LIHLITHAprendiendo a interactuar con las personas mediante la interacción continuada con personas
- Peñas Padilla, Anselmo
- Cieliebak, Mark
- Agirre Bengoa, Eneko
- Otegi, Arantxa
- Pradel, Camille
- Rosset, Sophie
ISSN: 1135-5948
Année de publication: 2019
Número: 63
Pages: 147-150
Type: Article
D'autres publications dans: Procesamiento del lenguaje natural
Résumé
The LIHLITH project will research, innovate and validate a new lifelong learning framework for the interaction of humans and machines on specific domains with the aim of improving the quality of existing dialogue systems and lowering the cost of deployment in new domains. LILITH will develop dialogue systems that learn autonomously from their interactions with the users, and retain this new knowledge in order to answer more accurately in future interactions. The key insight is that the dialogue systems will be designed to get feedback from the user. Based on this feedback, the system will keep improving after deployment all modules down in the pipeline. LIHLITH project will also develop and deliver evaluation protocols and benchmarks to allow public comparison and reproducibility. |
Références bibliographiques
- Agirre, E., A. Jonsson, and A. Larcher. 2019. Framing lifelong learning as autonomous deployment: Tune once live forever. In Proceedings of the Dialogue systems and lifelong learning special session of the Tenth International Workshop on Spoken Dialogue Systems Technology (IWSDS).
- Chen, Z. and B. Liu. 2016. Lifelong Machine Learning. Morgan & Claypool Publishers.