2000 character limit reached
Graph vs. Sequence: An Empirical Study on Knowledge Forms for Knowledge-Grounded Dialogue (2312.07868v1)
Published 13 Dec 2023 in cs.CL
Abstract: Knowledge-grounded dialogue is a task of generating an informative response based on both the dialogue history and external knowledge source. In general, there are two forms of knowledge: manually annotated knowledge graphs and knowledge text from website. From various evaluation viewpoints, each type of knowledge has advantages and downsides. To further distinguish the principles and determinants from the intricate factors, we conduct a thorough experiment and study on the task to answer three essential questions. The questions involve the choice of appropriate knowledge form, the degree of mutual effects between knowledge and the model selection, and the few-shot performance of knowledge. Supported by statistical shreds of evidence, we offer conclusive solutions and sensible suggestions for directions and standards of future research.
- Easy access to the freebase dataset. In Proceedings of the 23rd International Conference on World Wide Web, pages 95–98.
- Knowledge-aware zero-shot learning: Survey and perspective. In the 30th International Joint Conference on Artificial Intelligence.
- KGPT: Knowledge-grounded pre-training for data-to-text generation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8635–8648, Online. Association for Computational Linguistics.
- Knowledge-enhanced neural machine reasoning: A review. arXiv preprint arXiv:2302.02093.
- Wizard of Wikipedia: Knowledge-powered conversational agents. In Proceedings of the International Conference on Learning Representations (ICLR).
- Faithdial: A faithful benchmark for information-seeking dialogue. arXiv preprint, arXiv:2204.10757.
- On the origin of hallucinations in conversational models: Is it the datasets or the models? In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5271–5285, Seattle, United States. Association for Computational Linguistics.
- A knowledge-grounded neural conversation model. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32.
- Training compute-optimal large language models. CoRR, abs/2203.15556.
- 𝒒𝟐superscript𝒒2q^{2}bold_italic_q start_POSTSUPERSCRIPT bold_2 end_POSTSUPERSCRIPT: Evaluating factual consistency in knowledge-grounded dialogues via question generation and question answering. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7856–7870, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
- Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461.
- A diversity-promoting objective function for neural conversation models. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 110–119, San Diego, California. Association for Computational Linguistics.
- Zero-resource knowledge-grounded dialogue generation. Advances in Neural Information Processing Systems, 33:8475–8485.
- Towards deep conversational recommendations. Advances in neural information processing systems, 31.
- Knowledge-grounded dialogue generation with a unified knowledge representation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 206–218, Seattle, United States. Association for Computational Linguistics.
- Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out, pages 74–81.
- A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2262–2272, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- DuRecDial 2.0: A bilingual parallel corpus for conversational recommendation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4335–4347, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Augmented language models: a survey. arXiv preprint arXiv:2302.07842.
- Opendialkg: Explainable conversational reasoning with attention-based walks over knowledge graphs. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.
- Training language models to follow instructions with human feedback. arXiv preprint arXiv:2203.02155.
- Unifying large language models and knowledge graphs: A roadmap. arXiv preprint arXiv:2306.08302.
- Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318.
- 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, pages 2523–2544, Online. Association for Computational Linguistics.
- Focused attention improves document grounded generation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics. Association for Computational Linguistics.
- Language models are unsupervised multitask learners.
- Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(140):1–67.
- Increasing faithfulness in knowledge-grounded dialogue with controllable features. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 704–718, Online. Association for Computational Linguistics.
- Attention is all you need. Advances in neural information processing systems, 30.
- Graph attention networks. In International Conference on Learning Representations.
- RecInDial: A unified framework for conversational recommendation with pretrained language models. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 489–500, Online only. Association for Computational Linguistics.
- Huggingface’s transformers: State-of-the-art natural language processing. arXiv preprint arXiv:1910.03771.
- 𝒈𝟐superscript𝒈2g^{2}bold_italic_g start_POSTSUPERSCRIPT bold_2 end_POSTSUPERSCRIPT: Enhance knowledge grounded dialogue via ground graph. arXiv preprint arXiv:2204.12681.
- A survey of knowledge-enhanced text generation. ACM Computing Surveys, 54(11s):1–38.
- Low-resource knowledge-grounded dialogue generation. arXiv preprint arXiv:2002.10348.
- Knowledge-grounded dialogue generation with pre-trained language models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3377–3390, Online. Association for Computational Linguistics.
- A dataset for document grounded conversations. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.