A system for interactive learning in dialogue with a tutor

Skočaj, Danijel; Kristan, Matej; Vrečko, Alen; Mahnič, Marko; Janíček, Miroslav; Kruijff, Geert-Jan M.; Hanheide, Marc; Hawes, Nick; Keller, Thomas; Zillich, Michael; Zhou, Kai

doi:10.1109/iros.2011.6094926

Cited by 20 publications

(12 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These models either use toy languages as input (e.g., Siskind, 1996), or childdirected utterances from the CHILDES database (MacWhinney, 2014) paired with artificially generated semantic information. Some models have investigated the acquisition of terminology for visual concepts from simple videos (Fleischman and Roy, 2005;Skocaj et al, 2011). Lazaridou et al (2015) adapt the skip-gram word-embedding model (Mikolov et al, 2013) for learning word representations via a multi-task objective similar to ours, learning from a dataset where some words are individually aligned with corresponding images.…”

Section: Related Workmentioning

confidence: 99%

Learning language through pictures

Chrupała¹,

Kádár²,

Alishahi³

2015

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Confere

View full text Add to dashboard Cite

We propose IMAGINET, a model of learning visually grounded representations of language from coupled textual and visual input. The model consists of two Gated Recurrent Unit networks with shared word embeddings, and uses a multi-task objective by receiving a textual description of a scene and trying to concurrently predict its visual representation and the next word in the sentence. Mimicking an important aspect of human language learning, it acquires meaning representations for individual words from descriptions of visual scenes. Moreover, it learns to effectively use sequential structure in semantic interpretation of multi-word phrases.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning language through pictures

Chrupała¹,

Kádár²,

Alishahi³

2015

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Confere

View full text Add to dashboard Cite

show abstract

“…The Semantic Map generation can follow different approaches: by relying on hand-crafted ontologies and using traditional AI reasoning techniques [35,36], by exploiting the purely automatic interpretation of perceptual outcomes [37,38,39], or by relying on interactions in a human-robot collaboration setting [40,41]. • is-contain-able(C, t) denotes that the Contain-ability property holds for all the objects of the class C, e.g., is-contain-able(Cup, t);…”

Section: Semantic Mapmentioning

confidence: 99%

Grounded language interpretation of robotic commands through structured learning

Vanzo

Croce

Bastianelli

et al. 2020

Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…A dialogue initiated by the robot is very similar to any other planned knowledge-acquiring action and hence is modelled similarly. The dialogue model is based on the work of Skočaj et al [46], Janíček [21] and will only briefly be outlined in the following. There are two types of dialogue actions: engagement, and questions triggered by the deliberative layer.…”

Section: Dialoguementioning

confidence: 99%

Robot task planning and explanation in open and uncertain worlds

Hanheide¹,

Gbelbecker²,

Horn³

et al. 2017

Artificial Intelligence

Self Cite

130

View full text Add to dashboard Cite

A long-standing goal of AI is to enable robots to plan in the face of uncertain and incomplete information, and to handle task failure intelligently. This paper shows how to achieve this. There are two central ideas. The first idea is to organize the robot's knowledge into three layers: instance knowledge at the bottom, commonsense knowledge above that, and diagnostic knowledge on top. Knowledge in a layer above can be used to modify knowledge in the layer(s) below. The second idea is that the robot should represent not just how its actions change the world, but also what it knows or believes. There are two types of knowledge effects the robot's actions can have: epistemic effects (I believe X because I saw it) and assumptions (I'll assume X to be true). By combining the knowledge layers with the models of knowledge effects, we can simultaneously solve several problems in robotics: (i) task planning and execution under uncertainty; (ii) task planning and execution in open worlds; (iii) explaining task failure; (iv) verifying those explanations. The paper describes how the ideas are implemented in a three-layer architecture on a mobile robot platform. The robot implementation was evaluated in five different experiments on object search, mapping, and room categorization.

show abstract

A system for interactive learning in dialogue with a tutor

Cited by 20 publications

References 22 publications

Learning language through pictures

Learning language through pictures

Grounded language interpretation of robotic commands through structured learning

Robot task planning and explanation in open and uncertain worlds

Contact Info

Product

Resources

About