Improving Scientific Relation Classification with Task Specific Supersense

摘要

Classifying the relationship between entities is an important natural language processing (NLP) task. Scientific Relation Classification aims at automatically categorizing scientific semantic relationships among entities in scientific documents. Conventionally, only task unspecific supersense, such as supersense (or hyernym) from WordNet (e.g., ANIMAL is the supersense of "dog"), is used as a feature for relation classification. In this work, we hypothesize that task specific supersense could also be utilized as an informative feature for relation classification. Specifically, we define a new entity type based on the property of a given task, and facilitate scientific relation classification with the task specific supersense. Our experiments on three different datasets prove the effectiveness of the task specific supersense on relation classification in scientific articles.