A Linear Observed Time Statistical Parser Based on Maximum Entropy Models

Abstract

This paper presents a statistical parser for natural language that obtains a parsing accuracy---roughly 87% precision and 86% recall---which surpasses the best previously published results on the Wall St. Journal domain. The parser itself requires very little human intervention, since the information it uses to make parsing decisions is specified in a concise and simple manner, and is combined in a fully automatic way under the maximum entropy framework. The observed running time of the parser on a test sentence is linear with respect to the sentence length. Furthermore, the parser returns several scored parses for a sentence, and this paper shows that a scheme to pick the best parse from the 20 highest scoring parses could yield a dramatically higher accuracy of 93% precision and recall.

10 pages, LaTeX, uses aclap.sty, qtree.sty, to appear in EMNLP-2

Cited by in corpus (12)

• Grammar as a Foreign Language
• Memory-Based Shallow Parsing
• Chunk Tagger - Statistical Recognition of Noun Phrases
• Structured Training for Neural Network Transition-Based Parsing
• Big Data and Cross-Document Coreference Resolution: Current State and Future Opportunities
• Measuring efficiency in high-accuracy, broad-coverage statistical parsing
• Shift-Reduce Constituent Parsing with Neural Lookahead Features
• Richer Syntactic Dependencies for Structured Language Modeling
• Bunsetsu Identification Using Category-Exclusive Rules
• Probabilistic top-down parsing and language modeling
• Lexicalized Stochastic Modeling of Constraint-Based Grammars using Log-Linear Measures and EM Training
• Portability of Syntactic Structure for Language Modeling