Pseudo-Semantic Graphs for Generating Paraphrases

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AE5QZUZ6F" target="_blank" >RIV/00216208:11320/26:E5QZUZ6F - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-031-73503-5_18" target="_blank" >http://dx.doi.org/10.1007/978-3-031-73503-5_18</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-73503-5_18" target="_blank" >10.1007/978-3-031-73503-5_18</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Pseudo-Semantic Graphs for Generating Paraphrases

Popis výsledku v původním jazyce

Paraphrases are texts written using different words but conveying the same meaning; hence, their quality is based upon retaining semantics while varying syntax/vocabulary. Recent works leverage structured syntactic information to control the syntax of the generations while relying on pretrained language models to retain the semantics. However, rarely do works in the literature consider using structured semantic information to enrich the language representation. In this work, we propose to model the task of paraphrase generation as a pseudo-Graph-to-Text task where we fine-tune pretrained language models using as input linearized representations of pseudo-semantic graphs built from dependency parsing trees sourced from the original input texts. Our model achieves competitive results on three popular paraphrase generation benchmarks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Název v anglickém jazyce

Pseudo-Semantic Graphs for Generating Paraphrases

Popis výsledku anglicky

Paraphrases are texts written using different words but conveying the same meaning; hence, their quality is based upon retaining semantics while varying syntax/vocabulary. Recent works leverage structured syntactic information to control the syntax of the generations while relying on pretrained language models to retain the semantics. However, rarely do works in the literature consider using structured semantic information to enrich the language representation. In this work, we propose to model the task of paraphrase generation as a pseudo-Graph-to-Text task where we fine-tune pretrained language models using as input linearized representations of pseudo-semantic graphs built from dependency parsing trees sourced from the original input texts. Our model achieves competitive results on three popular paraphrase generation benchmarks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

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

2025

Kód důvěrnosti údajů

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

Název statě ve sborníku

Lect. Notes Comput. Sci.

ISBN

978-3-031-73502-8

ISSN

—

e-ISSN

—

Počet stran výsledku

13

Strana od-do

215-227

Název nakladatele

Springer Science and Business Media Deutschland GmbH

Místo vydání

—

Místo konání akce

Viana do Castelo

Datum konání akce

1. 1. 2026

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—