Statistical Decision-Tree Models for Parsing

TL;DR

This paper introduces SPATTER, a statistical decision-tree parser that constructs complete syntactic analyses for sentences, significantly outperforming traditional grammar-based parsers on large, ambiguous text corpora.

Contribution

The paper presents a novel decision-tree based statistical parser, SPATTER, which relies on lexical and contextual information, achieving superior accuracy over existing grammar-based methods.

Findings

SPATTER achieves 86-91% precision and recall on Wall Street Journal data.

SPATTER outperforms IBM's grammar-based parser in experiments.

The parser effectively handles sentences up to 40 words with high accuracy.

Abstract

Syntactic natural language parsers have shown themselves to be inadequate for processing highly-ambiguous large-vocabulary text, as is evidenced by their poor performance on domains like the Wall Street Journal, and by the movement away from parsing-based approaches to text-processing in general. In this paper, I describe SPATTER, a statistical parser based on decision-tree learning techniques which constructs a complete parse for every sentence and achieves accuracy rates far better than any published result. This work is based on the following premises: (1) grammars are too complex and detailed to develop manually for most interesting domains; (2) parsing models must rely heavily on lexical and contextual information to analyze sentences accurately; and (3) existing {$n$}-gram modeling techniques are inadequate for parsing models. In experiments comparing SPATTER with IBM's computer manuals parser, SPATTER significantly outperforms the grammar-based parser. Evaluating SPATTER against the Penn Treebank Wall Street Journal corpus using the PARSEVAL measures, SPATTER achieves 86\% precision, 86\% recall, and 1.3 crossing brackets per sentence for sentences of 40 words or less, and 91\% precision, 90\% recall, and 0.5 crossing brackets for sentences between 10 and 20 words in length.