18,371 Hits in 3.4 sec

Dialogue State Tracking with Incremental Reasoning

Lizi Liao, Le Hong Long, Yunshan Ma, Wenqiang Lei, Tat-Seng Chua
2021 Transactions of the Association for Computational Linguistics  
This paper proposes to track dialogue states gradually with reasoning over dialogue turns with the help of the back-end data.  ...  Tracking dialogue states to better interpret user goals and feed downstream policy learning is a bottleneck in dialogue management.  ...  Incremental Reasoning The ability to do reasoning over the dialogue history is essential for dialogue state trackers.  ... 
doi:10.1162/tacl_a_00384 fatcat:6quh2aapgnfvtnh3efhopddpde

Rethinking Dialogue State Tracking with Reasoning [article]

Lizi Liao, Yunshan Ma, Wenqiang Lei, Tat-Seng Chua
2020 arXiv   pre-print
This paper proposes to track dialogue states gradually with reasoning over dialogue turns with the help of the back-end data.  ...  Tracking dialogue states to better interpret user goals and feed downstream policy learning is a bottleneck in dialogue management.  ...  Incremental Reasoning The ability to do reasoning over the dialogue history is essential for dialogue state tracker to find user intention.  ... 
arXiv:2005.13129v2 fatcat:6zemr7ileve4haojiciag4z2vm

Bootstrapping incremental dialogue systems: using linguistic knowledge to learn from minimal data [article]

Dimitrios Kalatzis, Arash Eshghi, Oliver Lemon
2016 arXiv   pre-print
We present a method for inducing new dialogue systems from very small amounts of unannotated dialogue data, showing how word-level exploration using Reinforcement Learning (RL), combined with an incremental  ...  The method avoids the use of expensive and time-consuming dialogue act annotations, and supports more natural (incremental) dialogues than turn-based systems.  ...  We employ a Dynamic Syntax (DS) parser [8] for incremental language understanding and tracking of the dialogue state using Eshghi et al.'  ... 
arXiv:1612.00347v1 fatcat:er4dxk2c2nda3kfziynzssq7om

SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues [article]

Liang Qiu, Yuan Liang, Yizhou Zhao, Pan Lu, Baolin Peng, Zhou Yu, Ying Nian Wu, Song-Chun Zhu
2021 arXiv   pre-print
Empirical results on DialogRE and MovieGraph show that our model infers social relations more accurately than the state-of-the-art methods.  ...  Inferring social relations from dialogues is vital for building emotionally intelligent robots to interpret human language better and act accordingly.  ...  Such dynamic inference can potentially help reflect the evolving relations, unveil the reasoning process, and deal with long dialogues.  ... 
arXiv:2106.01006v2 fatcat:ymobbdwxyffbviyrab2u4k276e

Investigating Fluidity for Human-Robot Interaction with Real-time, Real-world Grounding Strategies

Julian Hough, David Schlangen
2016 Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue  
The framework consists of a combination of interactive Harel statecharts and the Incremental Unit framework.  ...  We experiment with a trade-off between the fluidity of the grounding mechanism with the 'safety' of ensuring task success.  ...  The statechart is then checked to see if a transition is possible from the user's current state as each word is processed, akin to incremental dialogue state tracking (Williams, 2012) .  ... 
doi:10.18653/v1/w16-3637 dblp:conf/sigdial/HoughS16 fatcat:ox4veyqk45cpfoql3u5blyk4d4

Page 534 of SMPTE Motion Imaging Journal Vol. 110, Issue 8 [page]

2001 SMPTE Motion Imaging Journal  
long periods of near silence on dedicated dialogue tracks.  ...  Where dialogue tracks are isolated, loudness metering is a fairly easy process, and in Cinema usage (where signal levels can be related directly to the reproduced sound pressure levels),+ metering with  ... 

Multi-tasking and collaborative activities in dialogue systems

Oliver Lemon, Alexander Gruenstein, Alexis Battle, Stanley Peters
2002 Proceedings of the 3rd SIGdial workshop on Discourse and dialogue -  
We explain dialogue management techniques for collaborative activities with humans, involving multiple concurrent tasks.  ...  We also describe the incremental message selection, aggregation, and generation method employed in the system.  ...  For these reasons we built a dialogue manager that represents (possibly collaborative) activities and their execution status, and tracks multiple threads of dialogue about concurrent and planned activities  ... 
doi:10.3115/1118121.1118137 dblp:conf/sigdial/LemonGBP02 fatcat:7fivkqnvnjfe5ec5sfvdsn37by

Response to the discussion points by Lina Varonina and Stefan Kopp

Lina Varonina, Stefan Kopp
2021 Italian Journal of Computational Linguistics  
Dialogue state tracking with incremental reasoning. Transactions of the Association for Computational Linguistics, 9:557–569.  ...  Schema-guided multi-domain dialogue state tracking with graph attention neural networks.  ... 
doi:10.4000/ijcol.815 fatcat:ptduewem6fgo7pu32ghl5qvu44

An Evidential Model for Tracking Initiative in Collaborative Dialogue Interactions [chapter]

Jennifer Chu-Carroll, Michael K. Brown
1998 Computational Models of Mixed-Initiative Interaction  
In this paper, we argue for the need to distinguish between task initiative and dialogue initiative, and present an evidential model for tracking shifts in both types of initiatives in collaborative dialogue  ...  Finally, we show how this initiative tracking model may be employed by a dialogue system to enable the system to tailor its responses to user utterances based on application domain, system's role in the  ...  Furthermore, substantial improvement is gained by the use of counters in constant-increment-with-counter and variable-increment-with-counter.  ... 
doi:10.1007/978-94-017-1118-0_2 fatcat:c35nt4jsfngylpgmbz7kh2mj5y

Challenging Neural Dialogue Models with Natural Data: Memory Networks Fail on Incremental Phenomena [article]

Igor Shalyminov, Arash Eshghi, Oliver Lemon
2017 arXiv   pre-print
We then explore the performance of a state-of-the-art retrieval model, MemN2N, on this more natural dataset.  ...  Natural, spontaneous dialogue proceeds incrementally on a word-by-word basis; and it contains many sorts of disfluency such as mid-utterance/sentence hesitations, interruptions, and self-corrections.  ...  Task 6, in turn, is based on real dialogues collected for the Dialog State Tracking Challenge 2.  ... 
arXiv:1709.07840v1 fatcat:eg7hkfcq7fbpvievjhxsquqj44

Aesop: A Visual Storytelling Platform for Conversational AI

Tim Meo, Aswin Raghavan, David A. Salter, Alex Tozzo, Amir Tamrakar, Mohamed Amer
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
Aesop consists of a language parser, human gesture monitoring, composition graphs, dialogue state manager, and an interactive 3D animation software.  ...  Aesop thus enables 3D spatial and temporal reasoning which are both essential for storytelling.  ...  Aesop will help address open research problems such as: conversational AI; joint language and gesture reasoning; planning and dialogue management; and narrative.  ... 
doi:10.24963/ijcai.2018/857 dblp:conf/ijcai/MeoRSTTA18 fatcat:3syf2coxzbfn3axc6w5i27q3gu

Coffee With a Hint of Data: Towards Using Data-Driven Approaches in Personalised Long-Term Interactions

Bahar Irfan, Mehdi Hellou, Tony Belpaeme
2021 Frontiers in Robotics and AI  
Based on these datasets, we explore the performance and the underlying inaccuracies of the state-of-the-art data-driven dialogue models that are strong baselines in other domains of personalisation in  ...  However, data-driven approaches are generally applied to single dialogue exchanges with a user and do not build up a memory over long-term conversation with different users, whereas long-term interactions  ...  ACKNOWLEDGMENTS The authors would like to thank Ghent University IDLab (Belgium) for access to the servers for the experiments, and Cité Internationale Universitaire de Paris (France) for hosting the user study with  ... 
doi:10.3389/frobt.2021.676814 pmid:34651017 pmcid:PMC8505524 fatcat:wxtxjfcuzvctdkrhyay2nemnyu

Challenges in Building Highly-Interactive Dialog Systems

Nigel G. Ward, David DeVault
2017 The AI Magazine  
, and conclusions or recommendations expressed in this material are those of the authors and do not necessarily reflect the views, position, or policy of the National Science Foundation or the United States  ...  Another reason is that dialogue systems are increasingly situated.  ...  Thus success in dialogue can require continuous tracking of the current state, regardless of who "has the floor."  ... 
doi:10.1609/aimag.v37i4.2687 fatcat:rfnl5u5lfnhqlpqmv74ekc5kgy

Domain Transfer in Dialogue Systems without Turn-Level Supervision [article]

Joachim Bingel, Victor Petrén Bach Hansen, Ana Valeria Gonzalez, Paweł Budzianowski, Isabelle Augenstein, Anders Søgaard
2019 arXiv   pre-print
Task oriented dialogue systems rely heavily on specialized dialogue state tracking (DST) modules for dynamically predicting user intent throughout the conversation.  ...  Across several domains, our experiments show that this method quickly adapts off-the-shelf models to new domains and performs on par with models trained with turn-level supervision.  ...  In developing goal-oriented dialogue systems, dialogue state tracking (DST) refers to the subtask of incrementally inferring a user's intent as expressed over a sequence of turns.  ... 
arXiv:1909.07101v1 fatcat:logglgkwfrd7hazddpbrs26lhm

DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue [article]

Hung Le and Chinnadhurai Sankar and Seungwhan Moon and Ahmad Beirami and Alborz Geramifard and Satwik Kottur
2021 arXiv   pre-print
Dialogues are synthesized over multiple question turns, each of which is injected with a set of cross-turn semantic relationships.  ...  Building such dialogue systems is a challenging problem, involving various reasoning types on both visual and language inputs.  ...  Neu- ral belief tracker: Data-driven dialogue state track- ing.  ... 
arXiv:2101.00151v2 fatcat:j4pv54mx3bhd7eyfs5eyzyoyju
« Previous Showing results 1 — 15 out of 18,371 results