Investigating Multilingual Coreference Resolution by Universal Annotations

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A2U5BUUQE" target="_blank" >RIV/00216208:11320/23:2U5BUUQE - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2023.findings-emnlp.671/" target="_blank" >https://aclanthology.org/2023.findings-emnlp.671/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2023.findings-emnlp.671" target="_blank" >10.18653/v1/2023.findings-emnlp.671</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Investigating Multilingual Coreference Resolution by Universal Annotations

Popis výsledku v původním jazyce

"Multilingual coreference resolution (MCR) has been a long-standing and challenging task. With the newly proposed multilingual coreference dataset, CorefUD (Nedoluzhko et al., 2022), we conduct an investigation into the task by using its harmonized universal morphosyntactic and coreference annotations. First, we study coreference by examining the ground truth data at different linguistic levels, namely mention, entity and document levels, and across different genres, to gain insights into the characteristics of coreference across multiple languages. Second, we perform an error analysis of the most challenging cases that the SotA system fails to resolve in the CRAC 2022 shared task using the universal annotations. Last, based on this analysis, we extract features from universal morphosyntactic annotations and integrate these features into a baseline system to assess their potential benefits for the MCR task. Our results show that our best configuration of features improves the baseline by 0.9% F1 score."

Název v anglickém jazyce

Investigating Multilingual Coreference Resolution by Universal Annotations

Popis výsledku anglicky

"Multilingual coreference resolution (MCR) has been a long-standing and challenging task. With the newly proposed multilingual coreference dataset, CorefUD (Nedoluzhko et al., 2022), we conduct an investigation into the task by using its harmonized universal morphosyntactic and coreference annotations. First, we study coreference by examining the ground truth data at different linguistic levels, namely mention, entity and document levels, and across different genres, to gain insights into the characteristics of coreference across multiple languages. Second, we perform an error analysis of the most challenging cases that the SotA system fails to resolve in the CRAC 2022 shared task using the universal annotations. Last, based on this analysis, we extract features from universal morphosyntactic annotations and integrate these features into a baseline system to assess their potential benefits for the MCR task. Our results show that our best configuration of features improves the baseline by 0.9% F1 score."

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

"Findings of the Association for Computational Linguistics: EMNLP 2023"

ISBN

979-8-89176-061-5

ISSN

—

e-ISSN

—

Počet stran výsledku

15

Strana od-do

10010-10024

Název nakladatele

arXiv

Místo vydání

Singapore

Místo konání akce

Singapore

Datum konání akce

1. 1. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—