ABSTRACT
Dialogue system has made great progress recently, but it is still in the initial stage of passive reply. How to build a dialogue model with proactive reply ability is a great challenge. This paper proposes an End-to-End dialogue model based on Memory network and Graph Neural Network, which uses memory network to store conversation history and knowledge, and uses Graph Neural Network to encode background knowledge. We propose a soft weighting mechanism to integrate the dialogue goal information into the query pointer, so as to enhance the dynamic topic transfer ability during decoding. Experimental results indicate that our model outperforms various kinds of generation models under automatic evaluations and can accomplish the conversational target more actively
- Qin Qin and Yong-qiang He, "Crowd Naturalness Driven Mobile Cognition Scheme in Human Computer Interaction Dialogue System," Journal of Communications, vol. 12, no. 2, pp. 118--122, 2017. Doi: 10.12720/jcm.12.2.118-122Google Scholar
- Ji Z, Lu Z, Li H. An Information Retrieval Approach to Short Text Conversation[J]. Computer Science, 2014.Google Scholar
- Shang L, Lu Z, Li H. Neural Responding Machine for Short-Text Conversation[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. 2015: 1577--1586.Google Scholar
- Serban I V, Sordoni A, Bengio Y, et al. Building end-to-end dialogue systems using generative hierarchical neural network models[C]//Thirtieth AAAI Conference on Artificial Intelligence. 2016. Google Scholar
- Eric M, Manning C D. A Copy-Augmented Sequence-to-Sequence Architecture Gives Good Performance on Task-Oriented Dialogue[C]//Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers. 2017: 468--473.Google Scholar
- Sukhbaatar S, Weston J, Fergus R. End-to-end memory networks[C]//Advances in neural information processing systems. 2015: 2440--2448. Google Scholar
- Ritter A, Cherry C, Dolan W B. Data-driven response generation in social media[C]//Proceedings of the conference on empirical methods in natural language processing. Association for Computational Linguistics, 2011: 583--593. Google Scholar
- Madotto A, Wu C S, Fung P. Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018: 1468--1478.Google Scholar
- Li J, Galley M, Brockett C, et al. A Diversity-Promoting Objective Function for Neural Conversation Models[C]//Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016: 110--119.Google Scholar
- Bordes A, Boureau Y L, Weston J. Learning end-to-end goal-oriented dialog[J]. arXiv preprint arXiv:1605.07683, 2016.Google Scholar
- Zhang B, Xu X, Li X, et al. Learning Personalized End-to-End Task-Oriented Dialogue Generation[C]//CCF International Conference on Natural Language Processing and Chinese Computing. Springer, Cham, 2019: 55--66.Google Scholar
- Young S, Gašić M, Thomson B, et al. Pomdp-based statistical spoken dialog systems: A review[J]. Proceedings of the IEEE, 2013, 101(5): 1160--1179.Google ScholarCross Ref
- Bordes A, Boureau Y L, Weston J. Learning end-to-end goal-oriented dialog[J]. arXiv preprint arXiv:1605.07683, 2016.Google Scholar
- Mo K, Zhang Y, Li S, et al. Personalizing a dialogue system with transfer reinforcement learning[C]//Thirty-Second AAAI Conference on Artificial Intelligence. 2018.Google Scholar
- Wang Y, Liu C, Huang M, et al. Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018: 2193--2203.Google Scholar
- Li R, Kahou S E, Schulz H, et al. Towards deep conversational recommendations[C]//Advances in Neural Information Processing Systems. 2018: 9725--9735. Google Scholar
- Wu W, Guo Z, Zhou X, et al. Proactive Human-Machine Conversation with Explicit Conversation Goal[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019: 3794--3804.Google Scholar
- Scarselli F, Gori M, Tsoi A C, et al. The graph neural network model[J]. IEEE Transactions on Neural Networks, 2008, 20(1): 61--80. Google ScholarDigital Library
- Hamilton W, Ying Z, Leskovec J. Inductive representation learning on large graphs[C]//Advances in Neural Information Processing Systems. 2017: 1024--1034. Google Scholar
- Berg R, Kipf T N, Welling M. Graph convolutional matrix completion[J]. arXiv preprint arXiv:1706.02263, 2017.Google Scholar
- Hamaguchi T, Oiwa H, Shimbo M, et al. Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach[C]//Pr-oceedings of Twenty-Sixth International Joint Conference on Artificial Intelligence 2017:1802--1808. Google Scholar
- Li Y, Tarlow D, Brockschmidt M, et al. Gated graph sequence neural networks[J]. arXiv preprint arXiv:1511.05493, 2015.Google Scholar
- Park N, Kan A, Dong X L, et al. Estimating node importance in knowledge graphs using graph neural networks[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2019: 596--606. Google Scholar
- Beck D, Haffari G, Cohn T. Graph-to-Sequence Learning using Gated Graph Neural Networks[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018: 273--283.Google Scholar
- Nathani D, Chauhan J, Sharma C, et al. Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019: 4710--4723.Google Scholar
- Bansal T, Juan D C, Ravi S, et al. A2N: Attending to Neighbors for Knowledge Graph Inference[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019: 4387--4392.Google Scholar
- Sukhbaatar S, Weston J, Fergus R. End-to-end memory networks[C]//Advances in neural information processing systems. 2015: 2440--2448. Google Scholar
- Chung J, Gulcehre C, Cho K, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[C]//NIPS 2014 Workshop on Deep Learning, December 2014. 2014.Google Scholar
Index Terms
- Multi-Hop Memory Network with Graph Neural Networks Encoding for Proactive Dialogue
Recommendations
Proactive Retrieval-based Chatbots based on Relevant Knowledge and Goals
SIGIR '21: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information RetrievalA proactive dialogue system has the ability to proactively lead the conversation. Different from the general chatbots which only react to the user, proactive dialogue systems can be used to achieve some goals, e.g., to recommend some items to the user. ...
Visual Dialog with Multi-turn Attentional Memory Network
Advances in Multimedia Information Processing – PCM 2018AbstractVisual dialog is a task of answering a question given an input image, a historical dialog about the image and often requires to retrieve visual and textual facts about the question. This problem is different from visual question answering (VQA), ...
Memory-Augmented Dialogue Management for Task-Oriented Dialogue Systems
Dialogue management (DM) is responsible for predicting the next action of a dialogue system according to the current dialogue state and thus plays a central role in task-oriented dialogue systems. Since DM requires having access not only to local ...
Comments