ABSTRACT
This paper introduces Sparsified Late Interaction for Multi-vector (SLIM) retrieval with inverted indexes. Multi-vector retrieval methods have demonstrated their effectiveness on various retrieval datasets, and among them, ColBERT is the most established method based on the late interaction of contextualized token embeddings of pre-trained language models. However, efficient ColBERT implementations require complex engineering and cannot take advantage of off-the-shelf search libraries, impeding their practical use. To address this issue, SLIM first maps each contextualized token vector to a sparse, high-dimensional lexical space before performing late interaction between these sparse token embeddings. We then introduce an efficient two-stage retrieval architecture that includes inverted index retrieval followed by a score refinement module to approximate the sparsified late interaction, which is fully compatible with off-the-shelf lexical search libraries such as Lucene. SLIM achieves competitive accuracy on MS MARCO Passages and BEIR compared to ColBERT while being much smaller and faster on CPUs. To our knowledge, we are the first to explore using sparse token representations for multi-vector retrieval. Source code and data are integrated into the Pyserini IR toolkit.
Supplemental Material
- Yang Bai, Xiaoguang Li, Gang Wang, Chaoliang Zhang, Lifeng Shang, Jun Xu, Zhaowei Wang, Fangshan Wang, and Qun Liu. 2020. SparTerm: Learning Term-based Sparse Representation for Fast Text Retrieval. https://doi.org/10.48550/ARXIV.2010.00768Google ScholarCross Ref
- Daniel Cer, Yinfei Yang, Sheng-yi Kong, Nan Hua, Nicole Limtiaco, Rhomni St. John, Noah Constant, Mario Guajardo-Cespedes, Steve Yuan, Chris Tar, Yun-Hsuan Sung, Brian Strope, and Ray Kurzweil. 2018. Universal Sentence Encoder. https://doi.org/10.48550/ARXIV.1803.11175Google ScholarCross Ref
- Nick Craswell, Bhaskar Mitra, Emine Yilmaz, and Daniel Campos. 2021. Overview of the TREC 2020 deep learning track. https://doi.org/10.48550/ARXIV.2102.07662Google ScholarCross Ref
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. 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). Association for Computational Linguistics, Minneapolis, Minnesota, 4171--4186. https://doi.org/10.18653/v1/N19--1423Google ScholarCross Ref
- Thibault Formal, Carlos Lassance, Benjamin Piwowarski, and Stéphane Clinchant. 2021a. SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval. https://doi.org/10.48550/ARXIV.2109.10086Google ScholarCross Ref
- Thibault Formal, Benjamin Piwowarski, and Stéphane Clinchant. 2021b. SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery. https://doi.org/10.1145/3404835.3463098Google ScholarDigital Library
- Luyu Gao and Jamie Callan. 2021. Condenser: a Pre-training Architecture for Dense Retrieval. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, 981--993. https://doi.org/10.18653/v1/2021.emnlp-main.75Google ScholarCross Ref
- Luyu Gao and Jamie Callan. 2022. Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Dublin, Ireland, 2843--2853. https://doi.org/10.18653/v1/2022.acl-long.203Google ScholarCross Ref
- Luyu Gao, Zhuyun Dai, and Jamie Callan. 2021a. COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Online, 3030--3042. https://doi.org/10.18653/v1/2021.naacl-main.241Google ScholarCross Ref
- Tianyu Gao, Xingcheng Yao, and Danqi Chen. 2021b. SimCSE: Simple Contrastive Learning of Sentence Embeddings. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, 6894--6910. https://doi.org/10.18653/v1/2021.emnlp-main.552Google ScholarCross Ref
- Ruiqi Guo, Philip Sun, Erik Lindgren, Quan Geng, David Simcha, Felix Chern, and Sanjiv Kumar. 2020. Accelerating Large-Scale Inference with Anisotropic Vector Quantization. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13--18 July 2020, Virtual Event (Proceedings of Machine Learning Research, Vol. 119). PMLR, 3887--3896. http://proceedings.mlr.press/v119/guo20h.htmlGoogle Scholar
- Hua He and Jimmy Lin. 2016. Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity Measurement. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, San Diego, California, 937--948. https://doi.org/10.18653/v1/N16--1108Google ScholarCross Ref
- Sebastian Hofst"atter, Omar Khattab, Sophia Althammer, Mete Sertkan, and Allan Hanbury. 2022. Introducing Neural Bag of Whole-Words with ColBERTer: Contextualized Late Interactions Using Enhanced Reduction. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management. Association for Computing Machinery, 737--747. https://doi.org/10.1145/3511808.3557367Google ScholarDigital Library
- Sebastian Hofst"atter, Sheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin, and Allan Hanbury. 2021. Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, 113--122. https://doi.org/10.1145/3404835.3462891Google ScholarDigital Library
- Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2021. Unsupervised Dense Information Retrieval with Contrastive Learning. https://doi.org/10.48550/ARXIV.2112.09118Google ScholarCross Ref
- Jeff Johnson, Matthijs Douze, and Hervé Jégou. 2021. Billion-Scale Similarity Search with GPUs. IEEE Transactions on Big Data, Vol. 7, 03 (jul 2021), 535--547. https://doi.org/10.1109/TBDATA.2019.2921572Google ScholarCross Ref
- Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, Online, 6769--6781. https://doi.org/10.18653/v1/2020.emnlp-main.550Google ScholarCross Ref
- Omar Khattab and Matei Zaharia. 2020. ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, 39--48. https://doi.org/10.1145/3397271.3401075Google ScholarDigital Library
- Wuwei Lan and Wei Xu. 2018. Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering. In Proceedings of the 27th International Conference on Computational Linguistics. Association for Computational Linguistics, Santa Fe, New Mexico, USA, 3890--3902. https://aclanthology.org/C18--1328Google Scholar
- Minghan Li, Sheng-Chieh Lin, Barlas Oguz, Asish Ghoshal, Jimmy Lin, Yashar Mehdad, Wen-tau Yih, and Xilun Chen. 2022. CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval. https://doi.org/10.48550/ARXIV.2211.10411Google ScholarCross Ref
- Jimmy Lin and Xueguang Ma. 2021. A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques. https://doi.org/10.48550/ARXIV.2106.14807Google ScholarCross Ref
- Jimmy Lin, Xueguang Ma, Sheng-Chieh Lin, Jheng-Hong Yang, Ronak Pradeep, and Rodrigo Nogueira. 2021a. Pyserini: A Python Toolkit for Reproducible Information Retrieval Research with Sparse and Dense Representations. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, 2356--2362. https://doi.org/10.1145/3404835.3463238Google ScholarDigital Library
- Sheng-Chieh Lin, Akari Asai, Minghan Li, Barlas Oguz, Jimmy Lin, Yashar Mehdad, Wen-tau Yih, and Xilun Chen. 2023. How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval. https://doi.org/10.48550/ARXIV.2302.07452Google ScholarCross Ref
- Sheng-Chieh Lin, Minghan Li, and Jimmy Lin. 2022. Aggretriever: A Simple Approach to Aggregate Textual Representation for Robust Dense Passage Retrieval. https://doi.org/10.48550/ARXIV.2208.00511Google ScholarCross Ref
- Sheng-Chieh Lin and Jimmy Lin. 2022. A Dense Representation Framework for Lexical and Semantic Matching. https://doi.org/10.48550/ARXIV.2206.09912Google ScholarCross Ref
- Sheng-Chieh Lin, Jheng-Hong Yang, and Jimmy Lin. 2021b. In-Batch Negatives for Knowledge Distillation with Tightly-Coupled Teachers for Dense Retrieval. In Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021). Association for Computational Linguistics, Online, 163--173. https://doi.org/10.18653/v1/2021.repl4nlp-1.17Google ScholarCross Ref
- Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. https://doi.org/10.48550/ARXIV.1907.11692Google ScholarCross Ref
- Shuqi Lu, Di He, Chenyan Xiong, Guolin Ke, Waleed Malik, Zhicheng Dou, Paul Bennett, Tie-Yan Liu, and Arnold Overwijk. 2021. Less is More: Pretrain a Strong Siamese Encoder for Dense Text Retrieval Using a Weak Decoder. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, 2780--2791. https://doi.org/10.18653/v1/2021.emnlp-main.220Google ScholarCross Ref
- Yi Luan, Jacob Eisenstein, Kristina Toutanova, and Michael Collins. 2021. Sparse, Dense, and Attentional Representations for Text Retrieval. Transactions of the Association for Computational Linguistics, Vol. 9 (2021), 329--345. https://doi.org/10.1162/tacl_a_00369Google ScholarCross Ref
- Antonio Mallia, Omar Khattab, Torsten Suel, and Nicola Tonellotto. 2021. Learning Passage Impacts for Inverted Indexes. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, 1723--1727. https://doi.org/10.1145/3404835.3463030Google ScholarDigital Library
- Christopher D. Manning, Prabhakar Raghavan, and Hinrich Schü tze. 2008. Introduction to information retrieval. Cambridge University Press. https://doi.org/10.1017/CBO9780511809071Google ScholarDigital Library
- Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016. MS MARCO: A human generated machine reading comprehension dataset. In CoCo@ NIPS. https://www.microsoft.com/en-us/research/publication/ms-marco-human-generated-machine-reading-comprehension-dataset/Google Scholar
- Yujie Qian, Jinhyuk Lee, Sai Meher Karthik Duddu, Zhuyun Dai, Siddhartha Brahma, Iftekhar Naim, Tao Lei, and Vincent Y. Zhao. 2022. Multi-Vector Retrieval as Sparse Alignment. https://doi.org/10.48550/ARXIV.2211.01267Google ScholarCross Ref
- 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 and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, 3982--3992. https://doi.org/10.18653/v1/D19--1410Google ScholarCross Ref
- Stephen E. Robertson and Hugo Zaragoza. 2009. The Probabilistic Relevance Framework: BM25 and Beyond. Foundations and Trends in Information Retrieval, Vol. 3, 4 (2009), 333--389. https://doi.org/10.1561/1500000019Google ScholarDigital Library
- Gerard Salton and Christopher Buckley. 1988. Term-weighting approaches in automatic text retrieval. Information Processing & Management, Vol. 24, 5 (1988), 513--523. https://doi.org/10.1016/0306--4573(88)90021-0Google ScholarDigital Library
- Keshav Santhanam, Omar Khattab, Christopher Potts, and Matei Zaharia. 2022a. PLAID: An Efficient Engine for Late Interaction Retrieval. https://doi.org/10.48550/ARXIV.2205.09707Google ScholarCross Ref
- Keshav Santhanam, Omar Khattab, Jon Saad-Falcon, Christopher Potts, and Matei Zaharia. 2022b. ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Seattle, United States, 3715--3734. https://doi.org/10.18653/v1/2022.naacl-main.272Google ScholarCross Ref
- Tao Shen, Xiubo Geng, Chongyang Tao, Can Xu, Kai Zhang, and Daxin Jiang. 2022. UnifieR: A Unified Retriever for Large-Scale Retrieval. https://doi.org/10.48550/ARXIV.2205.11194Google ScholarCross Ref
- Nandan Thakur, Nils Reimers, Andreas Rücklé, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). https://openreview.net/forum?id=wCu6T5xFjeJGoogle Scholar
- Pauli Virtanen, Ralf Gommers, Travis E. Oliphant, Matt Haberland, Tyler Reddy, David Cournapeau, Evgeni Burovski, Pearu Peterson, Warren Weckesser, Jonathan Bright, Stéfan J. van der Walt, Matthew Brett, Joshua Wilson, K. Jarrod Millman, Nikolay Mayorov, Andrew R. J. Nelson, Eric Jones, Robert Kern, Eric Larson, C J Carey, .Ilhan Polat, Yu Feng, Eric W. Moore, Jake VanderPlas, Denis Laxalde, Josef Perktold, Robert Cimrman, Ian Henriksen, E. A. Quintero, Charles R. Harris, Anne M. Archibald, Antônio H. Ribeiro, Fabian Pedregosa, Paul van Mulbregt, and SciPy 1.0 Contributors. 2020. SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python. Nature Methods, Vol. 17 (2020), 261--272. https://doi.org/10.1038/s41592-019-0686--2Google ScholarCross Ref
- Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul N. Bennett, Junaid Ahmed, and Arnold Overwijk. 2021. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3--7, 2021. OpenReview.net. https://openreview.net/forum?id=zeFrfgyZlnGoogle Scholar
- Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, and Shaoping Ma. 2021. Optimizing Dense Retrieval Model Training with Hard Negatives. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, 1503--1512. https://doi.org/10.1145/3404835.3462880Google ScholarDigital Library
- Shunyu Zhang, Yaobo Liang, Ming Gong, Daxin Jiang, and Nan Duan. 2022. Multi-View Document Representation Learning for Open-Domain Dense Retrieval. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Dublin, Ireland, 5990--6000. https://doi.org/10.18653/v1/2022.acl-long.414Google ScholarCross Ref
- Yinan Zhang, Raphael Tang, and Jimmy Lin. 2019. Explicit Pairwise Word Interaction Modeling Improves Pretrained Transformers for English Semantic Similarity Tasks. https://doi.org/10.48550/ARXIV.1911.02847Google ScholarCross Ref
Index Terms
- SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes
Recommendations
Inverted indexes vs. bitmap indexes in decision support systems
CIKM '09: Proceedings of the 18th ACM conference on Information and knowledge managementBitmap indexes are widely used in Decision Support Systems (DSSs) to improve query performance. In this paper, we evaluate the use of compressed inverted indexes with adapted query processing strategies from Information Retrieval as an alternative. In a ...
Anserini Gets Dense Retrieval: Integration of Lucene's HNSW Indexes
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementAnserini is a Lucene-based toolkit for reproducible information retrieval research in Java that has been gaining traction in the community. It provides retrieval capabilities for both "traditional" bag-of-words retrieval models such as BM25 as well as ...
Enhancing Sparse Retrieval via Unsupervised Learning
SIGIR-AP '23: Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific RegionRecent work has shown that neural retrieval models excel at text ranking tasks in a supervised setting when given large amounts of manually labeled training data. However, it remains an open question how to train unsupervised retrieval models that are ...
Comments