Adversarial Learning for Neural Dialogue Generation
Open accessThe DOI matches its Crossref record; 50 of the 50 references it cites were found in a registry or an index.
Abstract
In this paper, drawing intuition from the Turing test, we propose using adversarial training for open-domain dialogue generation: the system is trained to produce sequences that are indistinguishable from human-generated dialogue utterances.We cast the task as a reinforcement learning (RL) problem where we jointly train two systems, a generative model to produce response sequences, and a discriminator-analagous to the human evaluator in the Turing test-to distinguish between the human-generated dialogues and the machine-generated ones.The outputs from the discriminator are then used as rewards for the generative model, pushing the system to generate dialogues that mostly resemble human dialogues.In addition to adversarial training we describe a model for adversarial evaluation that uses success in fooling an adversary as a dialogue evaluation metric, while avoiding a number of potential pitfalls.Experimental results on several metrics, including adversarial evaluation, demonstrate that the adversarially-trained system generates higher-quality responses than previous baselines.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 3×
“2 To be specific, each utterance p or q is mapped to a vector representation h p or h q using LSTM (Hochreiter and Schmidhuber, 1997).”
MethodInfluentialLabaca-Castro, R. (2023) · Machine Learning under Malware Attack · doi:10.1007/978-3-658-40442-0_9 · Cited by 19,272
GAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
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
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
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Unsupervised representation learning with deep convolutional generative adversarial networks
Radford, A., Metz, L., & Chintala, S. (2015) · arXiv · doi:10.48550/arxiv.1511.06434 · Cited by 12,235 · cited 2×
“Adversarial networks The idea of generative adversarial networks has enjoyed great success in computer vision (Radford et al., 2015; Chen et al., 2016a; Salimans et al., 2016).”
BackgroundEffective Approaches to Attention-based Neural Machine Translation
Luong, T., Pham, H., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1166 · Cited by 8,382
Improved Techniques for Training GANs
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016) · arXiv · doi:10.48550/arxiv.1606.03498 · Cited by 6,965
Computing Machinery and Intelligence (1950)
Turing, A. (2004) · The Essential Turing · doi:10.1093/oso/9780198250791.003.0017 · Cited by 6,118
Cited by
Improved training of Wasserstein GANs
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. (2017) · arXiv · doi:10.48550/arxiv.1704.00028 · Cited by 6,800
“Other attempts at language modeling with GANs [31, 14, 29, 5, 15, 10] typically use discrete models and gradient estimators [27, 12, 16].”
MethodSpectral Normalization for Generative Adversarial Networks
Miyato, T., Kataoka, T., Koyama, M., & Yoshida, Y. (2018) · arXiv · doi:10.48550/arxiv.1802.05957 · Cited by 3,438
“…adversarial networks (GANs) (Goodfellow et al., 2014) have been enjoying considerable success as a framework of generative models in recent years, and it has been applied to numerous types of tasks and datasets (Radford et al., 2016; Salimans et al., 2016; Ho & Ermon, 2016; Li et al., 2017).”
MethodRecent Trends in Deep Learning Based Natural Language Processing [Review Article]
Young, T., Hazarika, D., Poria, S., & Cambria, E. (2018) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2018.2840738 · Cited by 2,921
Adversarial Examples for Evaluating Reading Comprehension Systems
Jia, R., & Liang, P. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1215 · Cited by 1,410
“Bowman et al. (2016) and Li et al. (2017) used such a setup for sentence and dialogue generation, respectively.”
The Curious Case of Neural Text Degeneration
Holtzman, A., Buys, J., Du, L., Forbes, M., & Choi, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.09751 · Cited by 1,304
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
Gui, J., Sun, Z., Wen, Y., Tao, D., & Ye, J. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3130191 · Cited by 1,231
“[382] used adversarial learning for neural dialogue generation.”
Recent Trends in Deep Learning Based Natural Language Processing
Young, T., Hazarika, D., Poria, S., & Cambria, E. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.02709 · Cited by 1,192
Generative adversarial networks: introduction and outlook
Wang, K., Gou, C., Duan, Y., Lin, Y., Zheng, X., & Wang, F.-Y. (2017) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2017.7510583 · Cited by 806
Recent Progress on Generative Adversarial Networks (GANs): A Survey
Pan, Z., Yu, W., Yi, X., Khan, A., Yuan, F., & Zheng, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2905015 · Cited by 701
GraphGAN: Graph Representation Learning With Generative Adversarial Nets
Wang, H., Wang, J., Wang, J., Zhao, M., Zhang, W., Zhang, F., Xie, X., & Guo, M. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11872 · Cited by 653
DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
Li, Y., Su, H., Shen, X., Li, W., Cao, Z., & Niu, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.03957 · Cited by 646
Towards a Human-like Open-Domain Chatbot
Adiwardana, D., Luong, M.-T., So, D. R., Hall, J., Fiedel, N., Thoppilan, R., Yang, Z., Kulshreshtha, A., Nemade, G., Lu, Y., et al. (2020) · arXiv · doi:10.48550/arxiv.2001.09977 · Cited by 614
“Recent works also explore new frameworks such as adversarial learning (Li et al., 2017; Zhang et al., 2018c), variational autoencod-ing (Zhao et al., 2017; Gu et al., 2019), or both (Gao et al., 2019b) at the cost of added complexity and less scalability.”
BackgroundA Survey on Dialogue Systems: Recent Advances and New Frontiers
Chen, H., Liu, X., Yin, D., & Tang, J. (2017) · ACM SIGKDD Explorations Newsletter · doi:10.1145/3166054.3166058 · Cited by 579
Electrocardiogram generation with a bidirectional LSTM-CNN generative adversarial network
Zhu, F., Ye, F., Fu, Y., Liu, Q., & Shen, B. (2019) · Scientific Reports · doi:10.1038/s41598-019-42516-z · Cited by 540
Challenges in Data-to-Document Generation
Wiseman, S., Shieber, S., & Rush, A. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1239 · Cited by 524
Long Text Generation via Adversarial Training with Leaked Information
Guo, J., Lu, S., Cai, H., Zhang, W., Yu, Y., & Wang, J. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11957 · Cited by 499
A Literature Survey of Recent Advances in Chatbots
Caldarini, G., Jaf, S., & McGarry, K. (2022) · Information · doi:10.3390/info13010041 · Cited by 470
“[52,77] suggest employing adversarial training for open-domain dialogue generation, drawing inspiration from the Turing test: the system is trained to generate sequences that are indistinguishable from human-generated sentences.”
BackgroundMethodLearning Cooperative Visual Dialog Agents with Deep Reinforcement Learning
Das, A., Kottur, S., Moura, J. M. F., Lee, S., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.321 · Cited by 356
Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network
Zhou, X., Li, L., Dong, D., Liu, Y., Chen, Y., Zhao, W. X., Yu, D., & Wu, H. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1103 · Cited by 328
Semantic memory: A review of methods, models, and current challenges
Kumar, A. A. (2021) · Psychonomic Bulletin & Review · doi:10.3758/s13423-020-01792-x · Cited by 314
Gao, X., Deng, F., & Yue, X. (2020) · Neurocomputing · doi:10.1016/j.neucom.2018.10.109 · Cited by 297
Challenges in building intelligent open-domain dialog systems
Huang, M., Zhu, X., & Gao, J. (2020) · ACM Transactions on Information Systems · doi:10.1145/3383123 · Cited by 288
Budzianowski, P., & Vulić, I. (2019) · Proceedings of the 3rd Workshop on Neural Generation and Translation · doi:10.18653/v1/d19-5602 · Cited by 279
Self-Supervised Video Hashing With Hierarchical Binary Auto-Encoder
Song, J., Zhang, H., Li, X., Gao, L., Wang, M., & Hong, R. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2814344 · Cited by 276
Automatic Detection of Generated Text is Easiest when Humans are Fooled
Ippolito, D., Duckworth, D., Callison-Burch, C., & Eck, D. (2019) · arXiv · doi:10.48550/arxiv.1911.00650 · Cited by 264
“Finally, discriminators for whether text is machine-generated are a promising research direction in adversarial training (Lin et al., 2017; Li et al., 2017) and in”
BackgroundAutomatic Detection of Generated Text is Easiest when Humans are Fooled
Ippolito, D., Duckworth, D., Callison-Burch, C., & Eck, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.164 · Cited by 264
“Finally, discriminators for whether text is machine-generated are a promising research direction in adversarial training (Lin et al., 2017; Li et al., 2017) and in”
BackgroundRecent advances in deep learning based dialogue systems: a systematic survey
Ni, J., Young, T., Pandelea, V., Xue, F., & Cambria, E. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-022-10248-8 · Cited by 264
DailyDialog: A Manually Labelled Multi-Turn Dialogue Dataset
Li, Y. (2025) · TIB Data Manager · doi:10.57702/l9x4bl6j · Cited by 262
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
Gui, J., Sun, Z., Wen, Y., Tao, D., & Ye, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.06937 · Cited by 253
Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
Esteban, C., Hyland, S. L., & Rätsch, G. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.02633 · Cited by 253
What makes a good conversation? How controllable attributes affect human judgments
See, A., Roller, S., Kiela, D., & Weston, J. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1170 · Cited by 247
A Survey of Evaluation Metrics Used for NLG Systems
Sai, A. B., Mohankumar, A. K., & Khapra, M. M. (2023) · ACM Computing Surveys · doi:10.1145/3485766 · Cited by 235
Unifying Human and Statistical Evaluation for Natural Language Generation
Hashimoto, T. B., Zhang, H., & Liang, P. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1169 · Cited by 161
Assessing The Factual Accuracy of Generated Text
Goodrich, B., Rao, V., Liu, P. J., & Saleh, M. (2019) · Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3292500.3330955 · Cited by 162
“tps: //doi.org/10.1145/3292500.3330955 1 INTRODUCTION Recently, there has been wide empirical success in text summarization [15, 21, 27], machine translation [1, 36, 39], dialogue response generation [12, 28, 29], and other text generation tasks. For evaluation, these models generally rely on metrics like ROUGE (Recal…”
MethodInfluentialUSR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation
Mehri, S., & Eskenazi, M. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.64 · Cited by 149
Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play
Sukhbaatar, S., Lin, Z., Kostrikov, I., Synnaeve, G., Szlam, A., & Fergus, R. (2017) · arXiv · doi:10.48550/arxiv.1703.05407 · Cited by 149
“Thus after finishing an episode, we update the model parameters θ by ∆θ = T∑ t=1 [ ∂ log f(at|st, θ) ∂θ ( T∑ i=t ri − b(st, θ) ) −λ ∂ ∂θ ( T∑ i=t ri − b(st, θ) )2 .”
Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog
Jaques, N., Ghandeharioun, A., Shen, J. H., Ferguson, C., Lapedriza, A., Jones, N., Gu, S., & Picard, R. (2019) · arXiv · doi:10.48550/arxiv.1907.00456 · Cited by 126
Adversarial Attacks Against Deep Generative Models on Data: A Survey
Sun, H., Zhu, T., Zhang, Z., Jin, D., Xiong, P., & Zhou, W. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3130903 · Cited by 90
“However, DGMs have wide applications in NLP, such as text to image (T2I) [93], [94], or text generation [95], [96], e.”
BackgroundImportance of Search and Evaluation Strategies in Neural Dialogue Modeling
Kulikov, I., Miller, A., Cho, K., & Weston, J. (2019) · Proceedings of the 12th International Conference on Natural Language Generation · doi:10.18653/v1/w19-8609 · Cited by 83
User Simulation for Evaluating Information Access Systems
Balog, K., & Zhai, C. (2024) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000098 · Cited by 52
Generation of Synthetic Electronic Medical Record Text
Guan, J., Li, R., Yu, S., & Zhang, X. (2018) · 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm.2018.8621223 · Cited by 49
Teaching Machines to Ask Questions
Yao, K., Zhang, L., Luo, T., Tao, L., & Wu, Y. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/632 · Cited by 44
Learning towards conversational AI: A survey
Fu, T., Gao, S., Zhao, X., Wen, J.-R., & Yan, R. (2022) · AI Open · doi:10.1016/j.aiopen.2022.02.001 · Cited by 46
Improvised Theatre Alongside Artificial Intelligences
Mathewson, K., & Mirowski, P. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v13i1.12926 · Cited by 31
On the Weaknesses of Reinforcement Learning for Neural Machine Translation
Choshen, L., Fox, L., Aizenbud, Z., & Abend, O. (2019) · arXiv · doi:10.48550/arxiv.1907.01752 · Cited by 28
MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation
Feng, J., Sun, Q., Xu, C., Zhao, P., Yang, Y., Tao, C., Zhao, D., & Lin, Q. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.405 · Cited by 26
User Simulation for Evaluating Information Access Systems
Balog, K., & Zhai, C. (2023) · arXiv · doi:10.48550/arxiv.2306.08550 · Cited by 26
What's to Know? Uncertainty as a Guide to Asking Goal-Oriented Questions
Abbasnejad, E., Wu, Q., Shi, Q., & van den Hengel, A. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00428 · Cited by 16
“Goal-oriented dialogue Dialogue generation [22, 23, 29, 3] has been studied for many years in the NLP literature, and has many applications.”
BackgroundQuestion Generation With Doubly Adversarial Nets
Bao, J., Gong, Y., Duan, N., Zhou, M., & Zhao, T. (2018) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2018.2859777 · Cited by 14
FCM: A Fine-grained Comparison Model for Multi-turn Dialogue Reasoning
Wang, X., Zhang, H., Zhao, S., Zou, Y., Chen, H., Ding, Z., Cheng, B., & Lan, Y. (2021) · Findings of the Association for Computational Linguistics: EMNLP 2021 · doi:10.18653/v1/2021.findings-emnlp.362 · Cited by 4
Metadata
- Authors
- Li, J., Monroe, W., Shi, T., Jean, S., Ritter, A., & Jurafsky, D.
- Venue
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Published
- 2017
- Pages
- 2157-2169
- OpenAlex
- W2581637843
- Cited by
- 873
- References
- 50
- FWCI
- 73.04
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.