Abstract
The rapid development of deep learning and artificial intelligence has transformed our approach to solving scientific problems across various domains, including computer vision, natural language processing, and automatic content generation. Information retrieval (IR) has also experienced significant advancements, with natural language understanding and multimodal content analysis enabling accurate information retrieval. However, the widespread adoption of neural networks has also influenced the focus of IR problem-solving, which nowadays predominantly relies on evaluating the similarity of dense vectors derived from the latent spaces of deep neural networks. Nevertheless, the challenges of conducting similarity searches on large-scale databases with billions of vectors persist. Traditional IR approaches use inverted indices and vector space models, which work well with sparse vectors. In this paper, we propose Vec2Doc, a novel method that converts dense vectors into sparse integer vectors, allowing for the use of inverted indices. Preliminary experimental evaluation shows a promising solution for large-scale vector-based IR problems.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amato, G., Bolettieri, P., Carrara, F., Falchi, F., Gennaro, C.: Large-scale image retrieval with elasticsearch. In: The 41st International ACM SIGIR Conference on Research Development in Information Retrieval, pp. 925–928 (2018)
Amato, G., Carrara, F., Falchi, F., Gennaro, C., Vadicamo, L.: Large-scale instance-level image retrieval. Inf. Process. Manage. 57(6), 102100 (2020)
Carrara, F., Vadicamo, L., Gennaro, C., Amato, G.: Approximate nearest neighbor search on standard search engines. In: Similarity Search and Applications: 15th International Conference, SISAP 2022, Bologna, Italy, October 5–7, 2022, Proceedings, pp. 214–221. Springer (2022)
Chávez, E., Figueroa, K., Navarro, G.: Effective proximity retrieval by ordering permutations. IEEE Trans. Pattern Anal. Mach. Intell. 30(9), 1647–1658 (2008)
Dua, D., Graff, C.: UCI machine learning repository (2017). http://archive.ics.uci.edu/ml
Gennaro, C., Amato, G., Bolettieri, P., Savino, P.: An Approach to Content-Based Image Retrieval Based on the Lucene Search Engine Library. In: Lalmas, M., Jose, J., Rauber, A., Sebastiani, F., Frommholz, I. (eds.) Research and Advanced Technology for Digital Libraries, pp. 55–66. Springer, Berlin, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15464-5_8
Higuchi, N., Imamura, Y., Mic, V., Shinohara, T., Hirata, K., Kuboyama, T.: Nearest-neighbor search from large datasets using narrow sketches. In: ICPRAM, pp. 401–410 (2022)
Mic, V., Novak, D., Zezula, P.: Binary sketches for secondary filtering. ACM Trans. Inform. Syst. (TOIS) 37(1), 1–28 (2018)
Novak, D., Zezula, P.: Ppp-codes for large-scale similarity searching. Transactions on Large-Scale Data-and Knowledge-Centered Systems XXIV: Special Issue on Database-and Expert-Systems Applications, pp. 61–87 (2016)
Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)
Povey, D., et al.: Semi-orthogonal low-rank matrix factorization for deep neural networks. In: Interspeech, pp. 3743–3747 (2018)
Salton, G., McGill, M.J.: Introduction to Modern Information Retrieval. McGraw-Hill Inc, New York, NY, USA (1986)
Shang, W., Sohn, K., Almeida, D., Lee, H.: Understanding and improving convolutional neural networks via concatenated rectified linear units. In: Proceedings of the 33rd International Conference on Machine Learning. ICML 2016, vol. 48, pp. 2217–2225. JMLR.org (2016)
Simhadri, H.V., et al.: Results of the neurips’21 challenge on billion-scale approximate nearest neighbor search. In: NeurIPS 2021 Competitions and Demonstrations Track, pp. 177–189. PMLR (2022)
Vadicamo, L., Connor, R., Chávez, E.: Query filtering using two-dimensional local embeddings. Inf. Syst. 101, 101808 (2021)
Vadicamo, L., Gennaro, C., Falchi, F., Chávez, E., Connor, R., Amato, G.: Re-ranking via local embeddings: a use case with permutation-based indexing and the nsimplex projection. Inf. Syst. 95, 101506 (2021)
Acknowledgements
This work was partially funded by AI4Media - A European Excellence Centre for Media, Society, and Democracy (EC, H2020 n. 951911), SUN - Social and hUman ceNtered XR (EC, Horizon Europe n. 101092612), and National Centre for HPC, Big Data and Quantum Computing - HPC (CUP B93C22000620006).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Carrara, F., Gennaro, C., Vadicamo, L., Amato, G. (2023). Vec2Doc: Transforming Dense Vectors into Sparse Representations for Efficient Information Retrieval. In: Pedreira, O., Estivill-Castro, V. (eds) Similarity Search and Applications. SISAP 2023. Lecture Notes in Computer Science, vol 14289. Springer, Cham. https://doi.org/10.1007/978-3-031-46994-7_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-46994-7_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46993-0
Online ISBN: 978-3-031-46994-7
eBook Packages: Computer ScienceComputer Science (R0)