Multifunctional ISO standard Dialogue Act tagging in Italian
The task of Dialogue Act (DA) tagging, a crucial component in many conversational agents, is often addressed assuming a single DA per speaker turn in the conversation. However, speakers' turns are often multifunctional, that is they can contain more than one DA (i.e. “I’m Alex. Have we met before?” contains a ‘statement’, followed by a ‘question’). This work focuses on multifunctional DA tagging in Italian. First, we present iLISTEN2ISO, a novel resource with multifunctional DAs annotation in Italian, created by annotating the iLISTEN corpus with the ISO standard. We provide an analysis of the corpus showing the importance of multifunctionality for DA tagging. Additionally, we train DA taggers for Italian on iLISTEN (achieving State of the Art results) and iLISTEN2ISO. Our findings indicate the importance of using a multifunctional approach for DA tagging.
Organization
- code: this folder contains the models used to achieve the resutls proposed in the paper.
- resource: this folder contains the mapping from iLISTEN to iLISTEN2ISO.
- paper: Multifunctional ISO standard Dialogue Act tagging in Italian.pdf
In order to run the code, you need the resources. Thus first visit the resource folder and then please go to the code folder.
Reference
If you use this resource or this code in your research, please cite us:
@article{roccabruna2020multifunctional,
title={Multifunctional ISO standard Dialogue Act tagging in Italian},
author={Roccabruna, Gabriel and Cervone, Alessandra and Riccardi, Giuseppe},
year={2020}
}