Emu: Enhancing Multilingual Sentence Embeddings with Semantic Specialization

Wataru Hirota, Yoshihiko Suhara, Behzad Golshan, Wang-Chiew Tan

AAAI 2020 pp. 7935-7943

doi:10.1609/AAAI.V34I05.6301 /aaai/2020/hirota2020aaai-emu/

Abstract

We present Emu, a system that semantically enhances multilingual sentence embeddings. Our framework fine-tunes pre-trained multilingual sentence embeddings using two main components: a semantic classifier and a language discriminator. The semantic classifier improves the semantic similarity of related sentences, whereas the language discriminator enhances the multilinguality of the embeddings via multilingual adversarial training. Our experimental results based on several language pairs show that our specialized embeddings outperform the state-of-the-art multilingual sentence embedding model on the task of cross-lingual intent classification using only monolingual labeled data.

PDF AAAI Semantic Scholar

Cite

Text

Hirota et al. "Emu: Enhancing Multilingual Sentence Embeddings with Semantic Specialization." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I05.6301

Markdown

[Hirota et al. "Emu: Enhancing Multilingual Sentence Embeddings with Semantic Specialization." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/hirota2020aaai-emu/) doi:10.1609/AAAI.V34I05.6301

BibTeX

@inproceedings{hirota2020aaai-emu,
  title     = {{Emu: Enhancing Multilingual Sentence Embeddings with Semantic Specialization}},
  author    = {Hirota, Wataru and Suhara, Yoshihiko and Golshan, Behzad and Tan, Wang-Chiew},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {7935-7943},
  doi       = {10.1609/AAAI.V34I05.6301},
  url       = {https://mlanthology.org/aaai/2020/hirota2020aaai-emu/}
}