Abstract
Consistency discrimination between attribute information and generated response is vital to personality-based dialogue. On existing work, few works specially investigates the consistency. In this paper, we propose a feasible method to solve this problem. We combine the typical natural language inference model (ESIM) and natural language understanding model (Bert) to discriminate consistency. But ESIM will fail when the input is structured attribute information. To solve this, We introduce external knowledge to expand the attribute information. Additionally, we observed the characteristics in the dialogue and found that adding a keyword matching label to the generated response is effective. We experimented on KvPI dataset and analyze the impact of different data sizes on the model. Compared with traditional methods, our method overall achieved better results.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Xu, B., Xu, Y., Liang, J., Xie, C., Liang, B., Cui, W., Xiao, Y.: CN-DBpedia: a never-ending chinese knowledge extraction system. In: Benferhat, S., Tabia, K., Ali, M. (eds.) IEA/AIE 2017. LNCS (LNAI), vol. 10351, pp. 428–438. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-60045-1_44
Bowman, S.R., Angeli, G., Potts, C., Manning, C.D.: A large annotated corpus for learning natural language inference. In: EMNLP (2015)
Chen, Q., Zhu, X.D., Ling, Z., Wei, S., Jiang, H., Inkpen, D.: Enhanced LSTM for natural language inference. In: ACL (2017)
Chen, W., et al.: TabFact: a large-scale dataset for table-based fact verification. arXiv:abs/1909.02164 (2020)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)
Huang, Z., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for sequence taggin. arXiv:abs/1508.01991 (2015)
Kim, H., Kim, B., Kim, G.: Will I sound like me? improving persona consistency in dialogues through pragmatic self-consciousness. In: EMNLP (2020)
Li, J., Galley, M., Brockett, C., Spithourakis, G.P., Gao, J., Dolan, W.: A persona-based neural conversation model. arXiv:abs/1603.06155 (2016)
Lin, Z., Madotto, A., Wu, C.S., Fung, P.: Personalizing dialogue agents via meta-learning. In: ACL (2019)
Liu, Q., et al.: You impress me: Dialogue generation via mutual persona perception. In: ACL (2020)
Manning, C.D., MacCartney, B.: Natural language inference (2009)
Mazaré, P.E., Humeau, S., Raison, M., Bordes, A.: Training millions of personalized dialogue agents. In: EMNLP (2018)
Mesgar, M., Simpson, E., Gurevych, I.: Improving factual consistency between a response and persona facts. In: EACL (2021)
Parikh, A.P., Täckström, O., Das, D., Uszkoreit, J.: A decomposable attention model for natural language inference. In: EMNLP (2016)
Platt, J.: Sequential minimal optimization : a fast algorithm for training support vector machines. Microsoft Research Technical Report (1998)
Qian, Q., Huang, M., Zhao, H., Xu, J., Zhu, X.: Assigning personality/profile to a chatting machine for coherent conversation generation. In: IJCAI (2018)
Radford, A., Narasimhan, K.: Improving language understanding by generative pre-training (2018)
Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137–1149 (2015)
Rocktäschel, T., Grefenstette, E., Hermann, K., Kociský, T., Blunsom, P.: Reasoning about entailment with neural attention. CoRR abs/1509.06664 (2016)
Sharma, A.: Sequential LSTM-based encoder for NLI (2017)
Song, H., Wang, Y., Zhang, K., Zhang, W., Liu, T.: BoB: BERT over BERT for training persona-based dialogue models from limited personalized data. In: ACL/IJCNLP (2021)
Song, H., Wang, Y., Zhang, W., Liu, X., Liu, T.: Generate, delete and rewrite: a three-stage framework for improving persona consistency of dialogue generation. In: ACL (2020)
Song, H., Wang, Y., Zhang, W., Zhao, Z., Liu, T., Liu, X.: Profile consistency identification for open-domain dialogue agents. In: EMNLP (2020)
Song, H., Zhang, W., Cui, Y., Wang, D., Liu, T.: Exploiting persona information for diverse generation of conversational responses. In: IJCAI (2019)
Song, H., Zhang, W., Hu, J., Liu, T.: Generating persona consistent dialogues by exploiting natural language inference. In: AAAI (2020)
Tigunova, A., Yates, A., Mirza, P., Weikum, G.: Charm: Inferring personal attributes from conversations. In: EMNLP (2020)
Welleck, S., Weston, J., Szlam, A.D., Cho, K.: Dialogue natural language inference. In: ACL (2019)
Wolf, T., Sanh, V., Chaumond, J., Delangue, C.: Transfertransfo: a transfer learning approach for neural network based conversational agents. arXiv:abs/1901.08149 (2019)
Zhang, S., Dinan, E., Urbanek, J., Szlam, A.D., Kiela, D., Weston, J.: Personalizing dialogue agents: I have a dog, do you have pets too? In: ACL (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhou, J. et al. (2022). Profile Consistency Discrimination. In: Rage, U.K., Goyal, V., Reddy, P.K. (eds) Database Systems for Advanced Applications. DASFAA 2022 International Workshops. DASFAA 2022. Lecture Notes in Computer Science, vol 13248. Springer, Cham. https://doi.org/10.1007/978-3-031-11217-1_14
Download citation
DOI: https://doi.org/10.1007/978-3-031-11217-1_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-11216-4
Online ISBN: 978-3-031-11217-1
eBook Packages: Computer ScienceComputer Science (R0)