Entity Linking (EL) recognizes textual mentions of entities and maps them to the corresponding entities in a Knowledge Graph (KG). In this paper, we propose a novel method for EL on short text using entity representations base on their name labels, descriptions, and other related entities in the KG. We then leverage a pre-trained BERT model to calculate the semantic similarity between the entity and the text. This method does not require a large volume of data to jointly train word and entity representations, and is easily portable to a new domain with a KG. We demonstrate that our approach outperforms previous methods on a public benchmark dataset with a large margin.
Cite as: Huang, B., Wang, H., Wang, T., Liu, Y., Liu, Y. (2020) Entity Linking for Short Text Using Structured Knowledge Graph via Multi-Grained Text Matching. Proc. Interspeech 2020, 4178-4182, doi: 10.21437/Interspeech.2020-1934
@inproceedings{huang20e_interspeech,
author={Binxuan Huang and Han Wang and Tong Wang and Yue Liu and Yang Liu},
title={{Entity Linking for Short Text Using Structured Knowledge Graph via Multi-Grained Text Matching}},
year=2020,
booktitle={Proc. Interspeech 2020},
pages={4178--4182},
doi={10.21437/Interspeech.2020-1934}
}