Skip to main content
Springer Nature Link
Log in

Read Then Respond: Multi-granularity Grounding Prediction for Knowledge-Grounded Dialogue Generation

  • Conference paper
  • First Online:
Advanced Data Mining and Applications (ADMA 2023)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 14177))

Included in the following conference series:

  • 981 Accesses

Abstract

Retrieval-augmented generative models have shown promising results in knowledge-grounding dialogue systems. However, identifying and utilizing exact knowledge from multiple passages based on dialogue context remains challenging due to the semantic dependency of the dialogue context. Existing research has observed that increasing the number of retrieved passages promotes the recall of relevant knowledge, but the performance of response generation improvement becomes marginal or even worse when the number reaches a certain threshold. In this paper, we present a multi-grained knowledge grounding identification method, in which the coarse-grained selects the most relevant knowledge from each retrieval passage separately, and the fine-grained refines the coarse-grained and identifies final knowledge as grounding in generation stage. To further guide the response generation with predicted grounding, we introduce a grounding-augmented copy mechanism in the decoding stage of dialogue generation. Empirical results on MultiDoc2Dial and WoW benchmarks show that our method outperforms state-of-the-art methods.

Y. Du and S. Zhang—Equal contribution.

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

Access this chapter

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

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    https://eval.ai/web/challenges/challenge-page/689/leaderboard/1909.

References

  1. Adolphs, L., Shuster, K., Urbanek, J., Szlam, A., Weston, J.: Reason first, then respond: Modular generation for knowledge-infused dialogue. arXiv preprint arXiv:2111.05204 (2021)

  2. Asai, A., Gardner, M., Hajishirzi, H.: Evidentiality-guided generation for knowledge-intensive NLP tasks. arXiv preprint arXiv:2112.08688 (2021)

  3. Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877–1901 (2020)

    Google Scholar 

  4. Chen, X., et al.: Bridging the gap between prior and posterior knowledge selection for knowledge-grounded dialogue generation. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3426–3437 (2020)

    Google Scholar 

  5. Davison, J., Feldman, J., Rush, A.M.: Commonsense knowledge mining from pretrained models. 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), pp. 1173–1178 (2019)

    Google Scholar 

  6. Dinan, E., Roller, S., Shuster, K., Fan, A., Auli, M., Weston, J.: Wizard of Wikipedia: Knowledge-powered conversational agents. arXiv preprint arXiv:1811.01241 (2018)

  7. Fajcik, M., Docekal, M., Ondrej, K., Smrz, P.: R2–d2: a modular baseline for open-domain question answering. arXiv preprint arXiv:2109.03502 (2021)

  8. Feng, S., Patel, S.S., Wan, H., Joshi, S.: MultiDoc2Dial: modeling dialogues grounded in multiple documents. In: EMNLP (2021)

    Google Scholar 

  9. Glass, M., Rossiello, G., Chowdhury, M.F.M., Naik, A., Cai, P., Gliozzo, A.: Re2G: retrieve, rerank, generate. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 2701–2715. Association for Computational Linguistics, Seattle, United States, July 2022. https://aclanthology.org/2022.naacl-main.194

  10. Holtzman, A., Buys, J., Du, L., Forbes, M., Choi, Y.: The curious case of neural text degeneration. arXiv preprint arXiv:1904.09751 (2019)

  11. Izacard, G., Grave, E.: Leveraging passage retrieval with generative models for open domain question answering. arXiv preprint arXiv:2007.01282 (2020)

  12. Jones, K.S.: A statistical interpretation of term specificity and its application in retrieval. J. Doc. 28, 1–11 (1972)

    Google Scholar 

  13. Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020)

  14. Lewis, M., et al.: Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)

  15. Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv. Neural. Inf. Process. Syst. 33, 9459–9474 (2020)

    Google Scholar 

  16. Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74–81 (2004)

    Google Scholar 

  17. Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)

    Google Scholar 

  18. Ma, Y., Nguyen, K.L., Xing, F.Z., Cambria, E.: A survey on empathetic dialogue systems. Inf. Fusion 64, 50–70 (2020)

    Article  Google Scholar 

  19. Paranjape, A., Khattab, O., Potts, C., Zaharia, M., Manning, C.D.: Hindsight: posterior-guided training of retrievers for improved open-ended generation. arXiv preprint arXiv:2110.07752 (2021)

  20. Petroni, F., et al.: Kilt: a benchmark for knowledge intensive language tasks. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 2523–2544 (2021)

    Google Scholar 

  21. Prabhumoye, S., Hashimoto, K., Zhou, Y., Black, A.W., Salakhutdinov, R.: Focused attention improves document-grounded generation. arXiv preprint arXiv:2104.12714 (2021)

  22. Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683 (2019)

  23. Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: Squad: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016)

  24. Rashkin, H., Reitter, D., Tomar, G.S., Das, D.: Increasing faithfulness in knowledge-grounded dialogue with controllable features. arXiv preprint arXiv:2107.06963 (2021)

  25. Reimers, N., Gurevych, I.: The curse of dense low-dimensional information retrieval for large index sizes. arXiv preprint arXiv:2012.14210 (2020)

  26. Robertson, S.E., Walker, S., Jones, S., Hancock-Beaulieu, M.M., Gatford, M., et al.: Okapi at TREC-3. NIST Spec. Publ. SP 109, 109 (1995)

    Google Scholar 

  27. Shuster, K., Poff, S., Chen, M., Kiela, D., Weston, J.: Retrieval augmentation reduces hallucination in conversation. arXiv preprint arXiv:2104.07567 (2021)

  28. Singh, D., Reddy, S., Hamilton, W., Dyer, C., Yogatama, D.: End-to-end training of multi-document reader and retriever for open-domain question answering. In: Advances in Neural Information Processing Systems, vol. 34 (2021)

    Google Scholar 

  29. Wu, Z., Lu, B.R., Hajishirzi, H., Ostendorf, M.: DIALKI: Knowledge identification in conversational systems through dialogue-document contextualization. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 1852–1863. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, November 2021. https://doi.org/10.18653/v1/2021.emnlp-main.140, https://aclanthology.org/2021.emnlp-main.140

  30. Xiong, L., et al.: Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808 (2020)

  31. Zhan, H., Zhang, H., Chen, H., Ding, Z., Bao, Y., Lan, Y.: Augmenting knowledge-grounded conversations with sequential knowledge transition. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 5621–5630 (2021)

    Google Scholar 

  32. Zhang, S., Du, Y., Liu, G., Yan, Z., Cao, Y.: G4: Grounding-guided goal-oriented dialogues generation with multiple documents. In: Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pp. 108–114. Association for Computational Linguistics, Dublin, Ireland, May 2022. https://doi.org/10.18653/v1/2022.dialdoc-1.11, https://aclanthology.org/2022.dialdoc-1.11

  33. Zhu, W., Mo, K., Zhang, Y., Zhu, Z., Peng, X., Yang, Q.: Flexible end-to-end dialogue system for knowledge grounded conversation. arXiv preprint arXiv:1709.04264 (2017)

Download references

Author information

Authors and Affiliations

  1. State Key Lab of Software Development Environment, Beihang University, Beijing, China

    Yiyang Du, Xianjie Wu & Zhoujun Li

  2. Baidu Inc., Beijing, China

    Shiwei Zhang

  3. Tencent Cloud Xiaowei, Beijing, China

    Zhao Yan & Yunbo Cao

Authors
  1. Yiyang Du
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shiwei Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xianjie Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhao Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yunbo Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Zhoujun Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yiyang Du .

Editor information

Editors and Affiliations

  1. Northeastern University, Shenyang, China

    Xiaochun Yang

  2. The University of Indonesia, Depok, Indonesia

    Heru Suhartanto

  3. Beijing Institute of Technology, Beijing, China

    Guoren Wang

  4. Northeastern University, Shenyang, China

    Bin Wang

  5. University of Technology Sydney, Sydney, NSW, Australia

    Jing Jiang

  6. Agency for Science, Technology and Research (A*STAR), Singapore, Singapore

    Bing Li

  7. Sun Yat-sen University, Guangzhou, China

    Huaijie Zhu

  8. Anhui University, Hefei, China

    Ningning Cui

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Du, Y., Zhang, S., Wu, X., Yan, Z., Cao, Y., Li, Z. (2023). Read Then Respond: Multi-granularity Grounding Prediction for Knowledge-Grounded Dialogue Generation. In: Yang, X., et al. Advanced Data Mining and Applications. ADMA 2023. Lecture Notes in Computer Science(), vol 14177. Springer, Cham. https://doi.org/10.1007/978-3-031-46664-9_20

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-46664-9_20

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-46663-2

  • Online ISBN: 978-3-031-46664-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics