Subword Pooling Makes a Difference
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10442224" target="_blank" >RIV/00216208:11320/21:10442224 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Subword Pooling Makes a Difference
Original language description
Contextual word-representations became a standard in modern natural language processing systems. These models use subword tokenization to handle large vocabularies and unknown words. Word-level usage of such systems requires a way of pooling multiple subwords that correspond to a single word. In this paper we investigate how the choice of subword pooling affects the downstream performance on three tasks: morphological probing, POS tagging and NER, in 9 typologically diverse languages. We compare these in two massively multilingual models, mBERT and XLM-RoBERTa. For morphological tasks, the widely used 'choose the first subword' is the worst strategy and the best results are obtained by using attention over the subwords. For POS tagging both of these strategies perform poorly and the best choice is to use a small LSTM over the subwords. The same strategy works best for NER and we show that mBERT is better than XLM-RoBERTa in all 9 languages. We publicly release all code, data and the full result tables at https://github.com/juditacs/subword-choice .
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
ISBN
978-1-954085-02-2
ISSN
—
e-ISSN
—
Number of pages
12
Pages from-to
2284-2295
Publisher name
Association for Computational Linguistics
Place of publication
Stroudsburg
Event location
online
Event date
Apr 19, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—