Leveraging Linguistically Enhanced Embeddings for Open Information Extraction

arXiv:2403.13903v1 Announce Type: new
Abstract: Open Information Extraction (OIE) is a structured prediction (SP) task in Natural Language Processing (NLP) that aims to extract structured $n$-ary tuples - usually subject-relation-object triples - from free text. The word embeddings in the input text can be enhanced with linguistic features, usually Part-of-Speech (PoS) and Syntactic Dependency Parse (SynDP) labels. However, past enhancement techniques cannot leverage the power of pretrained language models (PLMs), which themselves have been hardly used for OIE. To bridge …

abstract arxiv cs.cl embeddings extract extraction features free information information extraction language language processing natural natural language natural language processing nlp object part part-of-speech prediction processing speech text tuples type word word embeddings