Enhancing Negation Scope Detection using Multitask Learning

Harsh Patel, Xulang Zhang, Qian Liu

Abstract: Negation is a linguistic phenomenon that usually occurs in a text for denial or refute of some occasion. Detection of such negative assertions is an essential sub-task in various applications of information extraction and data mining. In this paper, we present a deep multitask learning (MTL) framework to enhance the performance of Negation Scope detection using part-of-speech (POS) tagging as an auxiliary task. We show how the relationship between these two tasks, which do not seem to be easily linked from a linguistic point of view, is mutually beneficial.