DefExt: A Semi Supervised Definition Extraction Tool

TL;DR

DefExt is a semi-supervised tool that extracts definitions from texts using a CRF-based model and bootstrapping, improving accuracy over time and available as open source.

Contribution

Introduces DefExt, a semi-supervised definition extraction tool utilizing CRF and bootstrapping, with open source release and evaluation results.

Findings

Effective in extracting definitions from diverse corpora

Improves with bootstrapping to adapt to target corpus

Open source with training and test data provided

Abstract

We present DefExt, an easy to use semi supervised Definition Extraction Tool. DefExt is designed to extract from a target corpus those textual fragments where a term is explicitly mentioned together with its core features, i.e. its definition. It works on the back of a Conditional Random Fields based sequential labeling algorithm and a bootstrapping approach. Bootstrapping enables the model to gradually become more aware of the idiosyncrasies of the target corpus. In this paper we describe the main components of the toolkit as well as experimental results stemming from both automatic and manual evaluation. We release DefExt as open source along with the necessary files to run it in any Unix machine. We also provide access to training and test data for immediate use.