Unsupervised Multilingual Sentence Embeddings for Parallel Corpus Mining
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10424463" target="_blank" >RIV/00216208:11320/20:10424463 - isvavai.cz</a>
Result on the web
<a href="https://www.aclweb.org/anthology/2020.acl-srw.34/" target="_blank" >https://www.aclweb.org/anthology/2020.acl-srw.34/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.18653/v1/2020.acl-srw.34" target="_blank" >10.18653/v1/2020.acl-srw.34</a>
Alternative languages
Result language
angličtina
Original language name
Unsupervised Multilingual Sentence Embeddings for Parallel Corpus Mining
Original language description
Existing models of multilingual sentence embeddings require large parallel data resources which are not available for low-resource languages. We propose a novel unsupervised method to derive multilingual sentence embeddings relying only on monolingual data. We first produce a synthetic parallel corpus using unsupervised machine translation, and use it to fine-tune a pretrained cross-lingual masked language model (XLM) to derive the multilingual sentence representations. The quality of the representations is evaluated on two parallel corpus mining tasks with improvements of up to 22 F1 points over vanilla XLM. In addition, we observe that a single synthetic bilingual corpus is able to improve results for other language pairs.
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
<a href="/en/project/GX19-26934X" target="_blank" >GX19-26934X: Neural Representations in Multi-modal and Multi-lingual Modeling</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2020
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 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
ISBN
978-1-952148-03-3
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
255-262
Publisher name
Association for Computational Linguistics
Place of publication
Stroudsburg, PA, USA
Event location
Online
Event date
Jul 5, 2020
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—