Relevance Filtering for Embedding-based Retrieval

• URL: http://arxiv.org/abs/2408.04887v1
• Date: Fri, 09 Aug 2024 06:21:20 GMT
• Title: Relevance Filtering for Embedding-based Retrieval
• Authors: Nicholas Rossi, Juexin Lin, Feng Liu, Zhen Yang, Tony Lee, Alessandro Magnani, Ciya Liao,
• Abstract summary: In embedding-based retrieval, Approximate Nearest Neighbor (ANN) search enables efficient retrieval of similar items from large-scale datasets. This paper introduces a novel relevance filtering component (called "Cosine Adapter") for embedding-based retrieval to address this challenge. We are able to significantly increase the precision of the retrieved set, at the expense of a small loss of recall.
• Score: 46.851594313019895
• License:
• Abstract: In embedding-based retrieval, Approximate Nearest Neighbor (ANN) search enables efficient retrieval of similar items from large-scale datasets. While maximizing recall of relevant items is usually the goal of retrieval systems, a low precision may lead to a poor search experience. Unlike lexical retrieval, which inherently limits the size of the retrieved set through keyword matching, dense retrieval via ANN search has no natural cutoff. Moreover, the cosine similarity scores of embedding vectors are often optimized via contrastive or ranking losses, which make them difficult to interpret. Consequently, relying on top-K or cosine-similarity cutoff is often insufficient to filter out irrelevant results effectively. This issue is prominent in product search, where the number of relevant products is often small. This paper introduces a novel relevance filtering component (called "Cosine Adapter") for embedding-based retrieval to address this challenge. Our approach maps raw cosine similarity scores to interpretable scores using a query-dependent mapping function. We then apply a global threshold on the mapped scores to filter out irrelevant results. We are able to significantly increase the precision of the retrieved set, at the expense of a small loss of recall. The effectiveness of our approach is demonstrated through experiments on both public MS MARCO dataset and internal Walmart product search data. Furthermore, online A/B testing on the Walmart site validates the practical value of our approach in real-world e-commerce settings.

Related papers

• pEBR: A Probabilistic Approach to Embedding Based Retrieval [4.8338111302871525]
  Embedding retrieval aims to learn a shared semantic representation space for both queries and items. In current industrial practice, retrieval systems typically retrieve a fixed number of items for different queries.
  arXiv  Detail & Related papers  (2024-10-25T07:14:12Z)
• SparseCL: Sparse Contrastive Learning for Contradiction Retrieval [87.02936971689817]
  Contradiction retrieval refers to identifying and extracting documents that explicitly disagree with or refute the content of a query. Existing methods such as similarity search and crossencoder models exhibit significant limitations. We introduce SparseCL that leverages specially trained sentence embeddings designed to preserve subtle, contradictory nuances between sentences.
  arXiv  Detail & Related papers  (2024-06-15T21:57:03Z)
• Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders [77.84801537608651]
  Cross-encoder (CE) models which compute similarity by jointly encoding a query-item pair perform better than embedding-based models (dual-encoders) at estimating query-item relevance. We propose a sparse-matrix factorization based method that efficiently computes latent query and item embeddings to approximate CE scores and performs k-NN search with the approximate CE similarity.
  arXiv  Detail & Related papers  (2024-05-06T17:14:34Z)
• Vector search with small radiuses [10.880913075221361]
  This paper focuses on the common case where a hard decision needs to be taken depending on the vector retrieval results. We show that the value of a range search result can be modeled rigorously based on the query-to-vector distance. This yields a metric for range search, RSM, that is both principled and easy to compute without running an end-to-end evaluation.
  arXiv  Detail & Related papers  (2024-03-16T00:34:25Z)
• Group Testing for Accurate and Efficient Range-Based Near Neighbor Search for Plagiarism Detection [2.3814052021083354]
  This work presents an adaptive group testing framework for the range-based high dimensional near neighbor search problem. Our method efficiently marks each item in a database as neighbor or non-neighbor of a query point, based on a cosine distance threshold without exhaustive search. We show that, using softmax-based features, our method achieves a more than ten-fold speed-up over exhaustive search with no loss of accuracy.
  arXiv  Detail & Related papers  (2023-11-05T06:12:03Z)
• Lexically-Accelerated Dense Retrieval [29.327878974130055]
  'LADR' (Lexically-Accelerated Dense Retrieval) is a simple-yet-effective approach that improves the efficiency of existing dense retrieval models. LADR consistently achieves both precision and recall that are on par with an exhaustive search on standard benchmarks.
  arXiv  Detail & Related papers  (2023-07-31T15:44:26Z)
• IRLI: Iterative Re-partitioning for Learning to Index [104.72641345738425]
  Methods have to trade between obtaining high accuracy while maintaining load balance and scalability in distributed settings. We propose a novel approach called IRLI, which iteratively partitions the items by learning the relevant buckets directly from the query-item relevance data. We mathematically show that IRLI retrieves the correct item with high probability under very natural assumptions and provides superior load balancing.
  arXiv  Detail & Related papers  (2021-03-17T23:13:25Z)
• Surprise: Result List Truncation via Extreme Value Theory [92.5817701697342]
  We propose a statistical method that produces interpretable and calibrated relevance scores at query time using nothing more than the ranked scores. We demonstrate its effectiveness on the result list truncation task across image, text, and IR datasets.
  arXiv  Detail & Related papers  (2020-10-19T19:15:50Z)
• LSF-Join: Locality Sensitive Filtering for Distributed All-Pairs Set Similarity Under Skew [58.21885402826496]
  All-pairs set similarity is a widely used data mining task, even for large and high-dimensional datasets. We present a new distributed algorithm, LSF-Join, for approximate all-pairs set similarity. We show that LSF-Join efficiently finds most close pairs, even for small similarity thresholds and for skewed input sets.
  arXiv  Detail & Related papers  (2020-03-06T00:06:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.