Related papers: To Interpolate or not to Interpolate: PRF, Dense a…

Text retrieval using learned dense representations has recently emerged as a promising alternative to "traditional" text retrieval using sparse bag-of-words representations. One recent work that has garnered much attention is the dense…

Despite the advantages of their low-resource settings, traditional sparse retrievers depend on exact matching approaches between high-dimensional bag-of-words (BoW) representations of both the queries and the collection. As a result,…

Sparse document representations have been widely used to retrieve relevant documents via exact lexical matching. Owing to the pre-computed inverted index, it supports fast ad-hoc search but incurs the vocabulary mismatch problem. Although…

Dense retrievers have achieved impressive performance, but their demand for abundant training data limits their application scenarios. Contrastive pre-training, which constructs pseudo-positive examples from unlabeled data, has shown great…

In neural Information Retrieval, ongoing research is directed towards improving the first retriever in ranking pipelines. Learning dense embeddings to conduct retrieval using efficient approximate nearest neighbors methods has proven to…

A retrieval model should not only interpolate the training data but also extrapolate well to the queries that are different from the training data. While neural retrieval models have demonstrated impressive performance on ad-hoc search…

Image interpolation is a special case of image super-resolution, where the low-resolution image is directly down-sampled from its high-resolution counterpart without blurring and noise. Therefore, assumptions adopted in super-resolution…

We propose the new problem of choosing which dense retrieval model to use when searching on a new collection for which no labels are available, i.e. in a zero-shot setting. Many dense retrieval models are readily available. Each model…

Multi-hop question answering (MHQA) involves reasoning across multiple documents to answer complex questions. Dense retrievers typically outperform sparse methods like BM25 by leveraging semantic embeddings; however, they require labeled…

Recently, information retrieval has seen the emergence of dense retrievers, using neural networks, as an alternative to classical sparse methods based on term-frequency. These models have obtained state-of-the-art results on datasets and…

Term-based sparse representations dominate the first-stage text retrieval in industrial applications, due to its advantage in efficiency, interpretability, and exact term matching. In this paper, we study the problem of transferring the…

Retrieval-augmented Generation (RAG) is powerful, but its effectiveness hinges on which retrievers we use and how. Different retrievers offer distinct, often complementary signals: BM25 captures lexical matches; dense retrievers, semantic…

Pseudo-relevance feedback (PRF) is commonly used to boost the performance of traditional information retrieval (IR) models by using top-ranked documents to identify and weight new query terms, thereby reducing the effect of query-document…

By leveraging a dual encoder architecture, Dense Passage Retrieval (DPR) has outperformed traditional sparse retrieval algorithms such as BM25 in terms of passage retrieval accuracy. Recently proposed methods have further enhanced DPR's…

Learned Sparse Retrievers (LSR) have evolved into an effective retrieval strategy that can bridge the gap between traditional keyword-based sparse retrievers and embedding-based dense retrievers. At its core, learned sparse retrievers try…

Modern knowledge-intensive systems, such as retrieval-augmented generation (RAG), rely on effective retrievers to establish the performance ceiling for downstream modules. However, retriever training has been bottlenecked by sparse,…

Dense retrievers play a vital role in accessing external and specialized knowledge to augment language models (LMs). Training dense retrievers typically requires annotated query-document pairs, which are costly to create and scarce in…

Neural retrieval models (NRMs) have been shown to outperform their statistical counterparts owing to their ability to capture semantic meaning via dense document representations. These models, however, suffer from poor interpretability as…

Expansion-enhanced sparse lexical representation improves information retrieval (IR) by minimizing vocabulary mismatch problems during lexical matching. In this paper, we explore the potential of jointly learning dense semantic…

Ranker and retriever are two important components in dense passage retrieval. The retriever typically adopts a dual-encoder model, where queries and documents are separately input into two pre-trained models, and the vectors generated by…