Streamlining event extraction with a simplified annotation framework

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3ATJQ66J84" target="_blank" >RIV/00216208:11320/25:TJQ66J84 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85192957688&doi=10.3389%2ffrai.2024.1361483&partnerID=40&md5=99dbcba6e126c86c6b93390eef61f2b6" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85192957688&doi=10.3389%2ffrai.2024.1361483&partnerID=40&md5=99dbcba6e126c86c6b93390eef61f2b6</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3389/frai.2024.1361483" target="_blank" >10.3389/frai.2024.1361483</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Streamlining event extraction with a simplified annotation framework

Popis výsledku v původním jazyce

Event extraction, grounded in semantic relationships, can serve as a simplified relation extraction. In this study, we propose an efficient open-domain event annotation framework tailored for subsequent information extraction, with a specific focus on its applicability to low-resource languages. The proposed event annotation method, which is based on event semantic elements, demonstrates substantial time-efficiency gains over traditional Universal Dependencies (UD) tagging. We show how language-specific pretraining outperforms multilingual counterparts in entity and relation extraction tasks and emphasize the importance of task- and language-specific fine-tuning for optimal model performance. Furthermore, we demonstrate the improvement of model performance upon integrating UD information during pre-training, achieving the F1 score of 71.16 and 60.43% for entity and relation extraction respectively. In addition, we showcase the usage of our extracted event graph for improving node classification in a retail banking domain. This work provides valuable guidance on improving information extraction and outlines a methodology for developing training datasets, particularly for low-resource languages. Copyright © 2024 Saetia, Thonglong, Amornchaiteera, Chalothorn, Taerungruang and Buabthong.

Název v anglickém jazyce

Streamlining event extraction with a simplified annotation framework

Popis výsledku anglicky

Event extraction, grounded in semantic relationships, can serve as a simplified relation extraction. In this study, we propose an efficient open-domain event annotation framework tailored for subsequent information extraction, with a specific focus on its applicability to low-resource languages. The proposed event annotation method, which is based on event semantic elements, demonstrates substantial time-efficiency gains over traditional Universal Dependencies (UD) tagging. We show how language-specific pretraining outperforms multilingual counterparts in entity and relation extraction tasks and emphasize the importance of task- and language-specific fine-tuning for optimal model performance. Furthermore, we demonstrate the improvement of model performance upon integrating UD information during pre-training, achieving the F1 score of 71.16 and 60.43% for entity and relation extraction respectively. In addition, we showcase the usage of our extracted event graph for improving node classification in a retail banking domain. This work provides valuable guidance on improving information extraction and outlines a methodology for developing training datasets, particularly for low-resource languages. Copyright © 2024 Saetia, Thonglong, Amornchaiteera, Chalothorn, Taerungruang and Buabthong.

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

2024

Kód důvěrnosti údajů

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

Název periodika

Frontiers in Artificial Intelligence

ISSN

2624-8212

e-ISSN

—

Svazek periodika

7

Číslo periodika v rámci svazku

2024

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

9

Strana od-do

1-9

Kód UT WoS článku

001218681100001

EID výsledku v databázi Scopus

2-s2.0-85192957688