One Size Does Not Fit All: Finding the Optimal Subword Sizes for FastText Models across Languages

Varování

Publikace nespadá pod Fakultu sportovních studií, ale pod Fakultu informatiky. Oficiální stránka publikace je na webu muni.cz.
Autoři

NOVOTNÝ Vít AYETIRAN Eniafe Festus BAČOVSKÝ Dalibor LUPTÁK Dávid ŠTEFÁNIK Michal SOJKA Petr

Rok publikování 2021
Druh Článek ve sborníku
Konference Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
www
Doi http://dx.doi.org/10.26615/978-954-452-072-4_120
Klíčová slova fastText; representation learning; word analogy; hyperparameter optimization; language modeling; language distance
Popis Unsupervised representation learning of words from large multilingual corpora is useful for downstream tasks such as word sense disambiguation, semantic text similarity, and information retrieval. The representation precision of log-bilinear fastText models is mostly due to their use of subword information. In previous work, the optimization of fastText's subword sizes has not been fully explored, and non-English fastText models were trained using subword sizes optimized for English and German word analogy tasks. In our work, we find the optimal subword sizes on the English, German, Czech, Italian, Spanish, French, Hindi, Turkish, and Russian word analogy tasks. We then propose a simple n-gram coverage model and we show that it predicts better-than-default subword sizes on the Spanish, French, Hindi, Turkish, and Russian word analogy tasks. We show that the optimization of fastText's subword sizes matters and results in a 14% improvement on the Czech word analogy task. We also show that expensive parameter optimization can be replaced by a simple n-gram coverage model that consistently improves the accuracy of fastText models on the word analogy tasks by up to 3% compared to the default subword sizes, and that it is within 1% accuracy of the optimal subword sizes.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.

Další info