9,878 Hits in 4.6 sec

Towards Closed Feedback Loops in HRI

Birte Carlmeyer, David Schlangen, Britta Wrede
2014 Proceedings of the 2014 Workshop on Multimodal, Multi-Party, Real-World Human-Robot Interaction - MMRWHRI '14  
In this paper, we present a first step towards incremental processing for modeling asynchronous human-robot interactions, to allow closed feedback loops in HRI.  ...  We achieve this by combining the incremental natural language processing framework InproTK with the human-robot dialog manager PaMini, which is based on generic interaction patterns.  ...  If the robot dialog act contains a verbalization output, a say task is sent via RSB and further processed by the incremental speech synthesis module (iSS) of InproTK.  ... 
doi:10.1145/2666499.2666500 dblp:conf/icmi/CarlmeyerSW14 fatcat:6ed3qje5fjeibcydvawleu4frq

Learning the Structure of Task-Driven Human–Human Dialogs

Srinivas Bangalore, Giuseppe Di Fabbrizio, Amanda Stent
2008 IEEE Transactions on Audio, Speech, and Language Processing  
In this paper, we use datadriven techniques to build task structures for individual dialogs, and use the dialog task structures for: dialog act classification, task/ subtask classification, task/subtask  ...  With the availability of large corpora of spoken dialog, it is now possible to use data-driven techniques to build and use models of task-oriented dialogs.  ...  Hollister and her team for their effort in annotating the dialogs for dialog acts and subtask structure and P. Haffner for providing them with the LLAMA  ... 
doi:10.1109/tasl.2008.2001102 fatcat:ig6pxvostbgtrmmvqc73z3hvmm

Learning the structure of task-driven human-human dialogs

Srinivas Bangalore, Giuseppe Di Fabbrizio, Amanda Stent
2006 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06  
In this paper, we use datadriven techniques to build task structures for individual dialogs, and use the dialog task structures for: dialog act classification, task/ subtask classification, task/subtask  ...  With the availability of large corpora of spoken dialog, it is now possible to use data-driven techniques to build and use models of task-oriented dialogs.  ...  Hollister and her team for their effort in annotating the dialogs for dialog acts and subtask structure and P. Haffner for providing them with the LLAMA  ... 
doi:10.3115/1220175.1220201 dblp:conf/acl/BangaloreFS06 fatcat:5sy53n6r5ffetggkfrwnfhywnm

Towards Learning Through Open-Domain Dialog [article]

Eugénio Ribeiro, Ricardo Ribeiro, David Martins de Matos
2022 arXiv   pre-print
The development of artificial agents able to learn through dialog without domain restrictions has the potential to allow machines to learn how to perform tasks in a similar manner to humans and change  ...  In this paper, we identify the modifications required for a dialog system to be able to learn from the dialog and propose generic approaches that can be used to implement those modifications.  ...  Acknowledgments Eugénio Ribeiro is supported by a PhD scholarship granted by Fundac ¸ão para a Ciência e a Tecnologia (FCT), with reference SFRH/BD/148142/2019.  ... 
arXiv:2202.03040v1 fatcat:723ekej7hfgzrbasdwvjyoifbu

Utility-Based Generation of Referring Expressions

Markus Guhe
2012 Topics in Cognitive Science  
This paper presents two cognitive models that simulate the production of referring expressions in the iMAP task-a task-oriented dialog.  ...  However, its explanatory power is limited, because it generates uniquely distinguishing referring expressions and because it considers features for inclusion in the referring expression in a fixed order  ...  Thanks to Mark Steedman and in particular to Ellen Gurman Bard for comments on earlier drafts; to Dan Bothell for providing help with the ACT-R system; and to Roger van Gompel, David Reitter, and two anonymous  ... 
doi:10.1111/j.1756-8765.2012.01185.x pmid:22496108 fatcat:wsbgetzpmjep3akqqoit6d4knm

Revisiting Human-Agent Communication: The Importance of Joint Co-construction and Understanding Mental States

Stefan Kopp, Nicole Krämer
2021 Frontiers in Psychology  
Yet, despite frequently made claims of "super-human performance" in, e.g., speech recognition or image processing, so far, no system is able to lead a half-decent coherent conversation with a human.  ...  equipped with: incremental joint co-construction and mentalizing.  ...  Hough and Schlangen (2016) present an extended version that models grounding and interactive repair in a task-oriented humanrobot dialog, by tracking the dialog state in two interacting state-machines  ... 
doi:10.3389/fpsyg.2021.580955 pmid:33833705 pmcid:PMC8021865 fatcat:nplpx3vt6rfhvgqgnx2ujr7rva

An Incremental Turn-Taking Model for Task-Oriented Dialog Systems

Andrei C. Coman, Koichiro Yoshino, Yukitoshi Murase, Satoshi Nakamura, Giuseppe Riccardi
2019 Interspeech 2019  
In this paper, we propose a token-by-token prediction of the dialog state from incremental transcriptions of the user utterance.  ...  To identify the point of maximal understanding in an ongoing utterance, we a) implement an incremental Dialog State Tracker which is updated on a token basis (iDST) b) re-label the Dialog State Tracking  ...  A turn-by-turn dialog state tracker estimates the dialog state p(st) only after processing all the tokens in the user's utterance.  ... 
doi:10.21437/interspeech.2019-1826 dblp:conf/interspeech/ComanYM0R19 fatcat:v4wu7zxj35hgxhjqusuavuxmte

Data fusion methods in multimodal human computer dialog

Ming-Hao YANG, Jian-Hua TAO
2019 Virtual Reality & Intelligent Hardware  
This paper presents a review of data fusion methods in multimodal human computer dialog.  ...  We first introduce the cognitive assumption of single channel processing, and then discuss its implementation methods in human computer dialog; for the task of multi-modal information fusion, serval computing  ...  A type of conversational humanoid robot, which can engage in both task-oriented dialogues and non-task-oriented dialog for accurately understanding human requests or non-task-oriented dialogues to allow  ... 
doi:10.3724/sp.j.2096-5796.2018.0010 dblp:journals/vrih/YangT19 fatcat:jltufn3o6fd4pjzv4pnqd6wmvy

Effects of Naturalistic Variation in Goal-Oriented Dialog [article]

Jatin Ganhotra, Robert Moore, Sachindra Joshi, Kahini Wadhawan
2020 arXiv   pre-print
In this work, we investigate the impact of naturalistic variation on two goal-oriented datasets: bAbI dialog task and Stanford Multi-Domain Dataset (SMD).  ...  F1 on SMD and 85% in per-dialog accuracy on bAbI task) of recent state-of-the-art end-to-end neural methods such as BossNet and GLMP on both datasets.  ...  , and • Publicly release improved testbeds for two datasets used extensively in goal-oriented dialog research: bAbI dialog task and SMD.  ... 
arXiv:2010.02260v1 fatcat:qsharrsbbnczlcj2wvwyptecbe

Robust Conversational AI with Grounded Text Generation [article]

Jianfeng Gao, Baolin Peng, Chunyuan Li, Jinchao Li, Shahin Shayandeh, Lars Liden, Heung-Yeung Shum
2020 arXiv   pre-print
responses grounded in dialog belief state and real-world knowledge for task completion.  ...  The primary results reported on task-oriented dialog benchmarks are very promising, demonstrating the big potential of this approach.  ...  GTG for task-oriented dialog Consider a multi-turn task-oriented dialog, as illustrated in Figure 9 . At each turn, GTG generates a natural language response r in the following steps.  ... 
arXiv:2009.03457v1 fatcat:2462mlxn7fg3zgw5mwknoqngaa

Incremental partition recombination for efficient tracking of multiple dialog states

Jason D. Williams
2010 2010 IEEE International Conference on Acoustics, Speech and Signal Processing  
To retain tractability, past work has suggested tracking dialog states in groups called partitions.  ...  For spoken dialog systems, tracking a distribution over multiple dialog states has been shown to add robustness to speech recognition errors.  ...  In practice there are too many dialog states to process in real time, so researchers have suggested maintaining a distribution over partitions of dialog states [3, 4] .  ... 
doi:10.1109/icassp.2010.5494939 dblp:conf/icassp/Williams10a fatcat:5sifovxag5bnhnsrz5f2pl4auy

Building Task-Oriented Visual Dialog Systems Through Alternative Optimization Between Dialog Policy and Language Generation [article]

Mingyang Zhou, Josh Arnold, Zhou Yu
2019 arXiv   pre-print
Reinforcement learning (RL) is an effective approach to learn an optimal dialog policy for task-oriented visual dialog systems.  ...  We evaluate our framework on the GuessWhich task and the framework achieves the state-of-the-art performance in both task completion and dialog quality.  ...  Acknowledgments This work was supported in part by Cisco.  ... 
arXiv:1909.05365v2 fatcat:avidxwp3nfavjmlkrwizo6lxva

Incremental Coordination: Attention-Centric Speech Production in a Physically Situated Conversational Agent

Zhou Yu, Dan Bohus, Eric Horvitz
2015 Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue  
We present an implementation and deployment of the model in a physically situated dialog system and discuss lessons learned.  ...  We introduce a model that considers the demands and availability of listeners' attention at the onset and throughout the production of system utterances, and that incrementally coordinates speech synthesis  ...  Most previous work on incremental processing in dialog has focused on the acoustic channel, including efforts on recognizing, generating, and synthesizing language incrementally.  ... 
doi:10.18653/v1/w15-4652 dblp:conf/sigdial/YuBH15 fatcat:eez74ipf2neuzfgwzm5xavmwbe

Description of Experiments [chapter]

1974 Monkeys As Perceivers  
The emphasis of the analysis presented in this paper addresses (1) the structure of dialog in relation to the process of assembly, which we found exemplified a relationship between dialog and task, (2  ...  Incremental focusing works to establish a group of one. Incremental focusing strategies are usually in the form of utterances which exhibit a top-down approach.  ... 
doi:10.1016/b978-0-12-534003-8.50017-7 fatcat:szsz3urvefegvjdg7nbakarbiq

Report from the NSF Future Directions Workshop, Toward User-Oriented Agents: Research Directions and Challenges [article]

Maxine Eskenazi, Tiancheng Zhao
2020 arXiv   pre-print
In the breakout sessions that followed, the participants defined the main research areas within the domain of intelligent agents and they discussed the major future directions that the research in each  ...  It took place in Pittsburgh Pennsylvania on October 24 and 25, 2019 and was sponsored by National Science Foundation Grant Number IIS-1934222.  ...  The evaluation of traditional task-oriented dialog systems has focused on objective measures of the quality of system components, task success, and user satisfaction as measured in post-use questionnaires  ... 
arXiv:2006.06026v1 fatcat:h2hbe4cr6vajvca4oqkfrmf5oa
« Previous Showing results 1 — 15 out of 9,878 results