Learning Syntactic Patterns for Automatic Hypernym Discovery

Abstract

Semantic taxonomies such as WordNet provide a rich source of knowledge for natural language processing applications, but are expensive to build, maintain, and extend. Motivated by the problem of automatically constructing and extending such taxonomies, in this paper we present a new algorithm for automatically learning hypernym (is-a) relations from text. Our method generalizes earlier work that had relied on using small numbers of hand-crafted regular expression patterns to identify hypernym pairs. Using “dependency path” features extracted from parse trees, we introduce a general-purpose formalization and generalization of these patterns. Given a training set of text containing known hypernym pairs, our algorithm automatically extracts useful dependency paths and applies them to new corpora to identify novel pairs. On our evaluation task (determining whether two nouns in a news article participate in a hypernym relationship), our automatically extracted database of hypernyms attains both higher precision and higher recall than WordNet.

Extracted Key Phrases

4 Figures and Tables

050'05'06'07'08'09'10'11'12'13'14'15'16'17
Citations per Year

712 Citations

Semantic Scholar estimates that this publication has 712 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Snow2004LearningSP, title={Learning Syntactic Patterns for Automatic Hypernym Discovery}, author={Rion Snow and Daniel Jurafsky and Andrew Y. Ng}, booktitle={NIPS}, year={2004} }