Exportar Publicação

Ribeiro, E., Ribeiro, R. & de Matos, D. M. (2018). A study on dialog act recognition using character-level tokenization. In Gennady Agre, Josef van Genabith, Thierry Declerck (Ed.), 18th International Conference on Artificial Intelligence: Methodology, Systems, and Applications, AIMSA 2018. (pp. 93-103). Varna: Springer.

E. Ribeiro et al.,  "A study on dialog act recognition using character-level tokenization", in 18th Int. Conf. on Artificial Intelligence: Methodology, Systems, and Applications, AIMSA 2018, Gennady Agre, Josef van Genabith, Thierry Declerck, Ed., Varna, Springer, 2018, vol. 11089, pp. 93-103

@inproceedings{ribeiro2018_1715083504819,
	author = "Ribeiro, E. and Ribeiro, R. and de Matos, D. M.",
	title = "A study on dialog act recognition using character-level tokenization",
	booktitle = "18th International Conference on Artificial Intelligence: Methodology, Systems, and Applications, AIMSA 2018",
	year = "2018",
	editor = "Gennady Agre, Josef van Genabith, Thierry Declerck",
	volume = "11089",
	number = "",
	series = "",
	doi = "10.1007/978-3-319-99344-7_9",
	pages = "93-103",
	publisher = "Springer",
	address = "Varna",
	organization = "",
	url = "https://link.springer.com/chapter/10.1007%2F978-3-319-99344-7_9"
}

TY  - CPAPER
TI  - A study on dialog act recognition using character-level tokenization
T2  - 18th International Conference on Artificial Intelligence: Methodology, Systems, and Applications, AIMSA 2018
VL  - 11089
AU  - Ribeiro, E.
AU  - Ribeiro, R.
AU  - de Matos, D. M.
PY  - 2018
SP  - 93-103
SN  - 0302-9743
DO  - 10.1007/978-3-319-99344-7_9
CY  - Varna
UR  - https://link.springer.com/chapter/10.1007%2F978-3-319-99344-7_9
AB  - 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.
ER  -