Negation Triplet Extraction with Syntactic Dependency and Semantic Consistency

arXiv:2404.09830v1 Announce Type: new
Abstract: Previous works of negation understanding mainly focus on negation cue detection and scope resolution, without identifying negation subject which is also significant to the downstream tasks. In this paper, we propose a new negation triplet extraction (NTE) task which aims to extract negation subject along with negation cue and scope. To achieve NTE, we devise a novel Syntax&Semantic-Enhanced Negation Extraction model, namely SSENE, which is built based on a generative pretrained language model (PLM) {of …

abstract arxiv cs.ai cs.cl detection extract extraction focus paper resolution semantic tasks type understanding