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

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F21%3A00122017" target="_blank" >RIV/00216224:14330/21:00122017 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.26615/978-954-452-072-4_120" target="_blank" >https://doi.org/10.26615/978-954-452-072-4_120</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.26615/978-954-452-072-4_120" target="_blank" >10.26615/978-954-452-072-4_120</a>

Result language
angličtina
Original language name
One Size Does Not Fit All: Finding the Optimal Subword Sizes for FastText Models across Languages
Original language description
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.
Czech name
—
Czech description
—

Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
ISBN
9789544520724
ISSN
1313-8502
e-ISSN
—
Number of pages
7
Pages from-to
1068-1074
Publisher name
INCOMA Ltd.
Place of publication
Varna, Bulgaria
Event location
online
Event date
Sep 1, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)