363 citations
- Heriot-Watt UniversityGB51 papers
- University of EdinburghGB10 papers
- Maxwell Institute for Mathematical SciencesGB9 papers
- Centre National de la Recherche ScientifiqueFR6 papers
- Imperial College LondonGB5 papers
- University of OxfordGB4 papers
- Huazhong University of Science and TechnologyCN3 papers
- Université de LilleFR3 papers
- CEA Paris-SaclayFR2 papers
- Center for Astrophysics Harvard & SmithsonianUS2 papers
- Centre de Recherche en InformatiqueFR2 papers
- Centre de Recherche en Informatique, Signal et Automatique de LilleFR2 papers
Showing 2017 · cs.CLShow all
3 papers · 2 filters
cs.CL2017★ 7 cited
The BURCHAK corpus: a Challenge Data Set for Interactive Learning of Visually Grounded Word Meanings
Yanchao Yu, Arash Eshghi, Gregory Mills +1
We motivate and describe a new freely available human-human dialogue dataset for interactive learning of visually grounded word meanings through ostensive definition by a tutor to…
cs.CL2017★ 7 cited
Training an adaptive dialogue policy for interactive learning of visually grounded word meanings
Yanchao Yu, Arash Eshghi, Oliver Lemon
We present a multi-modal dialogue system for interactive learning of perceptually grounded word meanings from a human tutor. The system integrates an incremental, semantic parsing/…
cs.CL2017★ 3 cited
Learning how to learn: an adaptive dialogue agent for incrementally learning visually grounded word meanings
Yanchao Yu, Arash Eshghi, Oliver Lemon
We present an optimised multi-modal dialogue agent for interactive learning of visually grounded word meanings from a human tutor, trained on real human-human tutoring data. Within…