Cross-lingual Adaptation Using Universal Dependencies

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10441595" target="_blank" >RIV/00216208:11320/21:10441595 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=dZhh3n11ec" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=dZhh3n11ec</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3448251" target="_blank" >10.1145/3448251</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Cross-lingual Adaptation Using Universal Dependencies

Popis výsledku v původním jazyce

We describe a cross-lingual adaptation method based on syntactic parse trees obtained from the Universal Dependencies (UD), which are consistent across languages, to develop classifiers in low-resource languages. The idea of UD parsing is to capture similarities as well as idiosyncrasies among typologically different languages. In this article, we show that models trained using UD parse trees for complex NLP tasks can characterize very different languages. We study two tasks of paraphrase identification and relation extraction as case studies. Based on UD parse trees, we develop several models using tree kernels and show that these models trained on the English dataset can correctly classify data of other languages, e.g., French, Farsi, and Arabic. The proposed approach opens up avenues for exploiting UD parsing in solving similar cross-lingual tasks, which is very useful for languages for which no labeled data is available.

Název v anglickém jazyce

Cross-lingual Adaptation Using Universal Dependencies

Popis výsledku anglicky

We describe a cross-lingual adaptation method based on syntactic parse trees obtained from the Universal Dependencies (UD), which are consistent across languages, to develop classifiers in low-resource languages. The idea of UD parsing is to capture similarities as well as idiosyncrasies among typologically different languages. In this article, we show that models trained using UD parse trees for complex NLP tasks can characterize very different languages. We study two tasks of paraphrase identification and relation extraction as case studies. Based on UD parse trees, we develop several models using tree kernels and show that these models trained on the English dataset can correctly classify data of other languages, e.g., French, Farsi, and Arabic. The proposed approach opens up avenues for exploiting UD parsing in solving similar cross-lingual tasks, which is very useful for languages for which no labeled data is available.

Druh

J_imp - Článek v periodiku v databázi Web of Science

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

2021

Kód důvěrnosti údajů

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

Název periodika

ACM Transactions on Asian and Low-Resource Language Information Processing

ISSN

2375-4699

e-ISSN

2375-4702

Svazek periodika

20

Číslo periodika v rámci svazku

4

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

23

Strana od-do

65

Kód UT WoS článku

000721582900012

EID výsledku v databázi Scopus

2-s2.0-85111026083