Translating Natural Language Instructions for Behavioral Robot Navigation with a Multi-Head Attention Mechanism

Patricio Cerda-Mardini, Vladimir Araujo, Álvaro Soto


Abstract
We propose a multi-head attention mechanism as a blending layer in a neural network model that translates natural language to a high level behavioral language for indoor robot navigation. We follow the framework established by (Zang et al., 2018a) that proposes the use of a navigation graph as a knowledge base for the task. Our results show significant performance gains when translating instructions on previously unseen environments, therefore, improving the generalization capabilities of the model.
Anthology ID:
2020.winlp-1.24
Volume:
Proceedings of the Fourth Widening Natural Language Processing Workshop
Month:
July
Year:
2020
Address:
Seattle, USA
Editors:
Rossana Cunha, Samira Shaikh, Erika Varis, Ryan Georgi, Alicia Tsai, Antonios Anastasopoulos, Khyathi Raghavi Chandu
Venue:
WiNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
96–98
Language:
URL:
https://aclanthology.org/2020.winlp-1.24
DOI:
10.18653/v1/2020.winlp-1.24
Bibkey:
Cite (ACL):
Patricio Cerda-Mardini, Vladimir Araujo, and Álvaro Soto. 2020. Translating Natural Language Instructions for Behavioral Robot Navigation with a Multi-Head Attention Mechanism. In Proceedings of the Fourth Widening Natural Language Processing Workshop, pages 96–98, Seattle, USA. Association for Computational Linguistics.
Cite (Informal):
Translating Natural Language Instructions for Behavioral Robot Navigation with a Multi-Head Attention Mechanism (Cerda-Mardini et al., WiNLP 2020)
Copy Citation:
Video:
 http://slideslive.com/38929563