Enhancing Bilingual Lexicon Induction with Dynamic Translation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F25%3A00140716" target="_blank" >RIV/00216224:14330/25:00140716 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.5220/0013346000003890" target="_blank" >http://dx.doi.org/10.5220/0013346000003890</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5220/0013346000003890" target="_blank" >10.5220/0013346000003890</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Enhancing Bilingual Lexicon Induction with Dynamic Translation

Popis výsledku v původním jazyce

Bilingual lexicon induction (BLI) has been a popular task for evaluating cross-lingual word embeddings (CWEs). The prevalent metric employed in the evaluation is precision at k, where k represents the number of target words retrieved for each source word. However, establishing a fixed k for the entire evaluation dataset proves challenging due to varying target word counts for each source word. This leads to limited results, compromising either precision or recall. In this paper, we present a novel classification-based approach with dynamic k for bilingual lexicon induction that aims to identify all relevant target words for each source word by exploiting the information derived from the aligned embeddings while offering a balanced trade-off between precision and recall. On top of that, it enables the evaluation of the existing CWEs using dynamic k. Compared to the standard baseline systems and evaluation procedures, it provides competitive results.

Název v anglickém jazyce

Enhancing Bilingual Lexicon Induction with Dynamic Translation

Popis výsledku anglicky

Bilingual lexicon induction (BLI) has been a popular task for evaluating cross-lingual word embeddings (CWEs). The prevalent metric employed in the evaluation is precision at k, where k represents the number of target words retrieved for each source word. However, establishing a fixed k for the entire evaluation dataset proves challenging due to varying target word counts for each source word. This leads to limited results, compromising either precision or recall. In this paper, we present a novel classification-based approach with dynamic k for bilingual lexicon induction that aims to identify all relevant target words for each source word by exploiting the information derived from the aligned embeddings while offering a balanced trade-off between precision and recall. On top of that, it enables the evaluation of the existing CWEs using dynamic k. Compared to the standard baseline systems and evaluation procedures, it provides competitive results.

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

2025

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART

ISBN

9789897587375

ISSN

2184-3589

e-ISSN

—

Počet stran výsledku

10

Strana od-do

735-744

Název nakladatele

SciTePress

Místo vydání

Porto

Místo konání akce

Porto, Portugal

Datum konání akce

1. 1. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—