Related papers: Dense Hierarchical Retrieval for Open-Domain Quest…

We propose a simple and efficient multi-hop dense retrieval approach for answering complex open-domain questions, which achieves state-of-the-art performance on two multi-hop datasets, HotpotQA and multi-evidence FEVER. Contrary to previous…

Dense retrieval methods typically target unstructured text data represented as flat strings. However, e-commerce catalogs often include structured information across multiple fields, such as brand, title, and description, which contain…

Neural networks with deep architectures have demonstrated significant performance improvements in computer vision, speech recognition, and natural language processing. The challenges in information retrieval (IR), however, are different…

Information Retriever (IR) aims to find the relevant documents (e.g. snippets, passages, and articles) to a given query at large scale. IR plays an important role in many tasks such as open domain question answering and dialogue systems,…

Dense retrieval models are commonly used in Information Retrieval (IR) applications, such as Retrieval-Augmented Generation (RAG). Since they often serve as the first step in these systems, their robustness is critical to avoid downstream…

Deep hashing models have been proposed as an efficient method for large-scale similarity search. However, most existing deep hashing methods only utilize fine-level labels for training while ignoring the natural semantic hierarchy…

We present a long-horizon, hierarchical deep research (DR) agent designed for complex materials and device discovery problems that exceed the scope of existing Machine Learning (ML) surrogates and closed-source commercial agents. Our…

The goal of screening prioritisation in systematic reviews is to identify relevant documents with high recall and rank them in early positions for review. This saves reviewing effort if paired with a stopping criterion, and speeds up review…

Temporal awareness is crucial in many information retrieval tasks, particularly in scenarios where the relevance of documents depends on their alignment with the query's temporal context. Traditional approaches such as BM25 and Dense…

Retrieval approaches that score documents based on learned dense vectors (i.e., dense retrieval) rather than lexical signals (i.e., conventional retrieval) are increasingly popular. Their ability to identify related documents that do not…

Hashing aims at generating highly compact similarity preserving code words which are well suited for large-scale image retrieval tasks. Most existing hashing methods first encode the images as a vector of hand-crafted features followed by a…

Generative retrieval is a promising new paradigm in text retrieval that generates identifier strings of relevant passages as the retrieval target. This paradigm leverages powerful generative language models, distinct from traditional sparse…

To extract answers from a large corpus, open-domain question answering (QA) systems usually rely on information retrieval (IR) techniques to narrow the search space. Standard inverted index methods such as TF-IDF are commonly used as thanks…

Efficiently retrieving a concise set of candidates from a large document corpus remains a pivotal challenge in Information Retrieval (IR). Neural retrieval models, particularly dense retrieval models built with transformers and pretrained…

The work of neural retrieval so far focuses on ranking short texts and is challenged with long documents. There are many cases where the users want to find a relevant passage within a long document from a huge corpus, e.g. Wikipedia…

Developing a universal model that can efficiently and effectively respond to a wide range of information access requests -- from retrieval to recommendation to question answering -- has been a long-lasting goal in the information retrieval…

Spoken Question Answering (SQA) is essential for machines to reply to user's question by finding the answer span within a given spoken passage. SQA has been previously achieved without ASR to avoid recognition errors and Out-of-Vocabulary…

The dual-encoder has become the de facto architecture for dense retrieval. Typically, it computes the latent representations of the query and document independently, thus failing to fully capture the interactions between the query and…

Apart from discriminative models for classification and object detection tasks, the application of deep convolutional neural networks to basic research utilizing natural imaging data has been somewhat limited; particularly in cases where a…

Generative retrieval employs sequence models for conditional generation of document IDs based on a query (DSI (Tay et al., 2022); NCI (Wang et al., 2022); inter alia). While this has led to improved performance in zero-shot retrieval, it is…