paper-with-me

Papers

A Situated Dialogue System for Learning Structural Concepts in Blocks World

2018-07-01 · WS 2018 7 · Ian Perera, James Allen, Choh Man Teng, Lucian Galescu

We present a modular, end-to-end dialogue system for a situated agent to address a multimodal, natural language dialogue task in which the agent learns complex representations of block structure classes through assertions, demonstrations, and questioning. The concept to learn is provided to the user through a set of positive and negative visual examples, from which the user determines the underlying constraints to be provided to the system in natural language. The system in turn asks questions about demonstrated examples and simulates new examples to check its knowledge and verify the user{'}s description is complete. We find that this task is non-trivial for users and generates natural language that is varied yet understood by our deep language understanding architecture.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Transfer Learning

Similar Papers 제목 키워드 기반

Back to the Blocks World: Learning New Actions through Situated Human-Robot Dialogue

2014-06-01 · WS 2014 6 · Lanbo She, Shaohua Yang, Yu Cheng, Yunyi Jia 외

A System For Robot Concept Learning Through Situated Dialogue

2022-09-01 · SIGDIAL (ACL) 2022 9 · Benjamin Kane, Felix Gervits, Matthias Scheutz, Matthew Marge

Robots operating in unexplored environments with human teammates will need to learn unknown concepts on the fly. To this end, we demonstrate a novel system that combines a computational model of question generation with …

One-Shot LearningQuestion GenerationQuestion-Generation

Building and Learning Structures in a Situated Blocks World Through Deep Language Understanding

2018-06-01 · WS 2018 6 · Ian Perera, James Allen, Choh Man Teng, Lucian Galescu

We demonstrate a system for understanding natural language utterances for structure description and placement in a situated blocks world context. By relying on a rich, domain-specific adaptation of a generic ontology and…

How Should Agents Ask Questions For Situated Learning? An Annotated Dialogue Corpus

2021-06-11 · SIGDIAL (ACL) 2021 7 · Felix Gervits, Antonio Roque, Gordon Briggs, Matthias Scheutz 외

Intelligent agents that are confronted with novel concepts in situated environments will need to ask their human teammates questions to learn about the physical world. To better understand this problem, we need data abou…

Novel ConceptsQuestion GenerationQuestion-Generation

Towards Collaborative Plan Acquisition through Theory of Mind Modeling in Situated Dialogue

2023-05-18 · Cristian-Paul Bara, Ziqiao Ma, Yingzhuo Yu, Julie Shah 외

Collaborative tasks often begin with partial task knowledge and incomplete initial plans from each partner. To complete these tasks, agents need to engage in situated communication with their partners and coordinate thei…

Collaborative Plan AcquisitionTheory of Mind Modeling