Bilingual Lexicon Induction From Comparable and Parallel Data: A Comparative Analysis

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F24%3A00136956" target="_blank" >RIV/00216224:14330/24:00136956 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-031-70563-2_3" target="_blank" >http://dx.doi.org/10.1007/978-3-031-70563-2_3</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-70563-2_3" target="_blank" >10.1007/978-3-031-70563-2_3</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Bilingual Lexicon Induction From Comparable and Parallel Data: A Comparative Analysis

Popis výsledku v původním jazyce

Bilingual lexicon induction (BLI) from comparable data has become a common way of evaluating cross-lingual word embeddings (CWEs). These models have drawn much attention, mainly due to their availability for rare and low-resource language pairs. An alternative offers systems exploiting parallel data, such as popular neural machine translation systems (NMTSs), which are effective and yield state-of-the-art results. Despite the significant advancements in NMTSs, their effectiveness in the BLI task compared to the models using comparable data remains underexplored. In this paper, we provide a comparative study of the NMTS and CWE models evaluated on the BLI task and demonstrate the results across three diverse language pairs: distant (Estonian-English) and close (Estonian-Finnish) language pair and language pair with different scripts (Estonian-Russian). Our study reveals the differences, strengths, and limitations of both approaches. We show that while NMTSs achieve impressive results for languages with a great amount of training data available, CWEs emerge as a better option when faced less resources.

Název v anglickém jazyce

Bilingual Lexicon Induction From Comparable and Parallel Data: A Comparative Analysis

Popis výsledku anglicky

Bilingual lexicon induction (BLI) from comparable data has become a common way of evaluating cross-lingual word embeddings (CWEs). These models have drawn much attention, mainly due to their availability for rare and low-resource language pairs. An alternative offers systems exploiting parallel data, such as popular neural machine translation systems (NMTSs), which are effective and yield state-of-the-art results. Despite the significant advancements in NMTSs, their effectiveness in the BLI task compared to the models using comparable data remains underexplored. In this paper, we provide a comparative study of the NMTS and CWE models evaluated on the BLI task and demonstrate the results across three diverse language pairs: distant (Estonian-English) and close (Estonian-Finnish) language pair and language pair with different scripts (Estonian-Russian). Our study reveals the differences, strengths, and limitations of both approaches. We show that while NMTSs achieve impressive results for languages with a great amount of training data available, CWEs emerge as a better option when faced less resources.

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)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

International Conference on Text, Speech, and Dialogue

ISBN

9783031705625

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

13

Strana od-do

30-42

Název nakladatele

Springer Nature Switzerland

Místo vydání

Cham

Místo konání akce

Cham

Datum konání akce

1. 1. 2024

Typ akce podle státní příslušnosti

CST - Celostátní akce

Kód UT WoS článku

001307840300003