Publicação
DEBACER: a method for slicing moderated debates
| dc.contributor.author | Ferraz, Thomas Palmeira | |
| dc.contributor.author | Alcoforado, Alexandre | |
| dc.contributor.author | Bustos, Enzo | |
| dc.contributor.author | Oliveira, André Seidel | |
| dc.contributor.author | Gerber, Rodrigo | |
| dc.contributor.author | Müller, Naíde | |
| dc.contributor.author | d’Almeida, André Corrêa | |
| dc.contributor.author | Veloso, Bruno Miguel | |
| dc.contributor.author | Costa, Anna Helena Reali | |
| dc.date.accessioned | 2022-03-22T09:50:11Z | |
| dc.date.available | 2022-03-22T09:50:11Z | |
| dc.date.issued | 2021-11-29 | |
| dc.description.abstract | Subjects change frequently in moderated debates with several participants, such as in parliamentary sessions, electoral debates, and trials. Partitioning a debate into blocks with the same subject is essential for understanding. Often a moderator is responsible for defining when a new block begins so that the task of automatically partitioning a moderated debate can focus solely on the moderator's behavior. In this paper, we (i) propose a new algorithm, DEBACER, which partitions moderated debates; (ii) carry out a comparative study between conventional and BERTimbau pipelines; and (iii) validate DEBACER applying it to the minutes of the Assembly of the Republic of Portugal. Our results show the effectiveness of DEBACER. | pt_PT |
| dc.description.version | info:eu-repo/semantics/publishedVersion | pt_PT |
| dc.identifier.doi | 10.5753/eniac.2021.18293 | pt_PT |
| dc.identifier.uri | http://hdl.handle.net/10400.14/37105 | |
| dc.language.iso | eng | pt_PT |
| dc.peerreviewed | yes | pt_PT |
| dc.publisher | Sociedade Brasileira de Computação | pt_PT |
| dc.subject | Language processing | pt_PT |
| dc.subject | Political documents | pt_PT |
| dc.subject | Spoken text processing | pt_PT |
| dc.subject | Speech split | pt_PT |
| dc.subject | Dialogue partitioning | pt_PT |
| dc.title | DEBACER: a method for slicing moderated debates | pt_PT |
| dc.type | book part | |
| dspace.entity.type | Publication | |
| oaire.citation.endPage | 678 | pt_PT |
| oaire.citation.startPage | 667 | pt_PT |
| oaire.citation.title | ENIAC 2021: XVIII encontro nacional de inteligência artificial e computacional. 18th national meeting on artificial and computational intelligence | pt_PT |
| rcaap.rights | openAccess | pt_PT |
| rcaap.type | bookPart | pt_PT |
Ficheiros
Principais
1 - 1 de 1
Miniatura indisponível
- Nome:
- document (4).pdf
- Tamanho:
- 416.4 KB
- Formato:
- Adobe Portable Document Format