Efficient One-Pass End-to-End Entity Linking for Questions

Belinda Z. Li, Sewon Min, Srinivasan Iyer, Yashar Mehdad, Wen-tau Yih


Abstract
We present ELQ, a fast end-to-end entity linking model for questions, which uses a biencoder to jointly perform mention detection and linking in one pass. Evaluated on WebQSP and GraphQuestions with extended annotations that cover multiple entities per question, ELQ outperforms the previous state of the art by a large margin of +12.7% and +19.6% F1, respectively. With a very fast inference time (1.57 examples/s on a single CPU), ELQ can be useful for downstream question answering systems. In a proof-of-concept experiment, we demonstrate that using ELQ significantly improves the downstream QA performance of GraphRetriever.
Anthology ID:
2020.emnlp-main.522
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6433–6441
Language:
URL:
https://aclanthology.org/2020.emnlp-main.522
DOI:
10.18653/v1/2020.emnlp-main.522
Bibkey:
Cite (ACL):
Belinda Z. Li, Sewon Min, Srinivasan Iyer, Yashar Mehdad, and Wen-tau Yih. 2020. Efficient One-Pass End-to-End Entity Linking for Questions. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6433–6441, Online. Association for Computational Linguistics.
Cite (Informal):
Efficient One-Pass End-to-End Entity Linking for Questions (Li et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.522.pdf
Video:
 https://slideslive.com/38939354
Code
 facebookresearch/BLINK +  additional community code
Data
GraphQuestionsNatural QuestionsTriviaQAWebQuestions