Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A6TIQXW8U" target="_blank" >RIV/00216208:11320/25:6TIQXW8U - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204923340&partnerID=40&md5=9aacebb8f7b0c75a6e4a6edd8bb9c4af" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204923340&partnerID=40&md5=9aacebb8f7b0c75a6e4a6edd8bb9c4af</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm

Popis výsledku v původním jazyce

In this paper, we conduct a holistic exploration of Universal Decompositional Semantic (UDS) parsing, aiming to provide a more efficient and effective solution for semantic parsing and to envision the development prospects after the emergence of large language models (LLMs). To achieve this, we first introduce a cascade model for UDS parsing that decomposes the complex task into semantically appropriate subtasks. Our approach outperforms prior models while significantly reducing inference time. Furthermore, to further exploit the hierarchical and automated annotation process of UDS, we explore the use of syntactic information and pseudo-labels, both of which enhance UDS parsing. Lastly, we investigate ChatGPT’s efficacy in handling the UDS task, highlighting its proficiency in attribute parsing but struggles in relation parsing, revealing that small parsing models still hold research significance. Our code is available at https://github.com/hexuandeng/HExp4UDS. © 2024 Association for Computational Linguistics

Název v anglickém jazyce

Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm

Popis výsledku anglicky

In this paper, we conduct a holistic exploration of Universal Decompositional Semantic (UDS) parsing, aiming to provide a more efficient and effective solution for semantic parsing and to envision the development prospects after the emergence of large language models (LLMs). To achieve this, we first introduce a cascade model for UDS parsing that decomposes the complex task into semantically appropriate subtasks. Our approach outperforms prior models while significantly reducing inference time. Furthermore, to further exploit the hierarchical and automated annotation process of UDS, we explore the use of syntactic information and pseudo-labels, both of which enhance UDS parsing. Lastly, we investigate ChatGPT’s efficacy in handling the UDS task, highlighting its proficiency in attribute parsing but struggles in relation parsing, revealing that small parsing models still hold research significance. Our code is available at https://github.com/hexuandeng/HExp4UDS. © 2024 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

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

SIGHAN - SIGHAN Workshop Chin. Language Processing, Proc. Workshop

ISBN

979-889176155-1

ISSN

—

e-ISSN

—

Počet stran výsledku

13

Strana od-do

45-57

Název nakladatele

Association for Computational Linguistics (ACL)

Místo vydání

—

Místo konání akce

Bangkok

Datum konání akce

1. 1. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—