What's to Know? Uncertainty as a Guide to Asking Goal-Oriented Questions
Open accessAbstract
One of the core challenges in Visual Dialogue problems is asking the question that will provide the most useful information towards achieving the required objective. Encouraging an agent to ask the right questions is difficult because we don't know a-priori what information the agent will need to achieve its task, and we don't have an explicit model of what it knows already. We propose a solution to this problem based on a Bayesian model of the uncertainty in the implicit model maintained by the visual dialogue agent, and in the function used to select an appropriate output. By selecting the question that minimises the predicted regret with respect to this implicit model the agent actively reduces ambiguity. The Bayesian model of uncertainty also enables a principled method for identifying when enough information has been acquired, and an action should be selected. We evaluate our approach on two goal-oriented dialogue datasets, one for visual-based collaboration task and the other for a negotiation-based task. Our uncertainty-aware information-seeking model outperforms its counterparts in these two challenging problems.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In 2020, Harris et al. [644] used MixUp, FMix, FastText-300d, CNN, FastText, bidirectional LSTM, and BERT with a relative entropy objective for image, audio, text, and point cloud classification on CIFAR-10, Fashion MNIST, and ImageNet.
“Harris al. [644] | et | 2020 | CIFAR-10, Fashion MNIST, ImageNet | Image, audio, text and point cloud clas- sification (mixed sample data augmenta- tion) | N/A | N/A | MixUp, FMix, FastText- 300d, CNN, FastText, bi- directional LSTM, BERT | Relative entropy objective”
From A review of uncertainty quantification in deep learning: Techniques, applications and challenges (2021) · cites this paper as [644]
The Experiments and GuessWhat sections describe goal-oriented dialogue tasks and an RNN questioner, not mixed-sample augmentation or classification on CIFAR-10, Fashion MNIST, and ImageNet. Searches for MixUp, FMix, FastText-300d, and a relative-entropy classification objective found no passage supporting the attributed study; the paper's text also does not establish who conducted that study. (LLM, conf=0.78)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · see citing works
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225 · see citing works
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. (2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 25,263 · see citing works
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · see citing works
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213 · see citing works
Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
Williams, R. J. (1992) · Machine Learning · doi:10.1007/bf00992696 · Cited by 7,936 · see citing works
On the Properties of Neural Machine Translation: Encoder–Decoder Approaches
Cho, K., van Merriënboer, B., Bahdanau, D., & Bengio, Y. (2014) · SSST@EMNLP · doi:10.3115/v1/w14-4012 · Cited by 7,251 · see citing works
Dropout as a bayesian approximation: Representing model uncertainty in deep learning
Gal, Y., & Ghahramani, Z. (2015) · arXiv · doi:10.48550/arxiv.1506.02142 · Cited by 6,471 · see citing works
(1999) · Cited by 5,147 · see citing works
What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
Kendall, A., & Gal, Y. (2017) · arXiv · doi:10.48550/arxiv.1703.04977 · Cited by 3,088 · see citing works
Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models
Serban, I. V., Sordoni, A., Bengio, Y., Courville, A. C., & Pineau, J. (2016) · AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · doi:10.1609/aaai.v30i1.9883 · Cited by 1,639 · see citing works
Vinyals, O., & Le, Q. (2015) · arXiv · doi:10.48550/arxiv.1506.05869 · Cited by 1,400 · see citing works
Deep Reinforcement Learning for Dialogue Generation
Li, J., Monroe, W., Ritter, A., Jurafsky, D., Galley, M., & Gao, J. (2016) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d16-1127 · Cited by 1,221 · see citing works
A theoretically grounded application of dropout in recurrent neural networks
Gal, Y., & Zoubin Ghahramani, A. (2016) · Cambridge University Engineering Department Publications Database · Cited by 1,051 · see citing works
POMDP-Based Statistical Spoken Dialog Systems: A Review
Young, S. J., Gašić, M., Thomson, B., & Williams, J. D. (2013) · Proceedings of the IEEE · doi:10.1109/jproc.2012.2225812 · Cited by 898 · see citing works
Adversarial Learning for Neural Dialogue Generation
Li, J., Monroe, W., Shi, T., Jean, S., Ritter, A., & Jurafsky, D. (2017) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d17-1230 · Cited by 880 · see citing works
A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
Sordoni, A., Galley, M., Auli, M., Brockett, C., Ji, Y., Mitchell, M., Nie, J., Gao, J., & Dolan, B. (2015) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.3115/v1/n15-1020 · Cited by 768 · see citing works
(2008) · ScholarlyCommons (University of Pennsylvania) · Cited by 581 · see citing works
Data-Driven Response Generation in Social Media
Ritter, A., Cherry, C. A., & Dolan, W. B. (2011) · Cited by 566 · see citing works
Learning End-to-End Goal-Oriented DialogPreprint
Bordes, A., Boureau, Y.-L., & Weston, J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.07683 · Cited by 481 · see citing works
Das, A., Kottur, S., Gupta, K., Singh, A., Yadav, D., Moura, J. M. F., Parikh, D., & Batra, D. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.121 · Cited by 445 · see citing works
Deep Reinforcement Learning for Dialogue GenerationPreprint
Li, J., Monroe, W., Ritter, A., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.01541 · Cited by 405 · see citing works
GuessWhat?! Visual Object Discovery through Multi-modal Dialogue
de Vries, H., Strub, F., Chandar, S., Pietquin, O., Larochelle, H., & Courville, A. C. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.475 · Cited by 378 · see citing works
Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning
Das, A., Kottur, S., Moura, J. M. F., Lee, S., & Batra, D. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.321 · Cited by 362 · see citing works
Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System
Singh, S. P., Litman, D. J., Kearns, M. J., & Walker, M. A. (2002) · Journal of Artificial Intelligence Research · doi:10.1613/jair.859 · Cited by 352 · see citing works
Deal or No Deal? End-to-End Learning of Negotiation Dialogues
Lewis, M., Yarats, D., Dauphin, Y., Parikh, D., & Batra, D. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1259 · Cited by 347 · see citing works
A tutorial on variational Bayesian inference
Fox, C. W., & Roberts, S. (2011) · Artificial Intelligence Review · doi:10.1007/s10462-011-9236-8 · Cited by 329 · see citing works
Adversarial Learning for Neural Dialogue GenerationPreprint
Li, J., Monroe, W., Shi, T., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.06547 · Cited by 211 · see citing works
Wang, Z., & Lemon, O. (2013) · doi:10.13140/2.1.1213.1522 · Cited by 159 · see citing works
Continuously Learning Neural Dialogue ManagementPreprint
Su, P.-H., Gašić, M., Mrkšić, N., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.02689 · Cited by 104 · see citing works
End-to-end optimization of goal-driven and visually grounded dialogue systems
Strub, F., de Vries, H., Mary, J., et al. (2017) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/385 · Cited by 91 · see citing works
Sample-efficient batch reinforcement learning for dialogue management optimization
Pietquin, O., Geist, M., Chandramohan, S., & Frezza-Buet, H. (2011) · ACM Transactions on Speech and Language Processing · doi:10.1145/1966407.1966412 · Cited by 90 · see citing works
Learning Cooperative Visual Dialog Agents with Deep Reinforcement LearningPreprint
Das, A., Kottur, S., Moura, J. M. F., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.06585 · Cited by 88 · see citing works
A Neural Network Approach to Context-Sensitive Generation of Conversational ResponsesPreprint
Sordoni, A., Galley, M., Auli, M., Brockett, C., Ji, Y., Mitchell, M., Nie, J., Gao, J., & Dolan, B. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.06714 · Cited by 63 · see citing works
Goal-Oriented Visual Question Generation via Intermediate Rewards
Zhang, J., Wu, Q., Shen, C., Zhang, J., Lu, J., & van den Hengel, A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01228-1_12 · Cited by 39 · see citing works
Self-citationEnd-to-end optimization of goal-driven and visually grounded dialogue systemsPreprint
Strub, F., de Vries, H., Mary, J., Piot, B., Courville, A. C., & Pietquin, O. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.05423 · Cited by 28 · see citing works
Visual DialogPreprint
Das, A., Kottur, S., Gupta, K., Singh, A., Jain, D., Moura, J. M. F., Parikh, D., & Batra, D. (2016) · arXiv (Cornell University) · Cited by 25 · see citing works
Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial LearningPreprint
Wu, Q., Wang, P., Shen, C., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.07613 · Cited by 16 · see citing works
Self-citationGuessWhat?! Visual object discovery through multi-modal dialoguePreprint
de Vries, H., Strub, F., Chandar, S., Pietquin, O., Larochelle, H., & Courville, A. C. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.08481 · Cited by 16 · see citing works
Answerer in Questioner's Mind for Goal-Oriented Visual Dialogue.Preprint
Lee, S.-W., Heo, Y., & Zhang, B. (2018) · arXiv (Cornell University) · Cited by 14 · see citing works
Lipton, Z. C., Li, X., Gao, J., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.05715 · Cited by 14 · see citing works
Deep Active Learning for Dialogue GenerationPreprint
Asghar, N., Poupart, P., Jiang, X., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.03929 · Cited by 10 · see citing works
Zhao, R., & Tresp, V. (2018) · arXiv (Cornell University) · Cited by 6 · see citing works
Flagged first, then by citations
Research works printed but not linked: 5
- Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vish- wanathan, and R. Garnett, editors, Advances in Neural In- formation Processing Systems 30, pages 5574-5584.
- N. Srinivas, A. Krause, S. Kakade, and M. Seeger. Gaussian process optimization in the bandit setting: no regret and ex- perimental design. In Proceedings of the 27th International Conference on International Conference on Machine Learn- ing, 2010. 5
- S. Sukhbaatar, a. szlam, J. Weston, and R. Fergus. End-to- end memory networks. In C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, and R. Garnett, editors, Advances in Neu- ral Information Processing Systems 28, pages 2440-2448.
- R. S. Sutton and A. G. Barto. Reinforcement learning: An in- troduction. IEEE Transactions on Neural Networks, 16:285- 286, 1998. 1, 4
- R. S. Sutton, D. McAllester, S. Singh, and Y. Mansour. Pol- icy gradient methods for reinforcement learning with func- tion approximation. In Proceedings of the 12th Interna- tional Conference on Neural Information Processing Sys- tems, NIPS'99, Cambridge, MA, USA, 1999. MIT Press. 4
Cited by
Sorted by citations
A review of uncertainty quantification in deep learning: Techniques, applications and challenges
Abdar, M., Pourpanah, F., Hussain, S., Rezazadegan, D., Liu, L., Ghavamzadeh, M., Fieguth, P., Cao, X., Khosravi, A., Acharya, U. R., et al. (2021) · Information Fusion · doi:10.1016/j.inffus.2021.05.008 · Cited by 2,720 · see citing works
- Authors
- Abbasnejad, E., Wu, Q., Shi, Q., & van den Hengel, A.
- Affiliations
- Adelaide
- The University of Adelaide (AU)
- Univ. of Adelaide
- Venue
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 4150-4159
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2903778570
- Cited by
- 16
- References
- 43
- Citations by year
- 2024: 2 · 2023: 2 · 2021: 6 · 2020: 6
- FWCI
- 1.15
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Multi-Agent Systems and Negotiation
- Keywords
- visual dialogue, uncertainty modeling, Bayesian uncertainty, regret minimization, negotiation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
