Large-Scale Noun Compound Interpretation Using Bootstrapping and the Web as a Corpus
This work addresses the need for semantic lexical resources in natural language processing, but it is incremental as it builds on existing bootstrapping and web-based methods.
The paper tackled the problem of acquiring noun compounds with fine-grained semantic interpretations for NLP applications by using bootstrapping and web statistics, resulting in improved accuracy and a higher number of interpreted compounds when one noun is fixed.
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.