CUNI Submission to the BUCC 2022 Shared Task on Bilingual Term Alignment
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3A10457085" target="_blank" >RIV/00216208:11320/22:10457085 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
CUNI Submission to the BUCC 2022 Shared Task on Bilingual Term Alignment
Original language description
We present our submission to the BUCC Shared Task on bilingual term alignment in comparable specialized corpora. We devised three approaches using static embeddings with post-hoc alignment, the Monoses pipeline for unsupervised phrase-based machine translation, and contextualized multilingual embeddings. We show that contextualized embeddings from pretrained multilingual models lead to similar results as static embeddings but further improvement can be achieved by task-specific fine-tuning. Retrieving term pairs from the running phrase tables of the Monoses systems can match this enhanced performance and leads to an average precision of 0.88 on the train set.
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
2022
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 LREC 2022 15th Workshop on Building and Using Comparable Corpora
ISBN
979-10-95546-94-8
ISSN
—
e-ISSN
—
Number of pages
7
Pages from-to
43-49
Publisher name
European Language Resources Association
Place of publication
Paris, France
Event location
Marseille, France
Event date
Jun 25, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—