Playing with Embeddings : Evaluating embeddings for Robot Language Learning through MUD Games

Anmol Gulati, Kumar Krishna Agrawal


Abstract
Acquiring language provides a ubiquitous mode of communication, across humans and robots. To this effect, distributional representations of words based on co-occurrence statistics, have provided significant advancements ranging across machine translation to comprehension. In this paper, we study the suitability of using general purpose word-embeddings for language learning in robots. We propose using text-based games as a proxy to evaluating word embedding on real robots. Based in a risk-reward setting, we review the effectiveness of the embeddings in navigating tasks in fantasy games, as an approximation to their performance on more complex scenarios, like language assisted robot navigation.
Anthology ID:
W17-5305
Volume:
Proceedings of the 2nd Workshop on Evaluating Vector Space Representations for NLP
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Samuel Bowman, Yoav Goldberg, Felix Hill, Angeliki Lazaridou, Omer Levy, Roi Reichart, Anders Søgaard
Venue:
RepEval
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
27–30
Language:
URL:
https://aclanthology.org/W17-5305/
DOI:
10.18653/v1/W17-5305
Bibkey:
Cite (ACL):
Anmol Gulati and Kumar Krishna Agrawal. 2017. Playing with Embeddings : Evaluating embeddings for Robot Language Learning through MUD Games. In Proceedings of the 2nd Workshop on Evaluating Vector Space Representations for NLP, pages 27–30, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Playing with Embeddings : Evaluating embeddings for Robot Language Learning through MUD Games (Gulati & Agrawal, RepEval 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-5305.pdf