Improving linear orthogonal mapping based cross-lingual representation using ridge regression and graph centrality

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AVED7NJD9" target="_blank" >RIV/00216208:11320/25:VED7NJD9 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85188573401&doi=10.1016%2fj.csl.2024.101640&partnerID=40&md5=6151af2a84f3f7facd35357c17f82d02" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85188573401&doi=10.1016%2fj.csl.2024.101640&partnerID=40&md5=6151af2a84f3f7facd35357c17f82d02</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.csl.2024.101640" target="_blank" >10.1016/j.csl.2024.101640</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Improving linear orthogonal mapping based cross-lingual representation using ridge regression and graph centrality

Popis výsledku v původním jazyce

Orthogonal linear mapping is a commonly used approach for generating cross-lingual embedding between two monolingual corpora that uses a word frequency-based seed dictionary alignment approach. While this approach is found to be effective for isomorphic language pairs, they do not perform well for distant language pairs with different sentence structures and morphological properties. For a distance language pair, the existing frequency-aligned orthogonal mapping methods suffer from two problems - (i)the frequency of source and target word are not comparable, and (ii)different word pairs in the seed dictionary may have different contribution. Motivated by the above two concerns, this paper proposes a novel centrality-aligned ridge regression-based orthogonal mapping. The proposed method uses centrality-based alignment for seed dictionary selection and ridge regression framework for incorporating influential weights of different word pairs in the seed dictionary. From various experimental observations over five language pairs (both isomorphic and distant languages), it is evident that the proposed method outperforms baseline methods in the Bilingual Dictionary Induction(BDI) task, Sentence Retrieval Task(SRT), and Machine Translation. Further, several analyses are also included to support the proposed method. © 2024 Elsevier Ltd

Název v anglickém jazyce

Improving linear orthogonal mapping based cross-lingual representation using ridge regression and graph centrality

Popis výsledku anglicky

Orthogonal linear mapping is a commonly used approach for generating cross-lingual embedding between two monolingual corpora that uses a word frequency-based seed dictionary alignment approach. While this approach is found to be effective for isomorphic language pairs, they do not perform well for distant language pairs with different sentence structures and morphological properties. For a distance language pair, the existing frequency-aligned orthogonal mapping methods suffer from two problems - (i)the frequency of source and target word are not comparable, and (ii)different word pairs in the seed dictionary may have different contribution. Motivated by the above two concerns, this paper proposes a novel centrality-aligned ridge regression-based orthogonal mapping. The proposed method uses centrality-based alignment for seed dictionary selection and ridge regression framework for incorporating influential weights of different word pairs in the seed dictionary. From various experimental observations over five language pairs (both isomorphic and distant languages), it is evident that the proposed method outperforms baseline methods in the Bilingual Dictionary Induction(BDI) task, Sentence Retrieval Task(SRT), and Machine Translation. Further, several analyses are also included to support the proposed method. © 2024 Elsevier Ltd

Druh

J_SC - Článek v periodiku v databázi SCOPUS

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

—

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název periodika

Computer Speech and Language

ISSN

0885-2308

e-ISSN

—

Svazek periodika

87

Číslo periodika v rámci svazku

2024

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

25

Strana od-do

1-25

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85188573401