A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
RMM: A Recursive Mental Model for Dialog Navigation
[article]
2020
arXiv
pre-print
Preserved Fulltext
Other Versions
Inspired by theory of mind, we propose the Recursive Mental Model (RMM). The navigating agent models the guiding agent to simulate answers given candidate generated questions. ...
We demonstrate that RMM enables better generalization to novel environments. Interlocutor modelling may be a way forward for human-agent dialogue where robots need to both ask and answer questions. ...
Acknowledgements We thank the anonymous reviewers and the AC for the questions they raised and their helpful commentary, which strengthened the presentation of our task and models. ...
arXiv:2005.00728v2
fatcat:5aczk2ips5alnjrsinprkd53wm
VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
(arXiv:2005.00728) for enabling the use of such models in different environments. ...
In this paper, we present VISITRON, a multi-modal Transformer-based navigator better suited to the interactive regime inherent to Cooperative Vision-and-Dialog Navigation (CVDN). ...
We would also like to thank the anonymous reviewers for their service and useful feedback. ...
arXiv:2105.11589v2
fatcat:7o7dxrlbl5bt7focxxackp6kyy
Improving Dialog Systems for Negotiation with Personality Modeling
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2010.09954v1 fatcat:eip45tepurhc7dv6qpln6izymu
In this paper, we explore the ability to model and infer personality types of opponents, predict their responses, and use this information to adapt a dialog agent's high-level strategy in negotiation tasks ...
We test our approach on the CraigslistBargain dataset and show that our method using ToM inference achieves a 20% higher dialog agreement rate compared to baselines on a mixed population of opponents. ...
Acknowledgements We thank Robert Hawkins, Jens Tuyls, Vishvak Murahari, and Howard Chen for helpful discussions and feedback. This research was supported by an Amazon Research Award. ...
arXiv:2010.09954v2
fatcat:ck7qqw5lerdnblpphqthysizc4
Improving Dialog Systems for Negotiation with Personality Modeling
2021
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
unpublished
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In this paper, we explore the ability to model and infer personality types of opponents, predict their responses, and use this information to adapt a dialog agent's high-level strategy in negotiation tasks ...
We test our approach on the CRAIGSLISTBAR-GAIN dataset (He et al., 2018) and show that our method using ToM inference achieves a 20% higher dialog agreement rate compared to baselines on a mixed population ...
Acknowledgements We thank Robert Hawkins, Jens Tuyls, Vishvak Murahari, Howard Chen and members of the Princeton NLP group for helpful discussions and feedback. ...
doi:10.18653/v1/2021.acl-long.56
fatcat:yrehfvxxjnb3vle3bdeiwypj64
Holistic recommender systems for software engineering
2014
Companion Proceedings of the 36th International Conference on Software Engineering - ICSE Companion 2014
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
For example, to help developers in the first phase, queries can be automatically generated [HBM + 13] so that development artifacts can be retrieved according to a specific code entity, and notified to ...
Any improvement in the search process would result in time saved for the developers. ...
They suggest how "ad-hoc heuristics can be used to better approximate the mental model used by developers when identifying class keywords". ...
doi:10.1145/2591062.2591081
dblp:conf/icse/Ponzanelli14
fatcat:jsvbb3jz4fbx3opvqntxrwlune
The internet in everyday life: Computer networking from the standpoint of the domestic user
2001
New Media & Society
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Users wished to be involved in a dialogical exchange. ...
model. ...
Appendix A
Respondent Recruitment Section 1: Cal1 for Participation in the Siudy
Cal1 for Participation in a Rese! ...
doi:10.1177/14614440122225994
fatcat:7okeavmjxbbwpkvvnnl5qmhlka
SMART 2012 Committee SMART 2012 Technical Program Committee
unpublished
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
We are grateful to the members of the SMART 2012 organizing committee for their help in handling the logistics and for their work to make this professional meeting a success. ...
We hope that SMART 2012 was a successful international forum for the exchange of ideas and results between academia and industry and for the promotion of progress in smart environment technologies. ...
We would like to thank Department of Electronics and Information Technology for providing us an opportunity to develop this smart artifact. ...
fatcat:5qkq3lfzhbefpaq6rq35ucakl4