When Word Pairs Matter - Analysis of the English-Slovak Evaluation Dataset

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F21%3A00123252" target="_blank" >RIV/00216224:14330/21:00123252 - isvavai.cz</a>
Result on the web
<a href="https://nlp.fi.muni.cz/raslan/2021/paper3.pdf" target="_blank" >https://nlp.fi.muni.cz/raslan/2021/paper3.pdf</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
When Word Pairs Matter - Analysis of the English-Slovak Evaluation Dataset
Original language description
Cross-lingual word embeddings facilitate the transfer of lexical knowledge across languages, and they are mainly used for finding transla- tion equivalents. Translation equivalents obtained in this way are usually evaluated with the help of ground truth dictionaries. However, the evalu- ation process, including the ground truth dictionaries, differs from model to model, impeding the correct interpretation of the results. Therefore, in this paper, we provide a thorough analysis of the English-Slovak ground truth dictionary and employ our analysis in evaluating two cross-lingual word embedding models. We show that word pairs choice is an important factor when accurately reflecting the model’s performance.
Czech name
—
Czech description
—

Project
<a href="/en/project/LM2018101" target="_blank" >LM2018101: Digital Research Infrastructure for the Language Technologies, Arts and Humanities</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Recent Advances in Slavonic Natural Language Processing (RASLAN 2021)
ISBN
9788026316701
ISSN
2336-4289
e-ISSN
—
Number of pages
9
Pages from-to
141-149
Publisher name
Tribun EU
Place of publication
Brno
Event location
Brno
Event date
Jan 1, 2021
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—

Similar results(10)