Efficient Interaction-based Neural Ranking with Locality Sensitive Hashing

By Shiyu Ji, Jinjin Shao, Tao Yang. 2019

17 citations recorded by the source corpus.

Interaction-based neural ranking has been shown to be effective for document search using distributed word representations. However the time or space required is very expensive for online query processing with neural ranking. This paper investigates fast approximation of three interaction-based neural ranking algorithms using Locality Sensitive Hashing (LSH). It accelerates query-document interaction computation by using a runtime cache with precomputed term vectors, and speeds up kernel calculation by taking advantages of limited integer similarity values. This paper presents the design choices with cost analysis, and an evaluation that assesses efficiency benefits and relevance tradeoffs for the tested datasets.

Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition, Information Retrieval & Search

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Computer Vision and Pattern Recognition

In Information Retrieval & Search

Citations in the corpus

ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT (2020, background): “Hofst¨atter et al. [10] and MacAvaney et al. [19] observe that BERT-based models in the literature are 100-1000 × more computationally expensive than prior models—some of which are arguably not inexpensive to begin with [14].”
Multi-Stage Document Ranking with BERT (2019, background): “…where the task is to learn some non-linear transformation of queries and documents (i.e., using a neural network) such that documents relevant to a query have high similarities in terms of a simple metric such as cosine similarity (Hen-derson et al., 2017; Zamani et al., 2018; Ji et al., 2019).”
Efficient Document Re-Ranking for Transformers by Precomputing Term Representations (2020, methodology): “ention to this matter [16]. That being said, some efforts do exist. For instance, Zamani et al. [50] investigate learning sparse query and document representations which allow for indexing. Ji et al. [21] demonstrate that Locality-Sensitive Hashing (LSH) and other tricks can be employed to improve t”
Training Curricula for Open Domain Answer Re-Ranking (2020, background): “This model yields competitive ranking performance and can be optimized for real-time ranking [18].”
Introducing Neural Bag of Whole-Words with ColBERTer: Contextualized Late Interactions using Enhanced Reduction (2022, background): “Wellstudied low hanging fruits for good tradeoffs include reducing the number of dimensions (either inside the model or outside with PCA) and reducing the number of bytes with quantization [12, 21, 27, 36].”
Interpretable & Time-Budget-Constrained Contextualization for Re-Ranking (2020, methodology): “One way to make neural IR models faster at query time is to offload computation to the indexing phase, either by assuming query term independence [23] or by approximating interaction similarities [17].”
Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation (2020, background): “Ji et al. [18] demonstrate that approximations of interaction-basedneuralrankingalgorithms usingkernelswithlocality-sensitive hashing accelerate the query-document interaction computation.”