Typology Guided Multilingual Position Representations: Case on Dependency Parsing

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AF93JMJU2" target="_blank" >RIV/00216208:11320/23:F93JMJU2 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85175494397&partnerID=40&md5=b9e9f5cd8b41dfa45422e5b6af6a8f13" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85175494397&partnerID=40&md5=b9e9f5cd8b41dfa45422e5b6af6a8f13</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Typology Guided Multilingual Position Representations: Case on Dependency Parsing

Popis výsledku v původním jazyce

"Recent multilingual models benefit from strong unified semantic representation models. However, due to conflict linguistic regularities, ignoring language-specific features during multilingual learning may suffer from negative transfer. In this work, we analyze the relation between a language's position space and its typological characterization, and suggest deploying different position spaces for different languages. We develop a position generation network which combines prior knowledge from typology features and existing position vectors. Experiments on the multilingual dependency parsing task show that the learned position vectors exhibit meaningful hidden structures, and they can help achieving the best multilingual parsing results. © 2023 Association for Computational Linguistics."

Název v anglickém jazyce

Typology Guided Multilingual Position Representations: Case on Dependency Parsing

Popis výsledku anglicky

"Recent multilingual models benefit from strong unified semantic representation models. However, due to conflict linguistic regularities, ignoring language-specific features during multilingual learning may suffer from negative transfer. In this work, we analyze the relation between a language's position space and its typological characterization, and suggest deploying different position spaces for different languages. We develop a position generation network which combines prior knowledge from typology features and existing position vectors. Experiments on the multilingual dependency parsing task show that the learned position vectors exhibit meaningful hidden structures, and they can help achieving the best multilingual parsing results. © 2023 Association for Computational Linguistics."

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)

Projekt

—

Návaznosti

—

Rok uplatnění

2023

Kód důvěrnosti údajů

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

Název statě ve sborníku

"Proc. Annu. Meet. Assoc. Comput Linguist."

ISBN

978-195942962-3

ISSN

0736-587X

e-ISSN

—

Počet stran výsledku

18

Strana od-do

13524-13541

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

—