An Effective Post-training Embedding Binarization Approach for Fast Online Top-K Passage Matching

Yankai Chen, Yifei Zhang, Huifeng Guo, Ruiming Tang, Irwin King

Abstract
With the rapid development of Natural Language Understanding for information retrieval, fine-tuned deep language models, e.g., BERT-based, perform remarkably effective in passage searching tasks. To lower the architecture complexity, the recent state-of-the-art model ColBERT employs Contextualized Late Interaction paradigm to independently learn fine-grained query-passage representations. Apart from the architecture simplification, embedding binarization, as another promising branch in model compression, further specializes in the reduction of memory and computation overheads. In this concise paper, we propose an effective post-training embedding binarization approach over ColBERT, achieving both architecture-level and embedding-level optimization for online inference. The empirical results demonstrate the efficaciousness of our proposed approach, empowering it to perform online query-passage matching acceleration.
Anthology ID:
2022.aacl-short.14
Volume:
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
November
Year:
2022
Address:
Online only
Editors:
Yulan He, Heng Ji, Sujian Li, Yang Liu, Chua-Hui Chang
Venues:
AACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
102–108
Language:
URL:
https://aclanthology.org/2022.aacl-short.14
DOI:
Bibkey:
Cite (ACL):
Yankai Chen, Yifei Zhang, Huifeng Guo, Ruiming Tang, and Irwin King. 2022. An Effective Post-training Embedding Binarization Approach for Fast Online Top-K Passage Matching. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 102–108, Online only. Association for Computational Linguistics.
Cite (Informal):
An Effective Post-training Embedding Binarization Approach for Fast Online Top-K Passage Matching (Chen et al., AACL-IJCNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/2022.aacl-short.14.pdf
PDF Search