Bernice: A Multilingual Pre-trained Encoder for Twitter

Alexandra DeLucia, Shijie Wu, Aaron Mueller, Carlos Aguirre, Philip Resnik, Mark Dredze


Abstract
The language of Twitter differs significantly from that of other domains commonly included in large language model training. While tweets are typically multilingual and contain informal language, including emoji and hashtags, most pre-trained language models for Twitter are either monolingual, adapted from other domains rather than trained exclusively on Twitter, or are trained on a limited amount of in-domain Twitter data.We introduce Bernice, the first multilingual RoBERTa language model trained from scratch on 2.5 billion tweets with a custom tweet-focused tokenizer. We evaluate on a variety of monolingual and multilingual Twitter benchmarks, finding that our model consistently exceeds or matches the performance of a variety of models adapted to social media data as well as strong multilingual baselines, despite being trained on less data overall.We posit that it is more efficient compute- and data-wise to train completely on in-domain data with a specialized domain-specific tokenizer.
Anthology ID:
2022.emnlp-main.415
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6191–6205
Language:
URL:
https://aclanthology.org/2022.emnlp-main.415
DOI:
Bibkey:
Cite (ACL):
Alexandra DeLucia, Shijie Wu, Aaron Mueller, Carlos Aguirre, Philip Resnik, and Mark Dredze. 2022. Bernice: A Multilingual Pre-trained Encoder for Twitter. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6191–6205, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Bernice: A Multilingual Pre-trained Encoder for Twitter (DeLucia et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/paclic-22-ingestion/2022.emnlp-main.415.pdf