Elamur Research⌕
☰
home / papers / 2023 / Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation

Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation

Paper · 2023 · Minki Kang, Jin Myung Kwak, Jinheon Baek et al.

Summary

Pre-trained language models write fluent dialogue replies but often state wrong facts. Earlier KG-grounded systems feed the model every triplet linked to entities in the conversation, although most are irrelevant to the current turn. This wastes computation and invites errors. The authors present SURGE (SUbgraph Retrieval-augmented GEneration), an end-to-end pipeline with three parts:

  • Retriever: a GNN-based component scores triplets against the dialogue context and keeps a small relevant subgraph. It is trained jointly with the generator by treating the subgraph as a latent variable, so no relevance labels are needed.
  • Graph encoding: a compact encoding, invariant to triplet order and relation direction, perturbs the PLM's token embeddings instead of prepending long fact sequences.
  • Contrastive loss: a graph-text objective pushes responses to agree with the retrieved facts.

On OpendialKG and KOMODIS, SURGE beats all non-oracle baselines on generation quality, retrieval, and a new knowledge-checking metric, KQA. The work shows that picking the right facts, rather than supplying more of them, is what makes dialogue more factual.

Key points

  • On OpendialKG, about 87% of 1-hop KG facts (only 12.6% useful) are irrelevant to the target response, which motivates subgraph retrieval.
  • KQA (Knowledge-verifying Question Answering) uses extractive QA to test whether generated replies contain the correct knowledge. It correlates with human informativeness ratings (Pearson 0.42).
  • SURGE outperforms baselines that receive all k-hop facts, including All Knowledge, Space Efficient Encoding, EARL, and DiffKG, on BLEU, ROUGE, F1, and KQA. It also has the best Knowledge F1.
  • Retrieval was evaluated with MRR and Hits@k on the 45% of test dialogues that contain gold knowledge. The semi-supervised, contrastive variant was the strongest.
  • In the human study, 46 annotators rated 30 sampled responses on a 3-point scale. SURGE scored highest on consistency, informativeness, and fluency.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Korea Advanced Institute of Science and TechnologyDaejeon · South Korea51 works · 3,167 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Vision and Pattern Recognition · 2,869 works

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 3,320 worksDialogue systems · 624 works

Cite

Cite as Minki Kang, Jin Myung Kwak, Jinheon Baek and Sung Ju Hwang. 2023. Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation. arXiv:2305.18846.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2305.18846 · arXiv 2305.18846

@misc{kang2023knowledge,
  title = {{Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation}},
  author = {Minki Kang, Jin Myung Kwak, Jinheon Baek and Sung Ju Hwang},
  year = {2023},
  doi = {10.48550/arxiv.2305.18846},
  eprint = {2305.18846},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2305.18846}
}

References

51 references, 30 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Daniel Adiwardana, Minh-Thang Luong, David R. So, Jamie Hall, Noah Fiedel, Romal Thoppilan, Zi Yang, Apoorv Kulshreshtha, Gaurav Nemade, Yifeng Lu, and Quoc V. Le. Towards a human-like open-domain chatbot. CoRR, abs/2001.09977, 2020.
  2. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. Neural machine translation by jointly learning to align and translate. In Yoshua Bengio and Yann LeCun, editors, 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, 2…
  3. Kurt D. Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. Freebase: a collaboratively created graph database for structuring human knowledge. In Proceedings of the ACM SIGMOD International Conference on Management of Data, SIGMOD 2008, Vancouver, BC, Canada, June 10-12, 2008, p… find
  4. Fuwei Cui, Hui Di, Hongjie Ren, Kazushige Ouchi, Ze Liu, and Jinan Xu. Syntactically diverse adversarial network for knowledge-grounded conversation generation. In Marie-Francine Moens, Xuanjing Huang, Lucia Specia, and Scott Wen-tau Yih, editors, Findings of the Association for Computational Lingui… find
  5. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. BERT: pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL…
  6. Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, and Jason Weston. Wizard of wikipedia: Knowledge-powered conversational agents. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net, 2019.
  7. Fabian Galetzka, Chukwuemeka Uchenna Eneh, and David Schlangen. A corpus of controlled opinionated and knowledgeable movie discussions for training neural conversation models. In Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, H… find
  8. Fabian Galetzka, Jewgeni Rose, David Schlangen, and Jens Lehmann. Space efficient context encoding for non-task-oriented dialogue generation with graph attention transformer. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint C… find
  9. Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Ming-Wei Chang. Retrieval augmented language model pre-training. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event, volume 119 of Proceedings of Machine Learning Research, pages…
  10. William L. Hamilton. Graph representation learning. Synthesis Lectures on Artificial Intelligence and Machine Learning, 14(3):1–159, 2020. find
  11. Ehsan Hosseini-Asl, Bryan McCann, Chien-Sheng Wu, Semih Yavuz, and Richard Socher. A simple language model for task-oriented dialogue. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual,…
  12. Samuel Humeau, Kurt Shuster, Marie-Anne Lachaux, and Jason Weston. Poly-encoders: Architectures and pre-training strategies for fast and accurate multi-sentence scoring. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net,… find
  13. Jaehyeong Jo, Jinheon Baek, Seul Lee, Dongki Kim, Minki Kang, and Sung Ju Hwang. Edge representation learning with hypergraphs. CoRR, abs/2106.15845, 2021. — [arXiv:2106.15845](https://arxiv.org/abs/2106.15845) find
  14. Thomas N. Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net, 2017.
  15. Mojtaba Komeili, Kurt Shuster, and Jason Weston. Internet-augmented dialogue generation. CoRR, abs/2107.07566, 2021.
  16. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joe…
  17. Patrick S. H. Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. Retrieval-augmented generation for knowledge-intensive NLP tasks. In Hugo Larochelle, Marc’Aurelio Ranza…
  18. Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. A diversity-promoting objective function for neural conversation models. In Kevin Knight, Ani Nenkova, and Owen Rambow, editors, NAACL HLT 2016, The 2016 Conference of the North American Chapter of the Association for Computation…
  19. Yu Li, Baolin Peng, Yelong Shen, Yi Mao, Lars Liden, Zhou Yu, and Jianfeng Gao. Knowledge-grounded dialogue generation with a unified knowledge representation. In Marine Carpuat, Marie-Catherine de Marneffe, and Iván Vladimir Meza Ruíz, editors, Proceedings of the 2022 Conference of the North Americ… find
  20. Chin-Yew Lin. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74–81, Barcelona, Spain, July 2004. Association for Computational Linguistics. URL https://aclanthology.org/W04-1013. ↗
  21. Ilya Loshchilov and Frank Hutter. Decoupled weight decay regularization. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019, 2019. URL https://openreview.net/forum?id=Bkg6RiCqY7. ↗
  22. Kaixin Ma, Hao Cheng, Xiaodong Liu, Eric Nyberg, and Jianfeng Gao. Open domain question answering with A unified knowledge interface. In Smaranda Muresan, Preslav Nakov, and Aline Villavicencio, editors, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume… find
  23. Joshua Maynez, Shashi Narayan, Bernd Bohnet, and Ryan T. McDonald. On faithfulness and factuality in abstractive summarization. In Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joel R. Tetreault, editors, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL…
  24. Seungwhan Moon, Pararth Shah, Anuj Kumar, and Rajen Subba. Opendialkg: Explainable conversational reasoning with attention-based walks over knowledge graphs. In Anna Korhonen, David R. Traum, and Lluís Màrquez, editors, Proceedings of the 57th Conference of the Association for Computational Linguist…
  25. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, July 6-12, 2002, Philadelphia, PA, USA, pages 311–318. ACL, 2002.
  26. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and S… — PyTorch: An Imperative Style, High-Performance Deep Learning Library
  27. Ethan Perez, Florian Strub, Harm de Vries, Vincent Dumoulin, and Aaron C. Courville. Film: Visual reasoning with a general conditioning layer. In Sheila A. McIlraith and Kilian Q. Weinberger, editors, Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th in…
  28. Fabio Petroni, Tim Rocktäschel, Sebastian Riedel, Patrick S. H. Lewis, Anton Bakhtin, Yuxiang Wu, and Alexander H. Miller. Language models as knowledge bases? In Kentaro Inui, Jing Jiang, Vincent Ng, and Xiaojun Wan, editors, Proceedings of the 2019 Conference on Empirical Methods in Natural Languag…
  29. Alec Radford, Jeff Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019. find
  30. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 21:140:1–140:67, 2020.
  31. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. Squad: 100, 000+ questions for machine comprehension of text. In Jian Su, Xavier Carreras, and Kevin Duh, editors, Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016, Austin, Texas, USA…
  32. Marc’Aurelio Ranzato, Sumit Chopra, Michael Auli, and Wojciech Zaremba. Sequence level training with recurrent neural networks. In Yoshua Bengio and Yann LeCun, editors, 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Procee…
  33. Stephen Robertson and Hugo Zaragoza. The probabilistic relevance framework: BM25 and beyond. Found. Trends Inf. Retr., 3(4):333–389, 2009. find
  34. Anna Rohrbach, Lisa Anne Hendricks, Kaylee Burns, Trevor Darrell, and Kate Saenko. Object hallucination in image captioning. In Ellen Riloff, David Chiang, Julia Hockenmaier, and Jun’ichi Tsujii, editors, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussel…
  35. Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Eric Michael Smith, Y-Lan Boureau, and Jason Weston. Recipes for building an open-domain chatbot. In Paola Merlo, Jörg Tiedemann, and Reut Tsarfaty, editors, Proceedings of the 16th Conference of the Eur…
  36. Md. Rashad Al Hasan Rony, Ricardo Usbeck, and Jens Lehmann. Dialokg: Knowledge-structure aware task-oriented dialogue generation. In Marine Carpuat, Marie-Catherine de Marneffe, and Iván Vladimir Meza Ruíz, editors, Findings of the Association for Computational Linguistics: NAACL 2022, Seattle, WA,… find
  37. Rico Sennrich, Barry Haddow, and Alexandra Birch. Neural machine translation of rare words with subword units. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, August 7-12, 2016, Berlin, Germany, Volume 1: Long Papers. The Association for Computer…
  38. Kurt Shuster, Spencer Poff, Moya Chen, Douwe Kiela, and Jason Weston. Retrieval augmentation reduces hallucination in conversation. In Marie-Francine Moens, Xuanjing Huang, Lucia Specia, and Scott Wen-tau Yih, editors, Findings of the Association for Computational Linguistics: EMNLP 2021, Virtual Ev…
  39. Yi-Lin Tuan, Yun-Nung Chen, and Hung-yi Lee. Dykgchat: Benchmarking dialogue generation grounding on dynamic knowledge 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-IJ… find
  40. Yi-Lin Tuan, Sajjad Beygi, Maryam Fazel-Zarandi, Qiaozi Gao, Alessandra Cervone, and William Yang Wang. Towards large-scale interpretable knowledge graph reasoning for dialogue systems. In Smaranda Muresan, Preslav Nakov, and Aline Villavicencio, editors, Findings of the Association for Computationa… find
  41. Laurens van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of Machine Learning Research, 9(86):2579–2605, 2008. URL http://jmlr.org/papers/v9/ vandermaaten08a.html. ↗
  42. Shikhar Vashishth, Soumya Sanyal, Vikram Nitin, and Partha P. Talukdar. Composition-based multi-relational graph convolutional networks. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net, 2020. find
  43. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett, editors, Advances in Ne…
  44. Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. Graph attention networks. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net, 2018. find
  45. Denny Vrandecic and Markus Krötzsch. Wikidata: a free collaborative knowledgebase. Commun. ACM, 57(10):78–85, 2014.
  46. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoe… — Transformers: State-of-the-Art Natural Language Processing
  47. Sixing Wu, Ying Li, Dawei Zhang, Yang Zhou, and Zhonghai Wu. Diverse and informative dialogue generation with context-specific commonsense knowledge awareness. In Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joel R. Tetreault, editors, Proceedings of the 58th Annual Meeting of the Association for… find
  48. Manzil Zaheer, Satwik Kottur, Siamak Ravanbakhsh, Barnabás Póczos, Ruslan Salakhutdinov, and Alexander J. Smola. Deep sets. In Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett, editors, Advances in Neural Information Processing S… find
  49. Houyu Zhang, Zhenghao Liu, Chenyan Xiong, and Zhiyuan Liu. Grounded conversation generation as guided traverses in commonsense knowledge graphs. In Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joel R. Tetreault, editors, Proceedings of the 58th Annual Meeting of the Association for Computational…
  50. Yizhe Zhang, Siqi Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, and Bill Dolan. Dialogpt: Large-scale generative pre-training for conversational response generation. In ACL, system demonstration, 2020.
  51. Hao Zhou, Minlie Huang, Yong Liu, Wei Chen, and Xiaoyan Zhu. EARL: informative knowledge-grounded conversation generation with entity-agnostic representation learning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, D… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/kang-2023-knowledge-graph-augmented-language-models/