Many data sets (e.g., reviews, forums, news, etc.) exist parallelly in multiple languages. They all cover the same content, but the linguistic differences make it impossible to use traditional, bag-of-word-based topic models. Models have to be either single-language or suffer from a huge, but extremely sparse vocabulary. Both issues can be addressed by transfer learning. In this paper, we introduce a zero-shot cross-lingual topic model. Our model learns topics on one language (here, English), and predicts them for unseen documents in different languages (here, Italian, French, German, and Portuguese). We evaluate the quality of the topic predictions for the same document in different languages. Our results show that the transferred topics are coherent and stable across languages, which suggests exciting future research directions.

Bianchi, F., Terragni, S., Hovy, D., Nozza, D., Fersini, E. (2021). Cross-lingual contextualized topic models with zero-shot learning. In EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference (pp.1676-1683). Association for Computational Linguistics (ACL).

Cross-lingual contextualized topic models with zero-shot learning

Bianchi F.;Terragni S.;Nozza D.;Fersini E.
2021

Abstract

Many data sets (e.g., reviews, forums, news, etc.) exist parallelly in multiple languages. They all cover the same content, but the linguistic differences make it impossible to use traditional, bag-of-word-based topic models. Models have to be either single-language or suffer from a huge, but extremely sparse vocabulary. Both issues can be addressed by transfer learning. In this paper, we introduce a zero-shot cross-lingual topic model. Our model learns topics on one language (here, English), and predicts them for unseen documents in different languages (here, Italian, French, German, and Portuguese). We evaluate the quality of the topic predictions for the same document in different languages. Our results show that the transferred topics are coherent and stable across languages, which suggests exciting future research directions.
No
paper
Topic Models; Zero-shot learning
English
16th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2021
9781954085022
Bianchi, F., Terragni, S., Hovy, D., Nozza, D., Fersini, E. (2021). Cross-lingual contextualized topic models with zero-shot learning. In EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference (pp.1676-1683). Association for Computational Linguistics (ACL).
Bianchi, F; Terragni, S; Hovy, D; Nozza, D; Fersini, E
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/363086
Citazioni
  • Scopus 19
  • ???jsp.display-item.citation.isi??? ND
Social impact