Sökning: id:"swepub:oai:gup.ub.gu.se/294796" >
Fast visual groundi...
Fast visual grounding in interaction: bringing few-shot learning with neural networks to an interactive robot
-
Cano Santín, José Miguel, 1990 (författare)
-
- Dobnik, Simon, 1977 (författare)
- Gothenburg University,Göteborgs universitet,Institutionen för filosofi, lingvistik och vetenskapsteori,Department of Philosophy, Linguistics and Theory of Science
-
- Ghanimifard, Mehdi, 1984 (författare)
- Gothenburg University,Göteborgs universitet,Institutionen för filosofi, lingvistik och vetenskapsteori,Department of Philosophy, Linguistics and Theory of Science
-
(creator_code:org_t)
- Association for Computational Linguistics (ACL), 2020
- 2020
- Engelska.
-
Ingår i: Proceedings of Conference on Probability and Meaning (PaM-2020), Gothenburg, Sweden (online) / Christine Howes, Stergios Chatzikyriakidis, Adam Ek and Vidya Somashekarappa (eds.). - : Association for Computational Linguistics (ACL). - 2002-9764.
- Relaterad länk:
-
https://gup.ub.gu.se... (primary) (free)
-
visa fler...
-
https://gup.ub.gu.se...
-
visa färre...
Abstract
Ämnesord
Stäng
- The major shortcomings of using neural networks with situated agents are that in incremental interaction very few learning examples are available and that their visual sensory representations are quite different from image caption datasets. In this work we adapt and evaluate a few-shot learning approach, Matching Networks (Vinyals et al., 2016), to conversational strategies of a robot interacting with a human tutor in order to efficiently learn to categorise objects that are presented to it and also investigate to what degree transfer learning from pre-trained models on images from different contexts can improve its performance. We discuss the implications of such learning on the nature of semantic representations the system has learned.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Språkteknologi (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Language Technology (hsv//eng)
Nyckelord
- situated interactive agents
- robots
- few-shot learning
- object recognition
- dialogue
- grounding
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas