Towards Improved Distantly Supervised Multilingual Named-Entity Recognition for Tweets

Ramy Eskander, Shubhanshu Mishra, Sneha Mehta, Sofia Samaniego, Aria Haghighi


Abstract
Recent low-resource named-entity recognition (NER) work has shown impressive gains by leveraging a single multilingual model trained using distantly supervised data derived from cross-lingual knowledge bases. In this work, we investigate such approaches by leveraging Wikidata to build large-scale NER datasets of Tweets and propose two orthogonal improvements for low-resource NER in the Twitter social media domain: (1) leveraging domain-specific pre-training on Tweets; and (2) building a model for each language family rather than an all-in-one single multilingual model. For (1), we show that mBERT with Tweet pre-training outperforms the state-of-the-art multilingual transformer-based language model, LaBSE, by a relative increase of 34.6% in F1 when evaluated on Twitter data in a language-agnostic multilingual setting. For (2), we show that learning NER models for language families outperforms a single multilingual model by relative increases of 14.1%, 15.8% and 45.3% in F1 when utilizing mBERT, mBERT with Tweet pre-training and LaBSE, respectively. We conduct analyses and present examples for these observed improvements.
Anthology ID:
2022.mrl-1.12
Volume:
Proceedings of the 2nd Workshop on Multi-lingual Representation Learning (MRL)
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates (Hybrid)
Editors:
Duygu Ataman, Hila Gonen, Sebastian Ruder, Orhan Firat, Gözde Gül Sahin, Jamshidbek Mirzakhalov
Venue:
MRL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
115–124
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2022.mrl-1.12/
DOI:
10.18653/v1/2022.mrl-1.12
Bibkey:
Cite (ACL):
Ramy Eskander, Shubhanshu Mishra, Sneha Mehta, Sofia Samaniego, and Aria Haghighi. 2022. Towards Improved Distantly Supervised Multilingual Named-Entity Recognition for Tweets. In Proceedings of the 2nd Workshop on Multi-lingual Representation Learning (MRL), pages 115–124, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
Cite (Informal):
Towards Improved Distantly Supervised Multilingual Named-Entity Recognition for Tweets (Eskander et al., MRL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2022.mrl-1.12.pdf