A Linear Observed Time Statistical Parser Based on Maximum Entropy Models

TL;DR

This paper introduces a maximum entropy-based statistical parser for natural language that achieves high accuracy with linear runtime and minimal human intervention, outperforming previous results on the Wall St. Journal domain.

Contribution

The paper presents a novel linear-time statistical parser using maximum entropy models that requires little human effort and improves parsing accuracy over prior methods.

Findings

Achieves roughly 87% precision and 86% recall on Wall St. Journal data.

Linear runtime complexity with respect to sentence length.

Using top 20 parses can increase accuracy to 93%.

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.