Question generation based on chat-response conversion
Corresponding Author
Sheng-Hua Zhong
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China
The National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China
Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen, China
Sheng-hua Zhong, College of Computer Science and Software Engineering, Shenzhen University, 518000, Shenzhen, People's Republic of China; or The National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, 518000, Shenzhen, People's Republic of China; or Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, 518060, Shenzhen, China.
Email: [email protected]
Search for more papers by this authorJianfeng Peng
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China
Search for more papers by this authorPeiqi Liu
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China
Search for more papers by this authorCorresponding Author
Sheng-Hua Zhong
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China
The National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China
Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen, China
Sheng-hua Zhong, College of Computer Science and Software Engineering, Shenzhen University, 518000, Shenzhen, People's Republic of China; or The National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, 518000, Shenzhen, People's Republic of China; or Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, 518060, Shenzhen, China.
Email: [email protected]
Search for more papers by this authorJianfeng Peng
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China
Search for more papers by this authorPeiqi Liu
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China
Search for more papers by this authorSummary
Today, thanks to the major breakthrough of sequences to sequences model in the field of natural language, most of the dialogue generation tasks are focused on generating more effective responses. However, the responses proposed by the chat-bot are only a passive answer or assentation, which does not arouse the desire of people to continue communicating. How to transform the chat robot from a passive reply to an active questioner has become an urgent problem. In this paper, a question generalization method with four types of question proposing schemes are designed, implemented, and tested to automate question generation process. The proposed system is controlled by a probability-triggered multiple conversion mechanism to actively propose different types of questions. We embed our methods in the mainstream dialogue generation model and demonstrate its effectiveness in dialogue response generalization on a standard dataset. In addition, it achieves good performance in subjective conversational assessment.
REFERENCES
- 1Kumar V, Boorla K, Meena Y, Ramakrishnan G, Li Y-F. Automating reading comprehension by generating question and answer pairs. Paper presented at: Pacific-Asia Conference on Knowledge Discovery and Data Mining; 2018; Melbourne, Australia.
- 2Ibarra F, Baez M, Fiore F, Casati F. Stimulating conversations in residential care through technology-mediated reminiscence. Paper presented at: IFIP Conference on Human-Computer Interaction; 2017; Bombay, India.
- 3Chandar P, Khazaeni Y, Davis M, et al. Leveraging conversational systems to assists new hires during onboarding. Paper presented at: IFIP Conference on Human-Computer Interaction; 2017; Bombay, India.
- 4Li J, Galley M, Brockett C, Gao J, Dolan B. A diversity-promoting objective function for neural conversation models. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies; 2016; San Diego, CA.
- 5Hussein H, Elmogy M, Guirguis S. Automatic English question generation system based on template driven scheme. Int J Comput Sci Issues. 2014; 11(6): 45.
- 6Cho K, Van Merriënboer B, Gulcehre C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:14061078; 2014.
- 7Wu B, Wang B, Xue H. Ranking responses oriented to conversational relevance in chat-bots. In: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers; 2016; Osaka, Japan.
- 8Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate. 2017.
- 9Sutskever I, Vinyals O, Le QV. Sequence to sequence learning with neural networks. Paper presented at: Advances in Neural Information Processing Systems; 2014; Montreal, Canada.
- 10Yao K, Zweig G, Peng B. Attention with intention for a neural network conversation model. arXiv preprint arXiv:151008565; 2015.
- 11Li J, Monroe W, Ritter A, Galley M, Gao J, Jurafsky D. Deep reinforcement learning for dialogue generation. arXiv preprint arXiv:160601541; 2016.
- 12Liu Y, Bi W, Gao J, Liu X, Yao J, Shi S. Towards less generic responses in neural conversation models: a statistical re-weighting method. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing; 2018; Brussels, Belgium.
- 13Mostow J, Chen W. Generating instruction automatically for the reading strategy of self-questioning. In: Artificial Intelligence in Education: Building Learning Systems that Care: From Knowledge Representation to Affective Modelling. Amsterdam, The Netherlands: IOS Press; 2009.
- 14Lindberg D, Popowich F, Nesbit J, Winne P. Generating natural language questions to support learning on-line. In: Proceedings of the 14th European Workshop on Natural Language Generation; 2013; Sofia, Bulgaria.
- 15Labutov I, Basu S, Vanderwende L. Deep questions without deep understanding. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers); 2015; Beijing, China.
- 16Du X, Cardie C. Identifying where to focus in reading comprehension for neural question generation. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing; 2017; Copenhagen, Denmark.
- 17Du X, Shao J, Cardie C. Learning to ask: neural question generation for reading comprehension. arXiv preprint arXiv:170500106; 2017.
- 18Yuan X, Wang T, Gulcehre C, et al. Machine comprehension by text-to-text neural question generation. In: Proceedings of the 2nd Workshop on Representation Learning for NLP; 2017; Vancouver, Canada.
- 19Tang D, Duan N, Qin T, Yan Z, Zhou M. Question answering and question generation as dual tasks. arXiv preprint arXiv:170602027; 2017.
- 20Wang T, Yuan X, Trischler A. A joint model for question answering and question generation. arXiv preprint arXiv:170601450; 2017.
- 21Komatani K, Otsuka T, Sato S, Nakano M. Question selection based on expected utility to acquire information through dialogue. Dialogues With Social Robots. Singapore: Springer; 2017: 79-91.
10.1007/978-981-10-2585-3_6 Google Scholar
- 22Liu H, Rong W, Shi L, Ouyang Y, Xiong Z. Question rewrite based dialogue response generation. Paper presented at: International Conference on Neural Information Processing; 2018; Siem Reap, Cambodia.
- 23Serikawa S, Lu H. Underwater image dehazing using joint trilateral filter. Comput Electr Eng. 2014; 40(1): 41-50.
- 24Lu H, Li Y, Mu S, Wang D, Kim H, Serikawa S. Motor anomaly detection for unmanned aerial vehicles using reinforcement learning. IEEE Internet Things J. 2017; 5(4): 2315-2322.
- 25Lu H, Li Y, Chen M, Kim H, Serikawa S. Brain intelligence: go beyond artificial intelligence. Mob Netw Appl. 2018; 23(2): 368-375.
- 26Lu H, Wang D, Li Y, et al. CONet: a cognitive ocean network. arXiv preprint arXiv:190106253; 2019.
- 27Lu H, Li Y, Uemura T, Kim H, Serikawa S. Low illumination underwater light field images reconstruction using deep convolutional neural networks. Future Gener Comput Syst. 2018; 82: 142-148.
- 28Yu Y, Tang S, Aizawa K, Aizawa A. Category-based deep CCA for fine-grained venue discovery from multimodal data. IEEE Trans Neural Netw Learn Syst. 2018; 30(4): 1250-1258.
- 29Yu Y, Tang S, Raposo F, Chen L. Deep cross-modal correlation learning for audio and lyrics in music retrieval. ACM Trans Multimed Comput Commun Appl. 2019; 15(1). Article No. 20.
- 30Li Y, Duan N, Zhou B, et al. Visual question generation as dual task of visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2018; Salt Lake City, Utah.
- 31Jain U, Zhang Z, Schwing AG. Creativity: generating diverse questions using variational autoencoders. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2017; Honolulu, Hawaii.
- 32Zhang J, Wu Q, Shen C, Zhang J, Lu J, Hengel Antonvanden. Asking the difficult questions: goal-oriented visual question generation via intermediate rewards. arXiv preprint arXiv:171107614; 2017.
- 33Duan N, Tang D, Chen P, Zhou M. Question generation for question answering. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing; 2017; Copenhagen, Denmark.
- 34Li J, Monroe W, Jurafsky D. A simple, fast diverse decoding algorithm for neural generation. arXiv preprint arXiv:161108562; 2016.
