'What are you referring to?'Evaluating the Ability of Multi-Modal Dialogue Models to Process Clarificational Exchanges
Referential ambiguities arise in dialogue when a referring expression does not uniquely
identify the intended referent for the addressee. Addressees usually detect such ambiguities …
identify the intended referent for the addressee. Addressees usually detect such ambiguities …
Exploring the naturalness of cognitive status-informed referring form selection models
G Del Castillo, G Clark, Z Han… - Proceedings of the 16th …, 2023 - aclanthology.org
Abstract Language-capable robots must be able to efficiently and naturally communicate
about objects in the environment. A key part of communication is Referring Form Selection …
about objects in the environment. A key part of communication is Referring Form Selection …
Evaluating cognitive status-informed referring form selection for human-robot interactions
Z Han, T Williams - Proceedings of the Annual Meeting of the …, 2023 - escholarship.org
Robots must be able to communicate naturally and efficiently, eg, using concise referring
forms like it, that, and the⟨ N'⟩. Recently researchers have started working on Referring …
forms like it, that, and the⟨ N'⟩. Recently researchers have started working on Referring …
Repairs in a Block World: A New Benchmark for Handling User Corrections with Multi-Modal Language Models
In dialogue, the addressee may initially misunderstand the speaker and respond
erroneously, often prompting the speaker to correct the misunderstanding in the next turn …
erroneously, often prompting the speaker to correct the misunderstanding in the next turn …
'What are you referring to?'Evaluating the ability of multi-modal dialogue models to process clarificational exchanges
Referential ambiguities arise in dialogue when a referring expression does not uniquely
identify the intended referent for the addressee. Addressees usually detect such ambiguities …
identify the intended referent for the addressee. Addressees usually detect such ambiguities …
A system for robot concept learning through situated dialogue
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 …
unknown concepts on the fly. To this end, we demonstrate a novel system that combines a …
不完全な物体検出結果に基づく対話を通じた目的地推定のための質問選択
時末卓幹， 武田龍， 駒谷和範， 翠輝久… - 第84 回全国大会講演 …, 2022 - ipsj.ixsq.nii.ac.jp
論文抄録 街中の画像情報とユーザの指示発話を入力とし, ユーザが意図する画像中の目的地を
推定するシステムの実現を目指す. 実環境中での画像認識結果は完全ではなく …
推定するシステムの実現を目指す. 実環境中での画像認識結果は完全ではなく …
物体検出器により得た確信度が対話システム性能に与える影響
谷口琉聖， 武田龍， 駒谷和範， 翠輝久… - … 会資料言語・音声理解と …, 2022 - jstage.jst.go.jp
抄録 物体検出の結果を用いることで, ユーザが意図する画像中の目的地点を推定する対話
システムを構築している. しかし, 確信度が低い検出物体を用いると誤解が生じる可能性がある …
システムを構築している. しかし, 確信度が低い検出物体を用いると誤解が生じる可能性がある …