Subwords-Only Alternatives to fastText for Morphologically Rich Languages
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10439963" target="_blank" >RIV/00216208:11320/21:10439963 - isvavai.cz</a>
Result on the web
<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=HUjN.9Fn4B" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=HUjN.9Fn4B</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1134/S0361768821010059" target="_blank" >10.1134/S0361768821010059</a>
Alternative languages
Result language
angličtina
Original language name
Subwords-Only Alternatives to fastText for Morphologically Rich Languages
Original language description
Abstract: In this work, we present purely subword-based alternatives to fastText word embedding algorithm The alternatives are modifications of the original fastText model, but rely on subword information only, eliminating the reliance on word-level vectors and at the same time helping to dramatically reduce the size of embeddings. Proposed models differ in their subword information extraction method: character n-grams, suffixes, and the byte-pair encoding units. We test the models in the task of morphological analysis and lemmatization for 3 morphologically rich languages: Finnish, Russian, and German. The results are compared with other recent subword-based models, demonstrating consistently higher results.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
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
Name of the periodical
Programming and Computer Software
ISSN
0361-7688
e-ISSN
1608-3261
Volume of the periodical
47
Issue of the periodical within the volume
1
Country of publishing house
RU - RUSSIAN FEDERATION
Number of pages
11
Pages from-to
56-66
UT code for WoS article
000620610400009
EID of the result in the Scopus database
2-s2.0-85101570469