Related papers: IncDSI: Incrementally Updatable Document Retrieval

Retrieving documents and prepending them in-context at inference time improves performance of language model (LMs) on a wide range of tasks. However, these documents, often spanning hundreds of words, make inference substantially more…

Ranked document retrieval is a fundamental task in search engines. Such queries are solved with inverted indexes that require additional 45%-80% of the compressed text space, and take tens to hundreds of microseconds per query. In this…

Machine learning tasks over image databases often generate masks that annotate image content (e.g., saliency maps, segmentation maps, depth maps) and enable a variety of applications (e.g., determine if a model is learning spurious…

What if Information Retrieval (IR) systems did not just retrieve relevant information that is stored in their indices, but could also "understand" it and synthesise it into a single document? We present a preliminary study that makes a…

Deep neural networks have achieved significant improvements in information retrieval (IR). However, most existing models are computational costly and can not efficiently scale to long documents. This paper proposes a novel End-to-End neural…

We show how full-text search based on inverted indices can be accelerated by clustering the documents without losing results (SeCluD -- SEarch with CLUstered Documents). We develop a fast multilevel clustering algorithm that explicitly uses…

With the growing popularity of LLM agents and RAG, it has become increasingly important to retrieve documents that are essential for solving a task, even when their connection to the task is indirect or implicit. Addressing this problem…

We call on the Document AI (DocAI) community to reevaluate current methodologies and embrace the challenge of creating more practically-oriented benchmarks. Document Understanding Dataset and Evaluation (DUDE) seeks to remediate the halted…

Document retrieval has been an important research problem over many years in the information retrieval community. State-of-the-art techniques utilize various methods in matching documents to a given document including keywords, phrases, and…

Document image restoration is a crucial aspect of Document AI systems, as the quality of document images significantly influences the overall performance. Prevailing methods address distinct restoration tasks independently, leading to…

Document listing on string collections is the task of finding all documents where a pattern appears. It is regarded as the most fundamental document retrieval problem, and is useful in various applications. Many of the fastest-growing…

Generative Retrieval (GR) is an emerging paradigm in information retrieval that leverages generative models to directly map queries to relevant document identifiers (DocIDs) without the need for traditional query processing or document…

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…

In this paper, proximity full-text searches in large text arrays are considered. A search query consists of several words. The search result is a list of documents containing these words. In a modern search system, documents that contain…

Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine…

Text indexing is a fundamental and well-studied problem. Classic solutions either replace the original text with a compressed representation, e.g., the FM-index and its variants, or keep it uncompressed but attach some redundancy - an index…

Popularized by the Differentiable Search Index, the emerging paradigm of generative retrieval re-frames the classic information retrieval problem into a sequence-to-sequence modeling task, forgoing external indices and encoding an entire…

Recent dense retrievers increasingly leverage the robust text understanding capabilities of Large Language Models (LLMs), encoding queries and documents into a shared embedding space for effective retrieval. However, most existing methods…

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…

A fundamental trade-off between effectiveness and efficiency needs to be balanced when designing an online question answering system. Effectiveness comes from sophisticated functions such as extractive machine reading comprehension (MRC),…