Learning from limited datasets: Implications for Natural Language Generation and Human-Robot Interaction

Jekaterina Belakova, Dimitra Gkatzia


Abstract
One of the most natural ways for human robot communication is through spoken language. Training human-robot interaction systems require access to large datasets which are expensive to obtain and labour intensive. In this paper, we describe an approach for learning from minimal data, using as a toy example language understanding in spoken dialogue systems. Understanding of spoken language is crucial because it has implications for natural language generation, i.e. correctly understanding a user’s utterance will lead to choosing the right response/action. Finally, we discuss implications for Natural Language Generation in Human-Robot Interaction.
Anthology ID:
W18-6902
Volume:
Proceedings of the Workshop on NLG for Human–Robot Interaction
Month:
November
Year:
2018
Address:
Tilburg, The Netherlands
Editors:
Mary Ellen Foster, Hendrik Buschmeier, Dimitra Gkatzia
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
8–11
Language:
URL:
https://aclanthology.org/W18-6902
DOI:
10.18653/v1/W18-6902
Bibkey:
Cite (ACL):
Jekaterina Belakova and Dimitra Gkatzia. 2018. Learning from limited datasets: Implications for Natural Language Generation and Human-Robot Interaction. In Proceedings of the Workshop on NLG for Human–Robot Interaction, pages 8–11, Tilburg, The Netherlands. Association for Computational Linguistics.
Cite (Informal):
Learning from limited datasets: Implications for Natural Language Generation and Human-Robot Interaction (Belakova & Gkatzia, INLG 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6902.pdf