WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models

Benjamin Minixhofer, Fabian Paischer, Navid Rekabsaz


Abstract
Large pretrained language models (LMs) have become the central building block of many NLP applications. Training these models requires ever more computational resources and most of the existing models are trained on English text only. It is exceedingly expensive to train these models in other languages. To alleviate this problem, we introduce a novel method – called WECHSEL – to efficiently and effectively transfer pretrained LMs to new languages. WECHSEL can be applied to any model which uses subword-based tokenization and learns an embedding for each subword. The tokenizer of the source model (in English) is replaced with a tokenizer in the target language and token embeddings are initialized such that they are semantically similar to the English tokens by utilizing multilingual static word embeddings covering English and the target language. We use WECHSEL to transfer the English RoBERTa and GPT-2 models to four languages (French, German, Chinese and Swahili). We also study the benefits of our method on very low-resource languages. WECHSEL improves over proposed methods for cross-lingual parameter transfer and outperforms models of comparable size trained from scratch with up to 64x less training effort. Our method makes training large language models for new languages more accessible and less damaging to the environment. We make our code and models publicly available.
Anthology ID:
2022.naacl-main.293
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3992–4006
Language:
URL:
https://aclanthology.org/2022.naacl-main.293
DOI:
10.18653/v1/2022.naacl-main.293
Bibkey:
Cite (ACL):
Benjamin Minixhofer, Fabian Paischer, and Navid Rekabsaz. 2022. WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3992–4006, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models (Minixhofer et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.293.pdf
Code
 cpjku/wechsel