Improving Entity Linking through Semantic Reinforced Entity Embeddings

Feng Hou, Ruili Wang, Jun He, Yi Zhou


Abstract
Entity embeddings, which represent different aspects of each entity with a single vector like word embeddings, are a key component of neural entity linking models. Existing entity embeddings are learned from canonical Wikipedia articles and local contexts surrounding target entities. Such entity embeddings are effective, but too distinctive for linking models to learn contextual commonality. We propose a simple yet effective method, FGS2EE, to inject fine-grained semantic information into entity embeddings to reduce the distinctiveness and facilitate the learning of contextual commonality. FGS2EE first uses the embeddings of semantic type words to generate semantic embeddings, and then combines them with existing entity embeddings through linear aggregation. Extensive experiments show the effectiveness of such embeddings. Based on our entity embeddings, we achieved new sate-of-the-art performance on entity linking.
Anthology ID:
2020.acl-main.612
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6843–6848
Language:
URL:
https://www.aclweb.org/anthology/2020.acl-main.612
DOI:
10.18653/v1/2020.acl-main.612
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.acl-main.612.pdf
Video:
 http://slideslive.com/38928767