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
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
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)
Asai, A., Gardner, M., Hajishirzi, H.: Evidentiality-guided generation for knowledge-intensive NLP tasks. arXiv preprint arXiv:2112.08688 (2021)
Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877–1901 (2020)
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)
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)
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)
Fajcik, M., Docekal, M., Ondrej, K., Smrz, P.: R2–d2: a modular baseline for open-domain question answering. arXiv preprint arXiv:2109.03502 (2021)
Feng, S., Patel, S.S., Wan, H., Joshi, S.: MultiDoc2Dial: modeling dialogues grounded in multiple documents. In: EMNLP (2021)
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
Holtzman, A., Buys, J., Du, L., Forbes, M., Choi, Y.: The curious case of neural text degeneration. arXiv preprint arXiv:1904.09751 (2019)
Izacard, G., Grave, E.: Leveraging passage retrieval with generative models for open domain question answering. arXiv preprint arXiv:2007.01282 (2020)
Jones, K.S.: A statistical interpretation of term specificity and its application in retrieval. J. Doc. 28, 1–11 (1972)
Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020)
Lewis, M., et al.: Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)
Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv. Neural. Inf. Process. Syst. 33, 9459–9474 (2020)
Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74–81 (2004)
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)
Ma, Y., Nguyen, K.L., Xing, F.Z., Cambria, E.: A survey on empathetic dialogue systems. Inf. Fusion 64, 50–70 (2020)
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)
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)
Prabhumoye, S., Hashimoto, K., Zhou, Y., Black, A.W., Salakhutdinov, R.: Focused attention improves document-grounded generation. arXiv preprint arXiv:2104.12714 (2021)
Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683 (2019)
Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: Squad: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016)
Rashkin, H., Reitter, D., Tomar, G.S., Das, D.: Increasing faithfulness in knowledge-grounded dialogue with controllable features. arXiv preprint arXiv:2107.06963 (2021)
Reimers, N., Gurevych, I.: The curse of dense low-dimensional information retrieval for large index sizes. arXiv preprint arXiv:2012.14210 (2020)
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)
Shuster, K., Poff, S., Chen, M., Kiela, D., Weston, J.: Retrieval augmentation reduces hallucination in conversation. arXiv preprint arXiv:2104.07567 (2021)
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)
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
Xiong, L., et al.: Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808 (2020)
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)
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
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)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
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)