Subword-based Cross-lingual Transfer of Embeddings from Hindi to Marathi and Nepali
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3A10456922" target="_blank" >RIV/00216208:11320/22:10456922 - isvavai.cz</a>
Výsledek na webu
<a href="https://aclanthology.org/2022.sigmorphon-1.pdf" target="_blank" >https://aclanthology.org/2022.sigmorphon-1.pdf</a>
DOI - Digital Object Identifier
—
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Subword-based Cross-lingual Transfer of Embeddings from Hindi to Marathi and Nepali
Popis výsledku v původním jazyce
Word embeddings are growing to be a crucial resource in the field of NLP for any language. This work introduces a novel technique for static subword embeddings transfer for Indic languages from a relatively higher resource language to a genealogically related low resource language. We primarily work with Hindi-Marathi, simulating a low-resource scenario for Marathi, and confirm observed trends on Nepali. We demonstrate the consistent benefits of unsupervised morphemic segmentation on both source and target sides over the treatment performed by fastText. Our best-performing approach uses an EM-style approach to learning bilingual subword embeddings; we also show, for the first time, that a trivial "copy- and-paste" embeddings transfer based on even perfect bilingual lexicons is inadequate in capturing language-specific relationships. We find that our approach substantially outperforms the fastText baselines for both Marathi and Nepali on the Word Similarity task as well as WordNet-Based Synonymy Tests;
Název v anglickém jazyce
Subword-based Cross-lingual Transfer of Embeddings from Hindi to Marathi and Nepali
Popis výsledku anglicky
Word embeddings are growing to be a crucial resource in the field of NLP for any language. This work introduces a novel technique for static subword embeddings transfer for Indic languages from a relatively higher resource language to a genealogically related low resource language. We primarily work with Hindi-Marathi, simulating a low-resource scenario for Marathi, and confirm observed trends on Nepali. We demonstrate the consistent benefits of unsupervised morphemic segmentation on both source and target sides over the treatment performed by fastText. Our best-performing approach uses an EM-style approach to learning bilingual subword embeddings; we also show, for the first time, that a trivial "copy- and-paste" embeddings transfer based on even perfect bilingual lexicons is inadequate in capturing language-specific relationships. We find that our approach substantially outperforms the fastText baselines for both Marathi and Nepali on the Word Similarity task as well as WordNet-Based Synonymy Tests;
Klasifikace
Druh
D - Stať ve sborníku
CEP obor
—
OECD FORD obor
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Návaznosti výsledku
Projekt
—
Návaznosti
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Ostatní
Rok uplatnění
2022
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
ISBN
978-1-955917-82-7
ISSN
—
e-ISSN
—
Počet stran výsledku
11
Strana od-do
61-71
Název nakladatele
Association for Computational Linguistics
Místo vydání
Stroudsburg, PA, USA
Místo konání akce
Seattle, WA, USA
Datum konání akce
14. 7. 2022
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
—