Efficient incremental beam-search parsing with generative and discriminative models: keynote talk

Authors:
Brian Roark
Affiliations:
Oregon Health & Science University
Venue:
IncrementParsing '04 Proceedings of the Workshop on Incremental Parsing: Bringing Engineering and Cognition Together
Year:
2004

Citing 8
Cited 0

Learning to Parse Natural Language with Maximum Entropy Models

Machine Learning - Special issue on natural language learning
Discriminative Reranking for Natural Language Parsing

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Towards Incremental Parsing of Natural Language Using Recursive Neural Networks

Applied Intelligence
Probabilistic top-down parsing and language modeling

Computational Linguistics
Robust garden path parsing

Natural Language Engineering
Estimators for stochastic "Unification-Based" grammars

ACL '99 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics
New ranking algorithms for parsing and tagging: kernels over discrete structures, and the voted perceptron

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Incremental parsing with the perceptron algorithm

ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

This talk will present several issues related to incremental (left-to-right) beam-search parsing of natural language using generative or discriminative models, either individually or in combination. The first part of the talk will provide background in incremental top-down and (selective) left-corner beam-search parsing algorithms, and in stochastic models for such derivation strategies. Next, the relative benefits and drawbacks of generative and discriminative models with respect to heuristic pruning and search will be discussed. A range of methods for using multiple models during incremental parsing will be detailed. Finally, we will discuss the potential for effective use of fast, finite-state processing, e.g. part-of-speech tagging, to reduce the parsing search space without accuracy loss. POS-tagging is shown to improve efficiency by as much as 20-25 percent with the same accuracy, largely due to the treatment of unknown words. In contrast, an 'islands-of-certainty' approach, which quickly annotates labeled bracketing over low-ambiguity word sequences, is shown to provide little or no efficiency gain over the existing beam-search.