SynonymNet: Multi-context Bilateral Matching for Entity SynonymsDownload PDF

27 Sept 2018 (modified: 22 Oct 2023)ICLR 2019 Conference Blind SubmissionReaders: Everyone
Abstract: Being able to automatically discover synonymous entities from a large free-text corpus has transformative effects on structured knowledge discovery. Existing works either require structured annotations, or fail to incorporate context information effectively, which lower the efficiency of information usage. In this paper, we propose a framework for synonym discovery from free-text corpus without structured annotation. As one of the key components in synonym discovery, we introduce a novel neural network model SynonymNet to determine whether or not two given entities are synonym with each other. Instead of using entities features, SynonymNet makes use of multiple pieces of contexts in which the entity is mentioned, and compares the context-level similarity via a bilateral matching schema to determine synonymity. Experimental results demonstrate that the proposed model achieves state-of-the-art results on both generic and domain-specific synonym datasets: Wiki+Freebase, PubMed+UMLS and MedBook+MKG, with up to 4.16% improvement in terms of Area Under the Curve (AUC) and 3.19% in terms of Mean Average Precision (MAP) compare to the best baseline method.
Keywords: deep learning, entity synonym
TL;DR: We introduce SynonymNet, a deep model for entity synonym discovery by a bilateral matching among multiple pieces of contexts in which an entity is mentioned.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:1901.00056/code)
8 Replies

Loading