Multi-source domain adaptation for dependency parsing via domain-aware feature generation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AX9IFBY4B" target="_blank" >RIV/00216208:11320/25:X9IFBY4B - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85202963407&doi=10.1007%2fs13042-024-02306-0&partnerID=40&md5=060923332bbaed26889271294a2824ed" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85202963407&doi=10.1007%2fs13042-024-02306-0&partnerID=40&md5=060923332bbaed26889271294a2824ed</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s13042-024-02306-0" target="_blank" >10.1007/s13042-024-02306-0</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Multi-source domain adaptation for dependency parsing via domain-aware feature generation

Popis výsledku v původním jazyce

With deep representation learning advances, supervised dependency parsing has achieved a notable enhancement. However, when the training data is drawn from various predefined out-domains, the parsing performance drops sharply due to the domain distribution shift. The key to addressing this problem is to model the associations and differences between multiple source and target domains. In this work, we propose an innovative domain-aware adversarial and parameter generation network for multi-source cross-domain dependency parsing where a domain-aware parameter generation network is used for identifying domain-specific features and an adversarial network is used for learning domain-invariant ones. Experiments on the benchmark datasets reveal that our model outperforms strong BERT-enhanced baselines by 2 points in the average labeled attachment score (LAS). Detailed analysis of various domain representation strategies shows that our proposed distributed domain embedding can accurately capture domain relevance, which motivates the domain-aware parameter generation network to emphasize useful domain-specific representations and disregard unnecessary or even harmful ones. Additionally, extensive comparison experiments show deeper insights on the contributions of the two components. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

Název v anglickém jazyce

Multi-source domain adaptation for dependency parsing via domain-aware feature generation

Popis výsledku anglicky

With deep representation learning advances, supervised dependency parsing has achieved a notable enhancement. However, when the training data is drawn from various predefined out-domains, the parsing performance drops sharply due to the domain distribution shift. The key to addressing this problem is to model the associations and differences between multiple source and target domains. In this work, we propose an innovative domain-aware adversarial and parameter generation network for multi-source cross-domain dependency parsing where a domain-aware parameter generation network is used for identifying domain-specific features and an adversarial network is used for learning domain-invariant ones. Experiments on the benchmark datasets reveal that our model outperforms strong BERT-enhanced baselines by 2 points in the average labeled attachment score (LAS). Detailed analysis of various domain representation strategies shows that our proposed distributed domain embedding can accurately capture domain relevance, which motivates the domain-aware parameter generation network to emphasize useful domain-specific representations and disregard unnecessary or even harmful ones. Additionally, extensive comparison experiments show deeper insights on the contributions of the two components. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

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

International Journal of Machine Learning and Cybernetics

ISSN

1868-8071

e-ISSN

—

Svazek periodika

2024

Číslo periodika v rámci svazku

2024

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

14

Strana od-do

1-14

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85202963407