Exploring a POS-based Two-stage Approach for Improving Low-Resource AMR-to-Text Generation

Marco Antonio Sobrevilla Cabezudo, Thiago Alexandre Salgueiro Pardo

Producción científica: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

Resumen

This work presents a two-stage approach for tackling low-resource AMR-to-text generation for Brazilian Portuguese. Our approach consists of (1) generating a masked surface realization in which some tokens are masked according to its Part-of-Speech class and (2) infilling the masked tokens according to the AMR graph and the previous masked surface realization. Results show a slight improvement over the baseline, mainly in BLEU (1.63) and METEOR (0.02) scores. Moreover, we evaluate the pipeline components separately, showing that the bottleneck of the pipeline is the masked surface realization. Finally, the human revision suggests that models still suffer from hallucinations, and some strategies to deal with the problems found are proposed.

Idioma originalInglés
Título de la publicación alojadaGEM 2022 - 2nd Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings of the Workshop
EditorialAssociation for Computational Linguistics (ACL)
Páginas531-538
Número de páginas8
ISBN (versión digital)9781959429128
EstadoPublicada - 2022
Publicado de forma externa
Evento2nd Workshop on Natural Language Generation, Evaluation, and Metrics, GEM 2022, as part of EMNLP 2022 - Abu Dhabi, Emiratos Árabes Unidos
Duración: 7 dic. 2022 → …

Serie de la publicación

NombreGEM 2022 - 2nd Workshop on Natural Language Generation, Evaluation, and Metrics, Proceedings of the Workshop

Conferencia

Conferencia2nd Workshop on Natural Language Generation, Evaluation, and Metrics, GEM 2022, as part of EMNLP 2022
País/TerritorioEmiratos Árabes Unidos
CiudadAbu Dhabi
Período7/12/22 → …

Huella

Profundice en los temas de investigación de 'Exploring a POS-based Two-stage Approach for Improving Low-Resource AMR-to-Text Generation'. En conjunto forman una huella única.

Citar esto