Exportar Publicação

Ribeiro, E., Ribeiro, R. & Matos, D. M. de. (2023). Automatic recognition of the general-purpose communicative functions defined by the ISO 24617-2 standard for dialog act annotation (Extended abstract). In Elkind, E. (Ed.), Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence. (pp. 6948-6953). Macao, SAR: International Joint Conferences on Artifical Intelligence (IJCAI).

E. Ribeiro et al.,  "Automatic recognition of the general-purpose communicative functions defined by the ISO 24617-2 standard for dialog act annotation (Extended abstract)", in Proc. of the Thirty-2nd Int. Joint Conf. on Artificial Intelligence, Elkind, E., Ed., Macao, SAR, International Joint Conferences on Artifical Intelligence (IJCAI), 2023, pp. 6948-6953

@inproceedings{ribeiro2023_1715323756916,
	author = "Ribeiro, E. and Ribeiro, R. and Matos, D. M. de.",
	title = "Automatic recognition of the general-purpose communicative functions defined by the ISO 24617-2 standard for dialog act annotation (Extended abstract)",
	booktitle = "Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence",
	year = "2023",
	editor = "Elkind, E.",
	volume = "",
	number = "",
	series = "",
	doi = "10.24963/IJCAI.2023/788",
	pages = "6948-6953",
	publisher = "International Joint Conferences on Artifical Intelligence (IJCAI)",
	address = "Macao, SAR",
	organization = "International Joint Conferences on Artifical Intelligence (IJCAI)",
	url = "https://www.ijcai.org/proceedings/2023/"
}

TY  - CPAPER
TI  - Automatic recognition of the general-purpose communicative functions defined by the ISO 24617-2 standard for dialog act annotation (Extended abstract)
T2  - Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence
AU  - Ribeiro, E.
AU  - Ribeiro, R.
AU  - Matos, D. M. de.
PY  - 2023
SP  - 6948-6953
DO  - 10.24963/IJCAI.2023/788
CY  - Macao, SAR
UR  - https://www.ijcai.org/proceedings/2023/
AB  - From the perspective of a dialog system, the identification of the intention behind the segments in a dialog is important, as it provides cues regarding the information present in the segments and how they should be interpreted. The ISO 24617-2 standard for dialog act annotation defines a hierarchically organized set of general-purpose communicative functions that correspond to different intentions that are relevant in the context of a dialog. In this paper, we explore the automatic recognition of these functions. To do so, we propose to adapt existing approaches to dialog act recognition, so that they can deal with the hierarchical classification problem. More specifically, we propose the use of an end-to-end hierarchical network with cascading outputs and maximum a posteriori path estimation to predict the communicative function at each level of the hierarchy, preserve the dependencies between the functions in the path, and decide at which level to stop. Additionally, we rely on transfer learning processes to address the data scarcity problem. Our experiments on the DialogBank show that this approach outperforms both flat and hierarchical approaches based on multiple classifiers and that each of its components plays an important role in the recognition of general-purpose communicative functions
ER  -