Strong Influence of Responses in Training Dialogue Response Generator
Source abstract
Abstract
The sequence-to-sequence model is a widely used model for dialogue response generators, but it tends to generate safe responses for most input queries. Since safe responses are unattractive and boring, a number of efforts have been made to make the generator produce diverse responses, but generating diverse responses is yet an open problem. As a solution to this problem, this paper proposes a novel response generator, Response Generator with Response Weight (RGRW). The proposed response generator is a transformer-based sequence-to-sequence model of which the encoder is a pre-trained Bidirectional Encoder Representations from Transformers (BERT) and the decoder is a variant of Generative Pre-Training of a language model-2 (GPT-2). Since the attention on the response is not reflected enough at the transformer-based sequence-to-sequence model, the proposed generator enhances the influence of a response by the response weight, which determines the importance of each token in a query with respect to the response. Then, the decoder of the generator processes the response weight as well as a query encoding to generate a diverse response. The effectiveness of RGRW is proven by showing that it generates more diverse and informative responses than the baseline response generator by focusing more on the tokens that are important for generating the response. Additionally, the proposed model overwhelms the Commonsense Knowledge-Aware Dialogue generation model (ConKADI), which is a state-of-the-art model.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Topic Modeling · Speech and dialogue systems · Natural Language Processing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Science and Engineering, Kyung Hee University, Yongin 17104, Korea
Funding
the National Research Foundation of Korea(NRF) funded by the Ministry of Education · Institute of Information & Communications Technology Planning & Evaluation(IITP) grant funded by the Korea government(MSIT)
References (42)
Show source-provided references
1. Sutskever, I., Vinyals, O., and Le, Q. (2014). Sequence to Sequence Learning with Neural Networks. Advances in Neural Information Processing Systems, Curran Associates, Inc.
2. Vinyals, O., and Le, Q. (2015). A Neural Conversational Model. arXiv.
3. Sordoni, A., Galley, M., Auli, M., Brockett, C., Ji, Y., Mitchell, M., Nie, J.Y., Gao, J., and Dolan, B. (June, January 31). A Neural Network Approach to Context-Sensitive Generation of Conversational Responses. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics, Denver, CO, USA.10.3115/v1/N15-1020 ↗
4. Serban, I.V., Sordoni, A., Lowe, R., Charlin, L., Pineau, J., Courville, A., and Bengio, Y. (2017, January 4–9). A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.10.1609/aaai.v31i1.10983 ↗
5. Ghazvininejad, M., Brockett, C., Chang, M., Dolan, B., Gao, J., tau Yih, W., and Galley, M. (2018, January 2–7). A Knowledge-Grounded Neural Conversation Model. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.10.1609/aaai.v32i1.11977 ↗
6. Wu, S., Li, Y., Zhang, D., Zhou, Y., and Wu, Z. (2020, January 5–10). Diverse and Informative Dialogue Generation with Context-Specific Commonsense Knowledge Awareness. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Seattle, WA, USA.10.18653/v1/2020.acl-main.515 ↗
7. Li, J., Galley, M., Brockett, C., Gao, J., and Dolan, B. (2016, January 12–17). A Diversity-Promoting Objective Function for Neural Conversation Models. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, CA, USA.10.18653/v1/N16-1014 ↗
8. Wu, B., Jiang, N., Gao, Z., Li, M., Wang, Z., Li, S., Feng, Q., Rong, W., and Wang, B. (2018). Why Do Neural Response Generation Models Prefer Universal Replies?. arXiv.
9. Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2019, January 2–7). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, MN, USA.
10. Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., and Sutskeveri, I. (2019). Language Models Are Unsupervised Multitask Learners, OpenAI. Technical Report.
11. Onan, A. (2019, January 24–27). Topic-enriched Word Embeddings for Sarcasm Identification. Proceedings of the Computer Science On-line Conference, Zlin, Czech Republic.10.1007/978-3-030-19807-7_29 ↗
12. Ensemble of Keyword Extraction Methods and Classifiers in Text Classification10.1016/j.eswa.2016.03.045 ↗
13. Zhou, H., Young, T., Huang, M., Zhao, H., Xu, J., and Zhu, X. (2018, January 13–19). Commonsense Knowledge Aware Conversation Generation with Graph Attention. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, Stockholm, Sweden.10.24963/ijcai.2018/643 ↗
14. Xu, Z., Liu, B., Wang, B., Sun, C., Wang, X., Wang, Z., and Qi, C. (2017, January 7–11). Neural Response Generation via GAN with an Approximate Embedding Layer. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark.10.18653/v1/D17-1065 ↗
15. Zhao, T., Zhao, R., and Eskenazi, M. (August, January 30). Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Vancouver, BC, Canada.
16. Li, J., Monroe, W., and Jurafsky, D. (2017). Data Distillation for Controlling Specificity in Dialogue Generation. arXiv.
17. Young, T., Cambria, E., Chaturvedi, I., Zhou, H., Biswas, S., and Huang, M. (2018, January 2–7). Augmenting End-to-End Dialogue Systems With Commonsense Knowledge. Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.10.1609/aaai.v32i1.11923 ↗
18. Liu, Z., Niu, Z.Y., Wu, H., and Wang, H. (2019, January 3–7). Knowledge Aware Conversation Generation with Explainable Reasoning over Augmented Graphs. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, Hong Kong, China.10.18653/v1/D19-1187 ↗
19. Dinan, E., Roller, S., Shuster, K., Fan, A., Auli, M., and Weston, J. (2018). Wizard of wikipedia: Knowledge-powered conversational agents. arXiv.
20. Zhang, S., Dinan, E., Urbanek, J., Szlam, A., Kiela, D., and Weston, J. (2018, January 15–20). Personalizing Dialogue Agents: I have a dog, do you have pets too?. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Australia.10.18653/v1/P18-1205 ↗
21. Rashkin, H., Smith, E., Li, M., and Boureau, Y.L. (August, January 28). Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy.
22. Jiang, S., Ren, P., Monz, C., and Rijke, M. (2019, January 15). Improving Neural Response Diversity with Frequency-Aware Cross-Entropy Loss. Proceedings of the Web Conference 2019, San Francisco, CA, USA.10.1145/3308558.3313415 ↗
23. A Term Weighted Neural Language Model and Stacked Bidirectional LSTM based Framework for Sarcasm Identification10.1109/ACCESS.2021.3049734 ↗
24. Xing, C., Wu, W., Wu, Y., Liu, J., Huang, Y., Zhou, M., and Ma, W.Y. (2017, January 4–9). Topic Aware Neural Response Generation. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.10.1609/aaai.v31i1.10981 ↗
25. Tang, J., Zhao, T., Xiong, C., Liang, X., Xing, E., and Hu, Z. (August, January 28). Target-Guided Open-Domain Conversation. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy.
26. Kingma, D., and Ba, J. (2015, January 7–9). Adam: A Method for Stochastic Optimization. Proceedings of the International Conference on Learning Representations, San Diego, CA, USA.
27. Pal, S., Herbig, N., Krüger, A., and van Genabith, J. (November, January 31). A Transformer-Based Multi-Source Automatic Post-Editing System. Proceedings of the Third Conference on Machine Translation: Shared Task Papers, Brussels, Belgium.
28. Zhang, M., Wang, X., Fang, F., Li, H., and Yamagishi, J. (2019, January 15–19). Joint Training Framework for Text-to-Speech and Voice Conversion Using Multi-Source Tacotron and WaveNet. Proceedings of the Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria.10.21437/Interspeech.2019-1357 ↗
29. Loshchilov, I., and Hutter, F. (2017). Decoupled Weight Decay Regularization. arXiv.
30. Li, Y., Su, H., Shen, X., Li, W., Cao, Z., and Niu, S. (December, January 27). DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset. Proceedings of the Eighth International Joint Conference on Natural Language Processing, Taipei, Taiwan.
31. Marujo, L., Ling, W., Trancoso, I., Dyer, C., Black, A., Gershman, A., Martins de Matos, D., Neto, J., and Carbonell, J. (2015, January 26–31). Automatic Keyword Extraction on Twitter. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, Beijing, China.10.3115/v1/P15-2105 ↗
32. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27–30). Rethinking the Inception Architecture for Computer Vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.308 ↗
33. Medelyan, O., Perrone, V., and Witten, I. (2010, January 21–25). Subject Metadata Support Powered by Maui. Proceedings of the 10th Annual Joint Conference on Digital Libraries, Gold Coast, Australia.10.1145/1816123.1816204 ↗
34. Ling, W., Dyer, C., Black, A., and Trancoso, I. (June, January 31). Two/Too Simple Adaptations of Word2Vec for Syntax Problems. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Denver, CO, USA.10.3115/v1/N15-1142 ↗
35. Owoputi, O., O’Connor, B., Dyer, C., Gimpel, K., Schneider, N., and Smith, N. (2013, January 9–14). Improved Part-of-Speech Tagging for Online Conversational Text with Word Clusters. Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Atlanta, GA, USA.
36. Marujo, L., Gershman, A., Carbonell, J., Frederking, R., and Neto, J.P. (2012, January 21–27). Supervised Topical Key Phrase Extraction of News Stories using Crowdsourcing, Light Filtering and Co-reference Normalization. Proceedings of the Eighth International Conference on Language Resources and Evaluation, Istanbul, Turkey.
37. Gu, J., Lu, Z., Li, H., and Li, V. (2016, January 7–12). Incorporating Copying Mechanism in Sequence-to-Sequence Learning. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Germany.10.18653/v1/P16-1154 ↗
38. Zhu, W., Mo, K., Zhang, Y., Zhu, Z., Peng, X., and Yang, Q. (2017). Flexible End-to-End Dialogue System for Knowledge Grounded Conversation. arXiv.
39. Liu, C.W., Lowe, R., Serban, I.V., Noseworthy, M., Charlin, L., and Pineau, J. (2016, January 1–5). How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, TX, USA.10.18653/v1/D16-1230 ↗
40. Li, J., Monroe, W., Shi, T., Jean, S., Ritter, A., and Jurafsky, D. (2017, January 7–11). Adversarial Learning for Neural Dialogue Generation. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark.10.18653/v1/D17-1230 ↗
41. Mou, L., Song, Y., Yan, R., Li, G., Zhang, L., and Jin, Z. (2016, January 11–16). Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversation. Proceedings of the COLING 2016, the 26th International Conference on Computational Linguistics, Osaka, Japan.
42. Zhao, M., Cong, Y., and Carin, L. (2020, January 12–18). On Leveraging Pretrained GANs for Generation with Limited Data. Proceedings of the Thirty-Seventh International Conference on Machine Learning, Vienna, Austria.