On Efficient Retrieval of Top Similarity Vectors

Shulong Tan, Zhixin Zhou, Zhaozhuo Xu, Ping Li


Abstract
Retrieval of relevant vectors produced by representation learning critically influences the efficiency in natural language processing (NLP) tasks. In this paper, we demonstrate an efficient method for searching vectors via a typical non-metric matching function: inner product. Our method, which constructs an approximate Inner Product Delaunay Graph (IPDG) for top-1 Maximum Inner Product Search (MIPS), transforms retrieving the most suitable latent vectors into a graph search problem with great benefits of efficiency. Experiments on data representations learned for different machine learning tasks verify the outperforming effectiveness and efficiency of the proposed IPDG.
Anthology ID:
D19-1527
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
5236–5246
Language:
URL:
https://aclanthology.org/D19-1527
DOI:
10.18653/v1/D19-1527
Bibkey:
Cite (ACL):
Shulong Tan, Zhixin Zhou, Zhaozhuo Xu, and Ping Li. 2019. On Efficient Retrieval of Top Similarity Vectors. 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 5236–5246, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
On Efficient Retrieval of Top Similarity Vectors (Tan et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp22-frontmatter/D19-1527.pdf