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

Belakova, Jekaterina; Gkatzia, Dimitra

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.

Citation

Belakova, J., & Gkatzia, D. (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 (8-11)

• Conference Name: Workshop on NLG for Human–Robot Interaction
• Conference Location: Tilburg, The Netherlands
• Start Date: Nov 8, 2018
• Publication Date: 2018
• Deposit Date: Apr 21, 2020
• Publicly Available Date: Apr 21, 2020
• Publisher: Association for Computational Linguistics (ACL)
• Pages: 8-11
• Book Title: Proceedings of the Workshop on NLG for Human–Robot Interaction
• Public URL: http://researchrepository.napier.ac.uk/Output/1791784