paper-with-me

Papers

Decision-Theoretic Question Generation for Situated Reference Resolution: An Empirical Study and Computational Model

2021-10-12 · Felix Gervits, Gordon Briggs, Antonio Roque, Genki A. Kadomatsu, Dean Thurston, Matthias Scheutz, Matthew Marge

Dialogue agents that interact with humans in situated environments need to manage referential ambiguity across multiple modalities and ask for help as needed. However, it is not clear what kinds of questions such agents should ask nor how the answers to such questions can be used to resolve ambiguity. To address this, we analyzed dialogue data from an interactive study in which participants controlled a virtual robot tasked with organizing a set of tools while engaging in dialogue with a live, remote experimenter. We discovered a number of novel results, including the distribution of question types used to resolve ambiguity and the influence of dialogue-level factors on the reference resolution process. Based on these empirical findings we: (1) developed a computational model for clarification requests using a decision network with an entropy-based utility assignment method that operates across modalities, (2) evaluated the model, showing that it outperforms a slot-filling baseline in environments of varying ambiguity, and (3) interpreted the results to offer insight into the ways that agents can ask questions to facilitate situated reference resolution.

📄 PDF Abstract BibTeX arXiv:2110.06288

Code (0)

등록된 구현이 없습니다.

Tasks

Question GenerationQuestion-Generationslot-fillingSlot Filling

Similar Papers 제목 키워드 기반

Situated Natural Language Explanations

2023-08-27 · Zining Zhu, Haoming Jiang, Jingfeng Yang, Sreyashi Nag 외

Natural language is among the most accessible tools for explaining decisions to humans, and large pretrained language models (PLMs) have demonstrated impressive abilities to generate coherent natural language explanation…

Prompt Engineering

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

Annotating anaphoric phenomena in situated dialogue

2021-06-01 · ACL (mmsr, IWCS) 2021 6 · Sharid Loáiciga, Simon Dobnik, David Schlangen

In recent years several corpora have been developed for vision and language tasks. With this paper, we intend to start a discussion on the annotation of referential phenomena in situated dialogue. We argue that there is …

coreference-resolutionCoreference Resolution

SOK-Bench: A Situated Video Reasoning Benchmark with Aligned Open-World Knowledge

2024-05-15 · CVPR 2024 1 · Andong Wang, Bo Wu, Sunli Chen, Zhenfang Chen 외

Learning commonsense reasoning from visual contexts and scenes in real-world is a crucial step toward advanced artificial intelligence. However, existing video reasoning benchmarks are still inadequate since they were ma…

General KnowledgeKnowledge GraphsWorld Knowledge

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