Cross-Lingual Universal Dependency Parsing Only From One Monolingual Treebank

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AA4HWA464" target="_blank" >RIV/00216208:11320/23:A4HWA464 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85164376341&doi=10.1109%2fTPAMI.2023.3291388&partnerID=40&md5=a1c963e57fa015f3459b548af078abc5" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85164376341&doi=10.1109%2fTPAMI.2023.3291388&partnerID=40&md5=a1c963e57fa015f3459b548af078abc5</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/tpami.2023.3291388" target="_blank" >10.1109/tpami.2023.3291388</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Cross-Lingual Universal Dependency Parsing Only From One Monolingual Treebank

Popis výsledku v původním jazyce

"Syntactic parsing is a highly linguistic processing task whose parser requires training on treebanks from the expensive human annotation. As it is unlikely to obtain a treebank for every human language, in this work, we propose an effective cross-lingual UD parsing framework for transferring parser from only one source monolingual treebank to any other target languages without treebank available. To reach satisfactory parsing accuracy among quite different languages, we introduce two language modeling tasks into the training process of dependency parsing as multi-tasking. Assuming only unlabeled data from target languages plus the source treebank can be exploited together, we adopt a self-training strategy for further performance improvement in terms of our multi-task framework. Our proposed cross-lingual parsers are implemented for English, Chinese, and 29 UD treebanks. The empirical study shows that our cross-lingual parsers yield promising results for all target languages, approaching the parser performance which is trained in its own target treebank. © 1979-2012 IEEE."

Název v anglickém jazyce

Cross-Lingual Universal Dependency Parsing Only From One Monolingual Treebank

Popis výsledku anglicky

"Syntactic parsing is a highly linguistic processing task whose parser requires training on treebanks from the expensive human annotation. As it is unlikely to obtain a treebank for every human language, in this work, we propose an effective cross-lingual UD parsing framework for transferring parser from only one source monolingual treebank to any other target languages without treebank available. To reach satisfactory parsing accuracy among quite different languages, we introduce two language modeling tasks into the training process of dependency parsing as multi-tasking. Assuming only unlabeled data from target languages plus the source treebank can be exploited together, we adopt a self-training strategy for further performance improvement in terms of our multi-task framework. Our proposed cross-lingual parsers are implemented for English, Chinese, and 29 UD treebanks. The empirical study shows that our cross-lingual parsers yield promising results for all target languages, approaching the parser performance which is trained in its own target treebank. © 1979-2012 IEEE."

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

2023

Kód důvěrnosti údajů

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

Název periodika

"IEEE Transactions on Pattern Analysis and Machine Intelligence"

ISSN

0162-8828

e-ISSN

—

Svazek periodika

45

Číslo periodika v rámci svazku

11

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

15

Strana od-do

13393-13407

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85164376341