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

Result code in 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>

Result on the web

<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

—

Result language

angličtina

Original language name

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

Original language description

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

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2024

Confidentiality

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

Article name in the collection

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

ISBN

979-889176155-1

ISSN

—

e-ISSN

—

Number of pages

13

Pages from-to

45-57

Publisher name

Association for Computational Linguistics (ACL)

Place of publication

—

Event location

Bangkok

Event date

Jan 1, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—