Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation Extraction
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AXF8DUI6H" target="_blank" >RIV/00216208:11320/23:XF8DUI6H - isvavai.cz</a>
Výsledek na webu
<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85174712588&partnerID=40&md5=a2b83b3970d5de663d10d5557cd1c929" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85174712588&partnerID=40&md5=a2b83b3970d5de663d10d5557cd1c929</a>
DOI - Digital Object Identifier
—
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation Extraction
Popis výsledku v původním jazyce
"Latest efforts on cross-lingual relation extraction (XRE) aggressively leverage the language-consistent structural features from the universal dependency (UD) resource, while they may largely suffer from biased transfer (e.g., either target-biased or source-biased) due to the inevitable linguistic disparity between languages. In this work, we investigate an unbiased UD-based XRE transfer by constructing a type of code-mixed UD forest. We first translate the sentence of the source language to the parallel target-side language, for both of which we parse the UD tree respectively. Then, we merge the source-/target-side UD structures as a unified code-mixed UD forest. With such forest features, the gaps of UD-based XRE between the training and predicting phases can be effectively closed. We conduct experiments on the ACE XRE benchmark datasets, where the results demonstrate that the proposed code-mixed UD forests help unbiased UD-based XRE transfer, with which we achieve significant XRE performance gains. © 2023 Association for Computational Linguistics."
Název v anglickém jazyce
Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation Extraction
Popis výsledku anglicky
"Latest efforts on cross-lingual relation extraction (XRE) aggressively leverage the language-consistent structural features from the universal dependency (UD) resource, while they may largely suffer from biased transfer (e.g., either target-biased or source-biased) due to the inevitable linguistic disparity between languages. In this work, we investigate an unbiased UD-based XRE transfer by constructing a type of code-mixed UD forest. We first translate the sentence of the source language to the parallel target-side language, for both of which we parse the UD tree respectively. Then, we merge the source-/target-side UD structures as a unified code-mixed UD forest. With such forest features, the gaps of UD-based XRE between the training and predicting phases can be effectively closed. We conduct experiments on the ACE XRE benchmark datasets, where the results demonstrate that the proposed code-mixed UD forests help unbiased UD-based XRE transfer, with which we achieve significant XRE performance gains. © 2023 Association for Computational Linguistics."
Klasifikace
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)
Návaznosti výsledku
Projekt
—
Návaznosti
—
Ostatní
Rok uplatnění
2023
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
"Proc. Annu. Meet. Assoc. Comput Linguist."
ISBN
978-195942962-3
ISSN
0736-587X
e-ISSN
—
Počet stran výsledku
14
Strana od-do
9395-9408
Název nakladatele
Association for Computational Linguistics (ACL)
Místo vydání
—
Místo konání akce
Cham
Datum konání akce
1. 1. 2023
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
—