learning for Natural Language Processing
ftp://ftp.cs.utexas.edu/pub/mooney/papers/chill-bkchapter-95.ps.Z
Add To MetaCart
Abstract:
Abstract. This paper presents results from recent experiments with Chill, a corpus-based parser acquisition system. Chill treats language acquisition as the learning of search-control rules within a logic program. Unlike many current corpus-based approaches that use statistical learning algorithms, Chill uses techniques from inductive logic programming (ILP) to learn relational representations. Chill is a very flexible system and has been used to learn parsers that produce syntactic parse trees, case-role analyses, and executable database queries. The reported experiments compare Chill's performance to that of a more naive application of ILP to parser acquisition. The results show that ILP techniques, as employed in Chill, are a viable alternative to statistical methods and that the control-rule framework is fundamental to Chill's success. 1
Citations
|
1134
|
Building a large annotated corpus of English: The Penn Treebank
– Marcus, Santorini, et al.
- 1993
|
|
843
|
Efficient induction of logic programs
– Muggleton, Feng
- 1990
|
|
747
|
Learning logical definitions from relations
– Quinlan
- 1990
|
|
223
|
Structural ambiguity and lexical relations
– Hindle, Rooth
- 1993
|
|
155
|
Foil: A midterm report
– Quinlan, Cameron-Jones
- 1993
|
|
154
|
Machine invention of first-order predicates by inverting resolution
– Muggleton, Buntine
- 1988
|
|
145
|
E.: A procedure for Quantitatively Comparing the Syntactic Coverage of English Grammars
– Black
- 1991
|
|
136
|
Mechanisms of sentence processing: Assigning roles to constituents of sentences
– McClelland, Kawamoto
- 1986
|
|
132
|
S.: Towards Historybased Grammars: Using Richer Models for Probabilistic Parsing
– Black, Jelinek, et al.
- 1993
|
|
128
|
Automatic acquisition of a large subcategorization dictionary from corpora
– Manning
- 1993
|
|
119
|
The Acquisition of Syntactic Knowledge
– Berwick
- 1985
|
|
112
|
Automatic grammar induction and parsing free text: A transformation-based approach
– Brill
- 1993
|
|
89
|
Protein secondary structure prediction using logic
– Muggleton, King, et al.
- 1992
|
|
75
|
Natural language processing with modular neural networks and distributed lexicon
– Miikkulainen, Dyer
- 1991
|
|
64
|
Learning semantic grammars with constructive inductive logic programming
– Zelle, Mooney
- 1993
|
|
62
|
Induction of first-order decision lists : Results on learning the past tense of english verbs
– Mooney, Califf
- 1995
|
|
46
|
Development and evaluation of a broad-coverage probabilistic grammar of English-language computer manuals
– Black, Lafferty, et al.
- 1992
|
|
44
|
Context-sensitive statistics for improved grammatical language models
– Charniak, Carroll
- 1994
|
|
44
|
Discrimination-based constructive induction of logic programs
– Kijsirikul, Numao, et al.
- 1992
|
|
37
|
The Acquisition and Use of Context-dependent Grammars for English
– Simmons, Yu
- 1992
|
|
36
|
Hidden Understanding Models of natural Language
– Miller, Bobrow, et al.
- 1994
|
|
31
|
Combining top-down and bottom-up methods in inductive logic programming
– Zelle, Mooney
- 1994
|
|
29
|
Inducing deterministic Prolog parsers from treebanks: A machine learning approach
– Zelle, Mooney
- 1994
|
|
23
|
Using Inductive Logic Programming to Automate the Construction of Natural Language Parsers
– Zelle
- 1995
|
|
16
|
Inside-outside reestimation from partially bracketed corpora
– Periera, Shabes
- 1992
|
|
15
|
Natrual Lagnuage Parsing as Statistical Pattern Recognition
– Magerman
- 1994
|
|
10
|
Toward the essential nature of satistical knowledge in sense resolution
– Lehman
- 1994
|
|
9
|
Inducing logic programs without explicit negative examples
– Zelle, Thompson, et al.
- 1995
|
|
4
|
Turbo Prolog 2.0 Reference Guide
– International
- 1988
|
