Abstract
In this paper, we propose Multilingual Meta-Embeddings (MME), an effective method to learn multilingual representations by leveraging monolingual pre-trained embeddings. MME learns to utilize information from these embeddings via a self-attention mechanism without explicit language identification. We evaluate the proposed embedding method on the code-switching English-Spanish Named Entity Recognition dataset in a multilingual and cross-lingual setting. The experimental results show that our proposed method achieves state-of-the-art performance on the multilingual setting, and it has the ability to generalize to an unseen language task.- Anthology ID:
- W19-4320
- Volume:
- Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)
- Month:
- August
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Isabelle Augenstein, Spandana Gella, Sebastian Ruder, Katharina Kann, Burcu Can, Johannes Welbl, Alexis Conneau, Xiang Ren, Marek Rei
- Venue:
- RepL4NLP
- SIG:
- SIGREP
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 181–186
- Language:
- URL:
- https://preview.aclanthology.org/icon-24-ingestion/W19-4320/
- DOI:
- 10.18653/v1/W19-4320
- Cite (ACL):
- Genta Indra Winata, Zhaojiang Lin, and Pascale Fung. 2019. Learning Multilingual Meta-Embeddings for Code-Switching Named Entity Recognition. In Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019), pages 181–186, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Learning Multilingual Meta-Embeddings for Code-Switching Named Entity Recognition (Winata et al., RepL4NLP 2019)
- PDF:
- https://preview.aclanthology.org/icon-24-ingestion/W19-4320.pdf