%0 Conference Proceedings %T Learning from limited datasets: Implications for Natural Language Generation and Human-Robot Interaction %A Belakova, Jekaterina %A Gkatzia, Dimitra %Y Foster, Mary Ellen %Y Buschmeier, Hendrik %Y Gkatzia, Dimitra %S Proceedings of the Workshop on NLG for Human–Robot Interaction %D 2018 %8 November %I Association for Computational Linguistics %C Tilburg, The Netherlands %F belakova-gkatzia-2018-learning %X 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. %R 10.18653/v1/W18-6902 %U https://aclanthology.org/W18-6902 %U https://doi.org/10.18653/v1/W18-6902 %P 8-11