0 citations0 references

Sparse, Dense, and Attentional Representations for Text Retrieval

Transactions of the Association for Computational Linguistics2021Vol. 9, pp. 329–345

Citations Over TimeTop 1% of 2021 papers

Yi Luan, Jacob Eisenstein, Kristina Toutanova, Michael Collins

Abstract

Abstract Dual encoders perform retrieval by encoding documents and queries into dense low-dimensional vectors, scoring each document by its inner product with the query. We investigate the capacity of this architecture relative to sparse bag-of-words models and attentional neural networks. Using both theoretical and empirical analysis, we establish connections between the encoding dimension, the margin between gold and lower-ranked documents, and the document length, suggesting limitations in the capacity of fixed-length encodings to support precise retrieval of long documents. Building on these insights, we propose a simple neural model that combines the efficiency of dual encoders with some of the expressiveness of more costly attentional architectures, and explore sparse-dense hybrids to capitalize on the precision of sparse retrieval. These models outperform strong alternatives in large-scale retrieval.

Related Papers

→ Large margin distribution machine(2014)105 cited
Intensive Margin and Extensive Margin Adjustments of Labor Market : Turkey versus United States(2013)
→ Large Margin Distribution Machine(2013)1 cited
On the Necessity and Feasibility of Constructing Big Water Margin Cultural System——Taking Big Folk Water Margin by Fan Chaoyang and Zhang Qingjian as an Example(2009)