Related papers: Semantic Recall for Vector Search
Vector retrieval systems exhibit significant performance variance across queries due to heterogeneous embedding quality. We propose a lightweight framework for predicting retrieval performance at the query level by combining quantization…
Although originally developed to evaluate sets of items, recall is often used to evaluate rankings of items, including those produced by recommender, retrieval, and other machine learning systems. The application of recall without a formal…
Fast k-Nearest Neighbor search over real-valued vector spaces (KNN) is an important algorithmic task for information retrieval and recommendation systems. We present a method for using reduced precision to represent vectors through…
Object detection often suffers from a plenty of bootless proposals, selecting high quality proposals remains a great challenge. In this paper, we propose a semantic, class-specific approach to re-rank object proposals, which can…
Vector databases typically rely on approximate nearest neighbor (ANN) search to retrieve the top-k closest vectors to a query in embedding space. While effective, this approach often yields semantically redundant results, missing the…
In realistic retrieval settings with large and evolving knowledge bases, the total number of documents relevant to a query is typically unknown, and recall cannot be computed. In this paper, we evaluate several established strategies for…
A common retrieve-and-rerank paradigm involves retrieving relevant candidates from a broad set using a fast bi-encoder (BE), followed by applying expensive but accurate cross-encoders (CE) to a limited candidate set. However, relying on…
Large language models (LLMs) are increasingly deployed for understanding large codebases, but whether they understand operational semantics of long code context or rely on pattern matching shortcuts remains unclear. We distinguish between…
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…
This paper introduces and analyzes a search and retrieval model that adopts key semantic communication principles from retrieval-augmented generation. We specifically present an information-theoretic analysis of a remote document retrieval…
We propose a novel method for evaluating the performance of a content search system that measures the semantic match between a query and the results returned by the search system. We introduce a metric called "on-topic rate" to measure the…
There is extensive interest in metric learning methods for image retrieval. Many metric learning loss functions focus on learning a correct ranking of training samples, but strongly overfit semantically inconsistent labels and require a…
In recent years, deep metric learning has achieved promising results in learning high dimensional semantic feature embeddings where the spatial relationships of the feature vectors match the visual similarities of the images. Similarity…
Recently, relational metric learning methods have been received great attention in recommendation community, which is inspired by the translation mechanism in knowledge graph. Different from the knowledge graph where the entity-to-entity…
We study the problem of semantic matching in product search, that is, given a customer query, retrieve all semantically related products from the catalog. Pure lexical matching via an inverted index falls short in this respect due to…
Semantic parsing is the problem of deriving machine interpretable meaning representations from natural language utterances. Neural models with encoder-decoder architectures have recently achieved substantial improvements over traditional…
Traditional retrieval methods have been essential for assessing document similarity but struggle with capturing semantic nuances. Despite advancements in latent semantic analysis (LSA) and deep learning, achieving comprehensive semantic…
Semantic annotations have to satisfy quality constraints to be useful for digital libraries, which is particularly challenging on large and diverse datasets. Confidence scores of multi-label classification methods typically refer only to…
Due to the falling costs of data acquisition and storage, researchers and industry analysts often want to find all instances of rare events in large datasets. For instance, scientists can cheaply capture thousands of hours of video, but are…
Sparse annotation poses persistent challenges to training dense retrieval models; for example, it distorts the training signal when unlabeled relevant documents are used spuriously as negatives in contrastive learning. To alleviate this…