Skip to main content
SpringerLink
Log in

RFM: response-aware feedback mechanism for background based conversation

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

In general, the existing dialogue systems tend to generate generic responses due to lack of external knowledge. One of the usual solutions is the Background Based Conversations (BBCs), which can help dialogue systems generate more informative and appropriate responses, based on an external knowledge source. Unfortunately, there still exists some difficulties for BBCs when correcting the selected knowledge during response generation, e.g., see GTTP, CaKe. In this paper, we propose a novel architecture called Response-aware Feedback Mechanism (RFM) for BBCs to address this shortcoming. The main advantage is that a Response-aware Feedback Weight Vector is introduced to integrate the background knowledge and responses, so that the knowledge selector could select more accurate knowledge. With the help of this self-correcting mechanism, the selected knowledge is adjusted and corrected dynamically in each decoding time step. As an application, we carry out experiments on the Holl-E and Wizard of Wikipedia datasets, the results indicate that the RFM model has much better performance on automatic and human evaluation, compare to eleven state-of-the-art methods, including RefNet and GLKS.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Notes

  1. https://github.com/ChenchenJT/RFM

  2. https://www.mindspore.cn/

References

  1. Bahdanau D, Cho K, Bengio Y (2015) Neural bibmachine translation by jointly learning to align and translate. In: 3rd International conference on learning representations, ICLR 2015. Conference track proceedings, San Diego, USA, 7-9 May 2015

  2. Bastianelli E, Nardi D, Aiello LC et al (2016) Speaky for robots: the development of vocal interfaces for robotic applications. Appl Intell 44(1):43–66. https://doi.org/10.1007/s10489-015-0695-5

    Article  Google Scholar 

  3. Chen H, Ren Z, Tang J et al (2018) Hierarchical variational bibmemory network for dialogue generation. In: Proceedings of the 2018 world wide web conference on world wide web, WWW 2018, Lyon, France, 23-27 April 2018, pp 1653–1662

  4. Cho K, van Merrienboer B et al, Gülçehre Ç (2014) Learning phrase representations using RNN encoder-decoder for statistical bibmachine translation. In: Proceedings of the 2014 conference on empirical methods in natural language processing, EMNLP 2014, 25-29 October 2014, Doha, Qatar, A bibmeeting of SIGDAT, a special interest group of the ACL, pp 1724-1734

  5. Cui F, Di H, Shen L et al (2021) Modeling semantic and emotional relationship in multi-turn emotional conversations using multi-task learning. Appl Intell. https://doi.org/10.1007/s10489-021-02683-xhttps://doi.org/10.1007/s10489-021-02683-x

  6. Dinan E, Roller S, Shuster K et al (2019) Wizard of wikipedia: knowledge-powered conversational agents. In: 7th International conference on learning representations, ICLR 2019, New Orleans, USA, 6-9 May 2019. OpenReview.net

  7. Feng Y, Wang Y, Li H (2021) A sequence-to-sequence approach to dialogue state tracking. In: Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing, ACL/IJCNLP 2021, (vol 1: Long Papers), virtual event, 1-6 August 2021, pp 1714–1725

  8. Gao J, Galley M, Li L (2019) Neural approaches to conversational AI. Found Trends Inf Retr 13(2-3):127–298. https://doi.org/10.1561/1500000074

    Article  Google Scholar 

  9. Gao Y, Wu C, Joty S R et al (2020) Explicit bibmemory tracker with coarse-to-fine reasoning for conversational bibmachine reading. In: Proceedings of the 58th annual meeting of the association for computational linguistics, ACL 2020, Online, 5-10 July 2020, pp 935–945

  10. Ghazvininejad M, Brockett C, Chang M et al (2018) A knowledge-grounded neural conversation bibmodel. In: Proceedings of the thirty-second AAAI conference on artificial intelligence, (AAAI-18), the 30th innovative applications of artificial intelligence (IAAI-18), and the 8th AAAI symposium on educational advances in artificial intelligence (EAAI-18), New Orleans, Louisiana, USA, 2-7 February 2018, pp 5110–5117

  11. Huang M, Zhu X, Gao J (2020) Challenges in building intelligent open-domain dialog systems. ACM Trans Inf Syst 38(3):21:1–21:32. https://doi.org/10.1145/3383123

    Article  Google Scholar 

  12. Kim B, Ahn J, Kim G (2020) Sequential latent knowledge selection for knowledge-grounded dialogue. In: 8th International conference on learning representations, ICLR 2020, addis ababa, ethiopia, 26-30 April 2020

  13. Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: 3rd International conference on learning representations, ICLR 2015, San Diego, USA, 7-9 May 2015, conference track proceedings

  14. Lei W, Jin X, Kan MY et al (2018) Sequicity: simplifying task-oriented dialogue systems with single sequence-to-sequence architectures. In: Proceedings of the 56th annual meeting of the association for computational linguistics (vol 1: long papers), pp 1437–1447

  15. Li Y, Zhang R, Li W et al (2022) Hierarchical prediction and adversarial learning for conditional response generation. IEEE Trans Knowl Data Eng 34(1):314–327. https://doi.org/10.1109/TKDE.2020.2977637https://doi.org/10.1109/TKDE.2020.2977637

    Article  Google Scholar 

  16. Li Z, Zhang J, Fei Z et al (2021) Conversations are not flat: Modeling the dynamic information flow across dialogue utterances. In: Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing, ACL/IJCNLP 2021, (vol 1: long papers), virtual event, 1-6 August 2021, pp 128–138

  17. Lian R, Xie M, Wang F et al (2019) Learning to select knowledge for response generation in dialog systems. In: Proceedings of the twenty-eighth international joint conference on artificial intelligence, IJCAI 2019, Macao, China, 10-16 August 2019, pp 5081–5087

  18. Lin X, Jian W, He J et al (2020) Generating informative conversational response using recurrent knowledge-interaction and knowledge-copy. In: Proceedings of the 58th annual meeting of the association for computational linguistics, ACL 2020, Online, 5-10 July 2020, pp 41–52

  19. Ling Y, Cai F, Hu X et al (2021) Context-controlled topic-aware neural response generation for open-domain dialog systems. Inf Process Manag 58(1):102,392. https://doi.org/10.1016/j.ipm.2020.102392https://doi.org/10.1016/j.ipm.2020.102392

    Article  Google Scholar 

  20. Liu Z, Niu Z, Wu H et al (2019) Knowledge aware conversation generation with explainable reasoning over augmented graphs. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing, EMNLP-IJCNLP 2019, Hong Kong, China, 3-7 November 2019, pp 1782– 1792

  21. Meng C, Ren P, Chen Z et al (2020) Refnet: a reference-aware network for background based conversation. In: The thirty-fourth AAAI conference on artificial intelligence, AAAI 2020, the thirty-second innovative applications of artificial intelligence conference, IAAI 2020, the tenth AAAI symposium on educational advances in artificial intelligence, EAAI 2020, New York, 7-12 February 2020, pp 8496–8503

  22. Meng C, Ren P, Chen Z et al (2020) Dukenet: a dual knowledge interaction network for knowledge-grounded conversation. In: Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval, SIGIR 2020, virtual event, China, 25-30 July 2020, pp 1151–1160

  23. Meng C, Ren P, Chen Z et al (2021) Initiative-aware self-supervised learning for knowledge-grounded conversations. In: SIGIR ’21: The 44th international ACM SIGIR conference on research and development in information retrieval, virtual event, canada, 11-15 july 2021, pp 522–532

  24. Moghe N, Arora S, Banerjee S et al (2018) Towards exploiting background knowledge for building conversation systems. In: Proceedings of the 2018 conference on empirical methods in natural language processing, Brussels, Belgium, 31 October - 4 November 2018, pp 2322–2332

  25. Pennington J, Socher R, Manning C D (2014) Glove: global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing, EMNLP 2014, 25-29 October 2014, Doha, Qatar. A bibmeeting of SIGDAT, a special interest group of the ACL, pp 1532–1543

  26. Rajpurkar P, Zhang J, Lopyrev K et al (2016) Squad: 100, 000+ questions for bibmachine comprehension of text. In: Proceedings of the 2016 conference on empirical methods in natural language processing, EMNLP 2016, Austin, Texas, USA, 1-4 November 2016, pp 2383–2392

  27. Ren P, Chen Z, Monz C et al (2020) Thinking globally, acting locally: distantly supervised global-to-local knowledge selection for background based conversation. In: The thirty-fourth AAAI conference on artificial intelligence, AAAI 2020, the thirty-second innovative applications of artificial intelligence conference, IAAI 2020, the tenth AAAI symposium on educational advances in artificial intelligence, EAAI 2020, New York, 7-12 February 2020, pp 8697–8704

  28. Ren P, Chen Z, Ren Z et al (2021) Conversations with search engines: serp-based conversational response generation. ACM Trans Inf Syst 39(4):47. https://doi.org/10.1145/3432726

    Article  Google Scholar 

  29. See A, Liu PJ, Manning CD (2017) Get to the point: summarization with pointer-generator networks. In: Proceedings of the 55th annual meeting of the association for computational linguistics, ACL 2017, Vancouver, Canada, 30 July - 4 August, vol 1: long papers, pp 1073–1083

  30. Seo MJ, Kembhavi A, Farhadi A et al (2017) Bidirectional attention flow for machine comprehension. In: 5th International conference on learning representations, ICLR 2017, Toulon, France, 24-26 April 2017, conference track proceedings

  31. Serban IV, Sordoni A, Bengio Y et al (2016) Building end-to-end dialogue systems using generative hierarchical neural network models. In: Proceedings of the thirtieth AAAI conference on artificial intelligence, 12-17 February 2016, Phoenix, Arizona, USA, pp 3776–3784

  32. Shang L, Lu Z, Li H (2015) Neural responding bibmachine for short-text conversation. In: Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing of the asian federation of natural language processing, ACL 2015, 26-31 July 2015, Beijing, China, vol 1: long papers, pp 1577–1586

  33. Srivastava R K, Greff K, Schmidhuber J (2015) Training very deep networks. In: Advances in neural information processing systems 28: annual conference on neural information processing systems 2015, 7-12 December 2015, Montreal, Quebec Canada, pp 2377–2385

  34. Sun C, Lv L, Liu T et al (2021) A joint bibmodel based on interactive gate bibmechanism for spoken language understanding. Appl Intell. https://doi.org/10.1007/s10489-021-02544-7

  35. Sutskever I, Vinyals O, Le Q V (2014) Sequence to sequence learning with neural networks. In: Advances in neural information processing systems 27: annual conference on neural information processing systems 2014, 8-13 December 2014, Montreal, Quebec Canada, pp 3104–3112

  36. Tian J, Tu Z, Li N et al (2022) Intention bibmodel based bibmulti-round dialogue strategies for conversational ai bots. Appl Intell. https://doi.org/10.1007/s10489-022-03288-8

  37. Trippas J R, Spina D, Thomas P, et al. (2020) Towards a bibmodel for spoken conversational search. Inf Process Manag 57(2):102,162. https://doi.org/10.1016/j.ipm.2019.102162

    Article  Google Scholar 

  38. Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. In: Advances in neural information processing systems 30: annual conference on neural information processing systems 2017, 4-9 December 2017, Long Beach, USA, pp 5998–6008

  39. Wang M, Fu W, He X et al (2022) A survey on large-scale bibmachine learning. IEEE Trans Knowl Data Eng 34(6):2574–2594. https://doi.org/10.1109/TKDE.2020.3015777

    Google Scholar 

  40. Wang W, Yang N, Wei F et al (2017) Gated self-bibmatching networks for reading comprehension and question answering. In: Proceedings of the 55th annual meeting of the association for computational linguistics, ACL 2017, Vancouver, Canada, 30 July - 4 August, vol 1: long papers, pp 189–198

  41. Wen H, Ferritto A, Ji H et al (2021) VAULT: variable unified long text representation for bibmachine reading comprehension. In: Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing, ACL/IJCNLP 2021, (vol 2: short papers), virtual event, 1-6 August 2021, pp 1035– 1042

  42. Xu F, Xu G, Wang Y et al (2021) Diverse dialogue generation by fusing bibmutual persona-aware and self-transferrer. Appl Intell. https://doi.org/10.1007/s10489-021-02660-4

  43. Xu M, Zeng B, Yang H et al (2022) Combining dynamic local context focus and dependency cluster attention for aspect-level sentiment classification. Neurocomputing. https://doi.org/10.1016/j.neucom.2021.12.084https://doi.org/10.1016/j.neucom.2021.12.084

  44. Yang W, Garg S, Bai Q et al (2022) Smart-contract enabled decentralized knowledge fusion for blockchain-based conversation system. Expert Syst Appl 203:117,089. https://doi.org/10.1016/j.eswa.2022.117089https://doi.org/10.1016/j.eswa.2022.117089

    Article  Google Scholar 

  45. Yu AW, Dohan D, Luong M et al (2018) Qanet: combining local convolution with global self-attention for reading comprehension. In: 6th International conference on learning representations, ICLR 2018, Vancouver, BC, Canada, 30 April - 3 May 2018. Conference track proceedings

  46. Zeng B, Zeng F, Han X et al (2022) Aspect extraction bibmodel based on interactive feature representation. J Comput Res Development 58(1):224–232. https://doi.org/10.7544/issn1000-1239.2021.20190305https://doi.org/10.7544/issn1000-1239.2021.20190305

    Google Scholar 

  47. Zhang H, Lan Y, Pang L et al (2019) Recosa: detecting the relevant contexts with self-attention for bibmulti-turn dialogue generation. In: Proceedings of the 57th conference of the association for computational linguistics, ACL 2019, Florence, Italy, 28 July - 2 August 2019, vol 1: long papers, pp 3721–3730

  48. Zhang W, Cui Y, Wang Y et al (2018) Context-sensitive generation of open-domain conversational responses. In: Proceedings of the 27th international conference on computational linguistics, pp 2437–2447

  49. Zhang X, Zhao X, Tan T (2021) Robust dialog state tracker with contextual-feature augmentation. Appl Intell 51(4):2377–2392. https://doi.org/10.1007/s10489-020-01991-y

    Article  Google Scholar 

  50. Zhang Y, Ren P, De Rijke M (2019) Improving background based conversation with context-aware knowledge pre-selection. In: 4th International workshop on search-oriented conversational AI, SCAI

  51. Zheng C, Cao Y, Jiang D et al (2020) Difference-aware knowledge selection for knowledge-grounded conversation generation. In: Findings of the association for computational linguistics: EMNLP 2020, pp 115–125

  52. Zhong P, Wang D, Li P et al (2021) CARE: commonsense-aware emotional response generation with latent concepts. In: Thirty-Fifth AAAI conference on artificial intelligence, AAAI 2021, thirty-third conference on innovative applications of artificial intelligence, IAAI 2021, the eleventh symposium on educational advances in artificial intelligence, EAAI 2021, virtual event, 2-9 February 2021, pp 14,577–14,585

  53. Zhou H, Young T, Huang M et al (2018) Commonsense knowledge aware conversation generation with graph attention. In: Proceedings of the twenty-seventh international joint conference on artificial intelligence, IJCAI 2018, 13-19 July 2018. Stockholm, Sweden, pp 4623–4629

  54. Zhou K, Prabhumoye S, Black AW (2018) A dataset for document grounded conversations. In: Proceedings of the 2018 conference on empirical methods in natural language processing, Brussels, Belgium, 31 October - 4 November 2018, pp 708–713

Download references

Acknowledgements

We thank the editor and all the anonymous reviewers for reviewing this paper. This work is supported by National Natural Science Foundation of China (No. 62076103), in part by the Guangdong Basic and Applied Basic Research Fund (No. 2021A1515011171) and the Guangdong General Colleges and University Special Projects in Key Areas of Artificial Intelligence of China (No. 2019KZDZX1033).

Author information

Authors and Affiliations

  1. School of Software, South China Normal University, Nanhai, Foshan, 528225, Guangdong, China

    Jiatao Chen, Biqing Zeng, Zhibin Du, Mayi Xu, Zibang Gan & Meirong Ding

  2. School of Computer Science, Guangdong AIB Polytechnic, Tianhe, Guangzhou, 510630, Guangdong, China

    Huimin Deng

Authors
  1. Jiatao Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Biqing Zeng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhibin Du
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Huimin Deng
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mayi Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Zibang Gan
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Meirong Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Biqing Zeng.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted bibmanuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, J., Zeng, B., Du, Z. et al. RFM: response-aware feedback mechanism for background based conversation. Appl Intell 53, 10858–10878 (2023). https://doi.org/10.1007/s10489-022-04056-4

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-04056-4

Keywords

Search

Navigation