Lexical Adaptation of Link Grammar to the Biomedical Sublanguage: a Comparative Evaluation of Three Approaches

TL;DR

This paper evaluates three methods for adapting the Link Grammar Parser to biomedical language, demonstrating that combining a domain-specific POS tagger with other techniques significantly improves parsing accuracy and efficiency.

Contribution

It introduces and compares three approaches for lexical adaptation of Link Grammar to biomedical text, highlighting the effectiveness of using a domain-specific POS tagger.

Findings

45% increase in parsing efficiency

10% relative decrease in error with POS tagging

Best approach combines multiple adaptation techniques

Abstract

We study the adaptation of Link Grammar Parser to the biomedical sublanguage with a focus on domain terms not found in a general parser lexicon. Using two biomedical corpora, we implement and evaluate three approaches to addressing unknown words: automatic lexicon expansion, the use of morphological clues, and disambiguation using a part-of-speech tagger. We evaluate each approach separately for its effect on parsing performance and consider combinations of these approaches. In addition to a 45% increase in parsing efficiency, we find that the best approach, incorporating information from a domain part-of-speech tagger, offers a statistically signicant 10% relative decrease in error. The adapted parser is available under an open-source license at http://www.it.utu.fi/biolg.