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

AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment (2407.01965v2)

Published 2 Jul 2024 in cs.CL and cs.IR

Abstract: Conversational Query Reformulation (CQR) has significantly advanced in addressing the challenges of conversational search, particularly those stemming from the latent user intent and the need for historical context. Recent works aimed to boost the performance of CRQ through alignment. However, they are designed for one specific retrieval system, which potentially results in poor generalization. To overcome this limitation, we present a novel framework AdaCQR. By aligning reformulation models with both term-based and semantic-based retrieval systems, AdaCQR enhances the generalizability of information-seeking queries across diverse retrieval environments through a dual-phase training strategy. We also developed two effective approaches for acquiring superior labels and diverse input candidates, boosting the efficiency and robustness of the framework. Experimental evaluations on the TopiOCQA and QReCC datasets demonstrate that AdaCQR significantly outperforms existing methods, offering both quantitative and qualitative improvements in conversational query reformulation.

PDF 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 (50)
  1. TopiOCQA: Open-domain conversational question answering with topic switching. Transactions of the Association for Computational Linguistics, 10:468–483.
  2. Open-domain question answering goes conversational via question rewriting. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 520–534, Online. Association for Computational Linguistics.
  3. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  4. Generalizing conversational dense retrieval via llm-cognition data augmentation. arXiv preprint arXiv:2402.07092.
  5. Interpreting conversational dense retrieval by rewriting-enhanced inversion of session embedding. arXiv preprint arXiv:2402.12774.
  6. Reciprocal rank fusion outperforms condorcet and individual rank learning methods. In Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval, pages 758–759.
  7. Lee R Dice. 1945. Measures of the amount of ecologic association between species. Ecology, 26(3):297–302.
  8. A survey on in-context learning. arXiv preprint arXiv:2301.00234.
  9. Can you unpack that? learning to rewrite questions-in-context. 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 5918–5924, Hong Kong, China. Association for Computational Linguistics.
  10. Mara Finkelstein and Markus Freitag. 2023. Mbr and qe finetuning: Training-time distillation of the best and most expensive decoding methods. In The Twelfth International Conference on Learning Representations.
  11. Neural approaches to conversational information retrieval, volume 44. Springer Nature.
  12. Generate, annotate, and learn: NLP with synthetic text. Transactions of the Association for Computational Linguistics, 10:826–842.
  13. Query expansion by prompting large language models. arXiv preprint arXiv:2305.03653.
  14. Itercqr: Iterative conversational query reformulation without human supervision. arXiv preprint arXiv:2311.09820.
  15. Billion-scale similarity search with GPUs. IEEE Transactions on Big Data, 7(3):535–547.
  16. Sungdong Kim and Gangwoo Kim. 2022. Saving dense retriever from shortcut dependency in conversational search. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10278–10287, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  17. Efficient memory management for large language model serving with pagedattention. In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles.
  18. Pyserini: A Python toolkit for reproducible information retrieval research with sparse and dense representations. In Proceedings of the 44th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021), pages 2356–2362.
  19. Contextualized query embeddings for conversational search. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1004–1015, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  20. Conversational question reformulation via sequence-to-sequence architectures and pretrained language models. arXiv preprint arXiv:2004.01909.
  21. BRIO: Bringing order to abstractive summarization. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2890–2903, Dublin, Ireland. Association for Computational Linguistics.
  22. Ilya Loshchilov and Frank Hutter. 2018. Decoupled weight decay regularization. In International Conference on Learning Representations.
  23. Sparse, dense, and attentional representations for text retrieval. Transactions of the Association for Computational Linguistics, 9:329–345.
  24. Large language models know your contextual search intent: A prompting framework for conversational search. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 1211–1225, Singapore. Association for Computational Linguistics.
  25. Learning denoised and interpretable session representation for conversational search. In Proceedings of the ACM Web Conference 2023, WWW ’23, page 3193–3202, New York, NY, USA. Association for Computing Machinery.
  26. ConvGQR: Generative query reformulation for conversational search. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4998–5012, Toronto, Canada. Association for Computational Linguistics.
  27. Learning to relate to previous turns in conversational search. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’23, page 1722–1732, New York, NY, USA. Association for Computing Machinery.
  28. Learning to relate to previous turns in conversational search. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’23, page 1722–1732, New York, NY, USA. Association for Computing Machinery.
  29. History-aware conversational dense retrieval. arXiv preprint arXiv:2401.16659.
  30. Ms marco: A human-generated machine reading comprehension dataset.
  31. OpenAI. 2022. Introducing chatgpt. https://openai.com/blog/chatgpt. Accessed: 2024-02-06.
  32. Prompting contrastive explanations for commonsense reasoning tasks. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 4179–4192, Online. Association for Computational Linguistics.
  33. Open-retrieval conversational question answering. In Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval, pages 539–548.
  34. Filip Radlinski and Nick Craswell. 2017. A theoretical framework for conversational search. In Proceedings of the 2017 Conference on Conference Human Information Interaction and Retrieval, CHIIR ’17, page 117–126, New York, NY, USA. Association for Computing Machinery.
  35. Direct preference optimization: Your language model is secretly a reward model. In Advances in Neural Information Processing Systems, volume 36, pages 53728–53741. Curran Associates, Inc.
  36. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, 21(140):1–67.
  37. The probabilistic relevance framework: Bm25 and beyond. Foundations and Trends® in Information Retrieval, 3(4):333–389.
  38. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347.
  39. David A. Smith and Jason Eisner. 2006. Minimum risk annealing for training log-linear models. In Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions, pages 787–794, Sydney, Australia. Association for Computational Linguistics.
  40. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288.
  41. Question rewriting for conversational question answering. In Proceedings of the 14th ACM international conference on web search and data mining, pages 355–363.
  42. Christophe Van Gysel and Maarten de Rijke. 2018. Pytrec_eval: An extremely fast python interface to trec_eval. In SIGIR. ACM.
  43. Diverse beam search: Decoding diverse solutions from neural sequence models. arXiv preprint arXiv:1610.02424.
  44. Aligning large language models with human: A survey. arXiv preprint arXiv:2307.12966.
  45. CONQRR: Conversational query rewriting for retrieval with reinforcement learning. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10000–10014, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  46. Approximate nearest neighbor negative contrastive learning for dense text retrieval. In International Conference on Learning Representations.
  47. Enhancing conversational search: Large language model-aided informative query rewriting. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5985–6006, Singapore. Association for Computational Linguistics.
  48. Ask optimal questions: Aligning large language models with retriever’s preference in conversational search. arXiv preprint arXiv:2402.11827.
  49. Few-shot generative conversational query rewriting. In Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval, pages 1933–1936.
  50. Few-shot conversational dense retrieval. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’21, page 829–838, New York, NY, USA. Association for Computing Machinery.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Yilong Lai (6 papers)
  2. Jialong Wu (36 papers)
  3. Congzhi Zhang (5 papers)
  4. Haowen Sun (12 papers)
  5. Deyu Zhou (42 papers)
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets