GEMNET: Effective Gated Gazetteer Representations for Recognizing Complex Entities in Low-context Input

Tao Meng, Anjie Fang, Oleg Rokhlenko, Shervin Malmasi


Abstract
Named Entity Recognition (NER) remains difficult in real-world settings; current challenges include short texts (low context), emerging entities, and complex entities (e.g. movie names). Gazetteer features can help, but results have been mixed due to challenges with adding extra features, and a lack of realistic evaluation data. It has been shown that including gazetteer features can cause models to overuse or underuse them, leading to poor generalization. We propose GEMNET, a novel approach for gazetteer knowledge integration, including (1) a flexible Contextual Gazetteer Representation (CGR) encoder that can be fused with any word-level model; and (2) a Mixture-of- Experts gating network that overcomes the feature overuse issue by learning to conditionally combine the context and gazetteer features, instead of assigning them fixed weights. To comprehensively evaluate our approaches, we create 3 large NER datasets (24M tokens) reflecting current challenges. In an uncased setting, our methods show large gains (up to +49% F1) in recognizing difficult entities compared to existing baselines. On standard benchmarks, we achieve a new uncased SOTA on CoNLL03 and WNUT17.
Anthology ID:
2021.naacl-main.118
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1499–1512
Language:
URL:
https://aclanthology.org/2021.naacl-main.118
DOI:
10.18653/v1/2021.naacl-main.118
Bibkey:
Cite (ACL):
Tao Meng, Anjie Fang, Oleg Rokhlenko, and Shervin Malmasi. 2021. GEMNET: Effective Gated Gazetteer Representations for Recognizing Complex Entities in Low-context Input. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1499–1512, Online. Association for Computational Linguistics.
Cite (Informal):
GEMNET: Effective Gated Gazetteer Representations for Recognizing Complex Entities in Low-context Input (Meng et al., NAACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2021.naacl-main.118.pdf
Video:
 https://preview.aclanthology.org/ingest-2024-clasp/2021.naacl-main.118.mp4
Data
MS MARCOWNUT 2017