Kernel Least Squares Transformations for Cross-Lingual Semantic Spaces

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F24%3A43973516" target="_blank" >RIV/49777513:23520/24:43973516 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-031-70563-2_18" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-70563-2_18</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-70563-2_18" target="_blank" >10.1007/978-3-031-70563-2_18</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Kernel Least Squares Transformations for Cross-Lingual Semantic Spaces

Popis výsledku v původním jazyce

The rapid development in the field of natural language processing (NLP) and the increasing complexity of linguistic tasks demand the use of efficient and effective methods. Cross-lingual linear transformations between semantic spaces play a crucial role in this domain. However, compared to more advanced models such as transformers, linear transformations often fall short, especially in terms of accuracy. It is thus necessary to employ innovative approaches that not only enhance performance but also maintain low computational complexity.In this study, we propose Kernel Least Squares (KLS) for linear transformation between semantic spaces. In our comprehensive analysis involving three intrinsic and two extrinsic experiments across six languages from three different language families and a comparative evaluation with nine different linear transformation methods, we demonstrate the superior performance of KLS. Our results show that the proposed method significantly improves word translation accuracy, thereby standing out as the most efficient method for transforming only the source semantic space.

Název v anglickém jazyce

Kernel Least Squares Transformations for Cross-Lingual Semantic Spaces

Popis výsledku anglicky

The rapid development in the field of natural language processing (NLP) and the increasing complexity of linguistic tasks demand the use of efficient and effective methods. Cross-lingual linear transformations between semantic spaces play a crucial role in this domain. However, compared to more advanced models such as transformers, linear transformations often fall short, especially in terms of accuracy. It is thus necessary to employ innovative approaches that not only enhance performance but also maintain low computational complexity.In this study, we propose Kernel Least Squares (KLS) for linear transformation between semantic spaces. In our comprehensive analysis involving three intrinsic and two extrinsic experiments across six languages from three different language families and a comparative evaluation with nine different linear transformation methods, we demonstrate the superior performance of KLS. Our results show that the proposed method significantly improves word translation accuracy, thereby standing out as the most efficient method for transforming only the source semantic space.

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

Text, Speech, and Dialogue. Lecture Notes in Computer Science

ISBN

978-3-031-70562-5

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

12

Strana od-do

227-238

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Brno

Datum konání akce

9. 9. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001307840300018