Weakly supervised definition extraction

Abstract

Definition Extraction (DE) is the task to extract textual definitions from naturally occurring text. It is gaining popularity as a prior step for constructing taxonomies, ontologies, automatic glossaries or dictionary entries. These fields of application motivate greater interest in well-formed encyclopedic text from which to extract definitions, and therefore DE for academic or lay discourse has received less attention. In this paper we propose a weakly supervised bootstrapping approach for identifying textual definitions with higher linguistic variability than the classic encyclopedic genus-et-differentia definition, and take the domain of Natural Language Processing as a use case. We also introduce a novel set of features for DE and explore their relevance. Evaluation is carried out on two datasets that reflect opposed ways of expressing definitional knowledge.