Pseudo-Semantic Graphs for Generating Paraphrases

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2024

Autores

Sousa, A (Autor) Outra; Henrique Lopes Cardoso (Autor) FEUP

Ata de Conferência Internacional

Título: Progress in Artificial Intelligence - 23rd EPIA Conference on Artificial Intelligence, EPIA 2024, Viana do Castelo, Portugal, September 3-6, 2024, Proceedings, Part III

Páginas: 215-227

23rd EPIA Conference on Artificial Intelligence, EPIA 2024

Viana do Castelo, 3 September 2024 through 6 September 2024

Indexação

Scopus - 0 Citações

Outras Informações

ID Authenticus: P-017-CVA

DOI: 10.1007/978-3-031-73503-5_18

Abstract (EN): 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.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 12