Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval
Kyoung-Rok Jang, Junmo Kang, Giwon Hong, Sung-Hyon Myaeng, Joohee Park, Taewon Yoon, Heecheol Seo
Abstract
The semantic matching capabilities of neural information retrieval can ameliorate synonymy and polysemy problems of symbolic approaches. However, neural models’ dense representations are more suitable for re-ranking, due to their inefficiency. Sparse representations, either in symbolic or latent form, are more efficient with an inverted index. Taking the merits of the sparse and dense representations, we propose an ultra-high dimensional (UHD) representation scheme equipped with directly controllable sparsity. UHD’s large capacity and minimal noise and interference among the dimensions allow for binarized representations, which are highly efficient for storage and search. Also proposed is a bucketing method, where the embeddings from multiple layers of BERT are selected/merged to represent diverse linguistic aspects. We test our models with MS MARCO and TREC CAR, showing that our models outperforms other sparse models.- Anthology ID:
- 2021.emnlp-main.78
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1016–1029
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.78
- DOI:
- 10.18653/v1/2021.emnlp-main.78
- Cite (ACL):
- Kyoung-Rok Jang, Junmo Kang, Giwon Hong, Sung-Hyon Myaeng, Joohee Park, Taewon Yoon, and Heecheol Seo. 2021. Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1016–1029, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval (Jang et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2021.emnlp-main.78.pdf
- Data
- MS MARCO