Abstract
Contextual word embeddings (e.g. GPT, BERT, ELMo, etc.) have demonstrated state-of-the-art performance on various NLP tasks. Recent work with the multilingual version of BERT has shown that the model performs surprisingly well in cross-lingual settings, even when only labeled English data is used to finetune the model. We improve upon multilingual BERT’s zero-resource cross-lingual performance via adversarial learning. We report the magnitude of the improvement on the multilingual MLDoc text classification and CoNLL 2002/2003 named entity recognition tasks. Furthermore, we show that language-adversarial training encourages BERT to align the embeddings of English documents and their translations, which may be the cause of the observed performance gains.- Anthology ID:
- D19-1138
- Volume:
- Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Venues:
- EMNLP | IJCNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1355–1360
- Language:
- URL:
- https://aclanthology.org/D19-1138
- DOI:
- 10.18653/v1/D19-1138
- Cite (ACL):
- Phillip Keung, Yichao Lu, and Vikas Bhardwaj. 2019. Adversarial Learning with Contextual Embeddings for Zero-resource Cross-lingual Classification and NER. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1355–1360, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Adversarial Learning with Contextual Embeddings for Zero-resource Cross-lingual Classification and NER (Keung et al., EMNLP-IJCNLP 2019)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/D19-1138.pdf
- Data
- MLDoc