Natural Language Grounding and Grammar Induction for Robotic Manipulation Commands

التفاصيل البيبلوغرافية
العنوان: Natural Language Grounding and Grammar Induction for Robotic Manipulation Commands
المؤلفون: Alomari, M, Duckworth, P, Hawasly, M, Hogg, DC, Cohn, AG
بيانات النشر: The Association for Computational Linguistics
سنة النشر: 2017
المجموعة: White Rose Research Online (Universities of Leeds, Sheffield & York)
الوصف: We present a cognitively plausible system capable of acquiring knowledge in language and vision from pairs of short video clips and linguistic descriptions. The aim of this work is to teach a robot manipulator how to execute natural language commands by demonstration. This is achieved by first learning a set of visual `concepts' that abstract the visual feature spaces into concepts that have human-level meaning. Second, learning the mapping/grounding between words and the extracted visual concepts. Third, inducing grammar rules via a semantic representation known as Robot Control Language (RCL). We evaluate our approach against state-of-the-art supervised and unsupervised grounding and grammar induction systems, and show that a robot can learn to execute never seen-before commands from pairs of unlabelled linguistic and visual inputs.
نوع الوثيقة: report
اللغة: unknown
Relation: Alomari, M orcid.org/0000-0002-6565-4887 , Duckworth, P, Hawasly, M et al. (2 more authors) (2017) Natural Language Grounding and Grammar Induction for Robotic Manipulation Commands. In: Proceedings of the First Workshop on Language Grounding for Robotics. 1st Workshop on Language Grounding for Robotics at ACL 2017, 30 Jul - 04 Aug 2017, Vancouver, BC. The Association for Computational Linguistics , pp. 35-43. ISBN 978-1-945626-64-7
الاتاحة: https://eprints.whiterose.ac.uk/119757/
http://aclweb.org/anthology/W/W17/W17-28.pdf
رقم الانضمام: edsbas.825683B5
قاعدة البيانات: BASE