论文信息 - Enriching the Output of a Parser Using Memory-based Learning

Enriching the Output of a Parser Using Memory-based Learning

We describe a method for enriching the output of a parser with information available in a corpus. The method is based on graph rewriting using memory-based learning, applied to dependency structures. This general framework allows us to accurately recover both grammatical and semantic information as well as non-local dependencies. It also facilitates dependency-based evaluation of phrase structure parsers. Our method is largely independent of the choice of parser and corpus, and shows state of the art performance.

Valentin Jijkoun | M. de Rijke | Maarten de Rijke | V. Jijkoun

[1] Valentin Jijkoun,et al. The University of Amsterdam at Senseval-3: Semantic roles and Logic forms , 2004, SENSEVAL@ACL.

[2] Amit Dubey,et al. Antecedent Recovery: Experiments with a Trace Tagger , 2003, EMNLP.

[3] Valentin Jijkoun,et al. Finding Non-local Dependencies: Beyond Pattern Matching , 2003, ACL.

[4] Michael Collins,et al. Head-Driven Statistical Models for Natural Language Parsing , 2003, CL.

[5] Mark Johnson,et al. A Simple Pattern-matching Algorithm for Recovering Empty Nodes and their Antecedents , 2002, ACL.

[6] Julia Hockenmaier. Parsing with Generative Models of Predicate-Argument Structure , 2003, ACL.

[7] Ted Briscoe,et al. Parser evaluation: using a grammatical relation annotation scheme , 2003 .

[8] Dan Klein,et al. Accurate Unlexicalized Parsing , 2003, ACL.

[9] Eugene Charniak,et al. Assigning Function Tags to Parsed Text , 2000, ANLP.

[10] Walter Daelemans,et al. TiMBL: Tilburg Memory-Based Learner, version 2.0, Reference guide , 1998 .

[11] Eugene Charniak,et al. A Maximum-Entropy-Inspired Parser , 2000, ANLP.