Utilize este identificador para referenciar este registo:
http://hdl.handle.net/10071/17048
Registo completo
Campo DC | Valor | Idioma |
---|---|---|
dc.contributor.author | Ribeiro, E. | - |
dc.contributor.author | Ribeiro, R. | - |
dc.contributor.author | de Matos, D. M. | - |
dc.contributor.editor | Gennady Agre, Josef van Genabith, Thierry Declerck | - |
dc.date.accessioned | 2019-01-10T17:49:59Z | - |
dc.date.available | 2019-01-10T17:49:59Z | - |
dc.date.issued | 2018 | - |
dc.identifier.isbn | 978-3-319-99343-0 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | https://ciencia.iscte-iul.pt/id/ci-pub-52995 | - |
dc.identifier.uri | http://hdl.handle.net/10071/17048 | - |
dc.description.abstract | Dialog act recognition is an important step for dialog systems since it reveals the intention behind the uttered words. Most approaches on the task use word-level tokenization. In contrast, this paper explores the use of character-level tokenization. This is relevant since there is information at the sub-word level that is related to the function of the words and, thus, their intention. We also explore the use of different context windows around each token, which are able to capture important elements, such as affixes. Furthermore, we assess the importance of punctuation and capitalization. We performed experiments on both the Switchboard Dialog Act Corpus and the DIHANA Corpus. In both cases, the experiments not only show that character-level tokenization leads to better performance than the typical word-level approaches, but also that both approaches are able to capture complementary information. Thus, the best results are achieved by combining tokenization at both levels. | eng |
dc.language.iso | eng | - |
dc.publisher | Springer | - |
dc.relation | UID/CEC/50021/2013 | - |
dc.rights | openAccess | - |
dc.subject | Dialog act recognition | eng |
dc.subject | Character-level | eng |
dc.subject | Switchboard dialog act corpus | eng |
dc.subject | DIHANA corpus | eng |
dc.subject | Multilinguality | eng |
dc.title | A study on dialog act recognition using character-level tokenization | eng |
dc.type | conferenceObject | - |
dc.event.type | Conferência | pt |
dc.event.location | Varna | eng |
dc.event.date | 2018 | - |
dc.pagination | 93 - 103 | - |
dc.peerreviewed | yes | - |
dc.journal | 18th International Conference on Artificial Intelligence: Methodology, Systems, and Applications, AIMSA 2018 | - |
dc.volume | 11089 | - |
degois.publication.firstPage | 93 | - |
degois.publication.lastPage | 103 | - |
degois.publication.location | Varna | eng |
degois.publication.title | A study on dialog act recognition using character-level tokenization | eng |
dc.description.version | info:eu-repo/semantics/acceptedVersion | - |
dc.identifier.doi | 10.1007/978-3-319-99344-7_9 | - |
dc.subject.fos | Domínio/Área Científica::Ciências Naturais::Matemáticas | por |
dc.subject.fos | Domínio/Área Científica::Ciências Naturais::Ciências da Computação e da Informação | por |
Aparece nas coleções: | CTI-CRI - Comunicações a conferências internacionais |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
1805.07231.pdf | Pós-print | 399,24 kB | Adobe PDF | Ver/Abrir |
Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.