A Comparison of Architectures and Pretraining Methods for Contextualized Multilingual Word Embeddings

Abstract

The lack of annotated data in many languages is a well-known challenge within the field of multilingual natural language processing (NLP). Therefore, many recent studies focus on zero-shot transfer learning and joint training across languages to overcome data scarcity for low-resource languages. In this work we (i) perform a comprehensive comparison of state-of-the-art multilingual word and sentence encoders on the tasks of named entity recognition (NER) and part of speech (POS) tagging; and (ii) propose a new method for creating multilingual contextualized word embeddings, compare it to multiple baselines and show that it performs at or above state-of-the-art level in zero-shot transfer settings. Finally, we show that our method allows for better knowledge sharing across languages in a joint training setting.

Cite

Text

van der Heijden et al. "A Comparison of Architectures and Pretraining Methods for Contextualized Multilingual Word Embeddings." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I05.6443

Markdown

[van der Heijden et al. "A Comparison of Architectures and Pretraining Methods for Contextualized Multilingual Word Embeddings." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/vanderheijden2020aaai-comparison/) doi:10.1609/AAAI.V34I05.6443

BibTeX

@inproceedings{vanderheijden2020aaai-comparison,
  title     = {{A Comparison of Architectures and Pretraining Methods for Contextualized Multilingual Word Embeddings}},
  author    = {van der Heijden, Niels and Abnar, Samira and Shutova, Ekaterina},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {9090-9097},
  doi       = {10.1609/AAAI.V34I05.6443},
  url       = {https://mlanthology.org/aaai/2020/vanderheijden2020aaai-comparison/}
}