Large-Scale Noun Compound Interpretation Using Bootstrapping and the Web as a Corpus

TL;DR

This paper presents a bootstrapping method leveraging web data to automatically interpret noun compounds with fine-grained semantic relations, enhancing semantic resource creation for NLP.

Contribution

It introduces a novel bootstrapping approach that jointly extracts noun compounds and their semantic interpretations using web statistics, improving accuracy and coverage.

Findings

Higher number of interpreted NCs with fixed compounds

Improved accuracy due to semantic restrictions

Effective use of web data for semantic extraction

Abstract

Responding to the need for semantic lexical resources in natural language processing applications, we examine methods to acquire noun compounds (NCs), e.g., "orange juice", together with suitable fine-grained semantic interpretations, e.g., "squeezed from", which are directly usable as paraphrases. We employ bootstrapping and web statistics, and utilize the relationship between NCs and paraphrasing patterns to jointly extract NCs and such patterns in multiple alternating iterations. In evaluation, we found that having one compound noun fixed yields both a higher number of semantically interpreted NCs and improved accuracy due to stronger semantic restrictions.