| Full text | |
| Author(s): |
Sobrevilla Cabezudo, Marco Antonio
;
Salgueiro, Thiago Alexandre
Total Authors: 2
|
| Document type: | Journal article |
| Source: | PROCESAMIENTO DEL LENGUAJE NATURAL; v. N/A, n. 68, p. 13-pg., 2022-03-01. |
| Abstract | |
This work presents a study of how varied strategies for tackling low-resource AMR-to-text generation for three approaches are helpful in Brazilian Portuguese. Specifically, we explore the helpfulness of additional translated corpus, different granularity levels in input representation, and three preprocessing steps. Results show that translation is useful. However, it must be used in each approach differently. In addition, finer-grained representations as characters and subwords improve the performance and reduce the bias on the development set, and preprocessing steps are helpful in different contexts, being delexicalisation and preordering the most important ones. (AU) | |
| FAPESP's process: | 19/07665-4 - Center for Artificial Intelligence |
| Grantee: | Fabio Gagliardi Cozman |
| Support Opportunities: | Research Grants - Research Program in eScience and Data Science - Research Centers in Engineering Program |
| FAPESP's process: | 13/07375-0 - CeMEAI - Center for Mathematical Sciences Applied to Industry |
| Grantee: | Francisco Louzada Neto |
| Support Opportunities: | Research Grants - Research, Innovation and Dissemination Centers - RIDC |