Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
38 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Enhancing Knowledge Retrieval with Topic Modeling for Knowledge-Grounded Dialogue (2405.04713v1)

Published 7 May 2024 in cs.IR

Abstract: Knowledge retrieval is one of the major challenges in building a knowledge-grounded dialogue system. A common method is to use a neural retriever with a distributed approximate nearest-neighbor database to quickly find the relevant knowledge sentences. In this work, we propose an approach that utilizes topic modeling on the knowledge base to further improve retrieval accuracy and as a result, improve response generation. Additionally, we experiment with a LLM, ChatGPT, to take advantage of the improved retrieval performance to further improve the generation results. Experimental results on two datasets show that our approach can increase retrieval and generation performance. The results also indicate that ChatGPT is a better response generator for knowledge-grounded dialogue when relevant knowledge is provided.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (27)
  1. Pre-training is a hot topic: Contextualized document embeddings improve topic coherence. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 759–766, Online. Association for Computational Linguistics.
  2. 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, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics.
  3. Wizard of Wikipedia: Knowledge-powered conversational agents. In Proceedings of the International Conference on Learning Representations (ICLR).
  4. Coherence-aware neural topic modeling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 830–836, Brussels, Belgium. Association for Computational Linguistics.
  5. Injecting knowledge into language generation: a case study in auto-charting after-visit care instructions from medical dialogue. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023, pages 2373–2390. Association for Computational Linguistics.
  6. MultiDoc2Dial: Modeling dialogues grounded in multiple documents. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6162–6176, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  7. Language-agnostic transformers and assessing ChatGPT-based query rewriting for multilingual document-grounded QA. In Proceedings of the Third DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pages 101–108, Toronto, Canada. Association for Computational Linguistics.
  8. Benjamin Heinzerling and Kentaro Inui. 2021. Language models as knowledge bases: On entity representations, storage capacity, and paraphrased queries. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1772–1791, Online. Association for Computational Linguistics.
  9. Billion-scale similarity search with gpus. IEEE Transactions on Big Data, 7(3):535–547.
  10. Dense passage retrieval for open-domain question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6769–6781, Online. Association for Computational Linguistics.
  11. A systematic study and comprehensive evaluation of ChatGPT on benchmark datasets. In Findings of the Association for Computational Linguistics: ACL 2023, pages 431–469, Toronto, Canada. Association for Computational Linguistics.
  12. BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7871–7880, Online. Association for Computational Linguistics.
  13. Retrieval-augmented generation for knowledge-intensive nlp tasks. In Advances in Neural Information Processing Systems, volume 33, pages 9459–9474. Curran Associates, Inc.
  14. 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.
  15. OpenAI. 2022. Chatgpt blog post.
  16. 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.
  17. Language models as knowledge bases? 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), pages 2463–2473, Hong Kong, China. Association for Computational Linguistics.
  18. Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics.
  19. How much knowledge can you pack into the parameters of a language model? In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5418–5426, Online. Association for Computational Linguistics.
  20. Stephen Robertson and Hugo Zaragoza. 2009. The probabilistic relevance framework: Bm25 and beyond. Found. Trends Inf. Retr., 3(4):333–389.
  21. AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4222–4235, Online. Association for Computational Linguistics.
  22. Akash Srivastava and Charles Sutton. 2017. Autoencoding variational inference for topic models. In International Conference on Learning Representations.
  23. Nhat Tran and Diane Litman. 2022. Getting better dialogue context for knowledge identification by leveraging document-level topic shift. In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 368–375, Edinburgh, UK. Association for Computational Linguistics.
  24. Section-aware commonsense knowledge-grounded dialogue generation with pre-trained language model. In Proceedings of the 29th International Conference on Computational Linguistics, pages 521–531, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
  25. Approximate nearest neighbor negative contrastive learning for dense text retrieval. In International Conference on Learning Representations.
  26. Retrieval-free knowledge-grounded dialogue response generation with adapters. In Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pages 93–107, Dublin, Ireland. Association for Computational Linguistics.
  27. There is no standard answer: Knowledge-grounded dialogue generation with adversarial activated multi-reference learning. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 1878–1891, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Nhat Tran (5 papers)
  2. Diane Litman (49 papers)
Citations (1)
View on Semantic Scholar