Related papers: Building Retrieval Systems for the ClueWeb22-B Cor…
We present Lit2Vec, a reproducible workflow for constructing and validating a chemistry corpus from the Semantic Scholar Open Research Corpus using conservative, metadata-based license screening. Using this workflow, we assembled an…
Recent multilingual named entity recognition (NER) work has shown that large language models (LLMs) can provide effective synthetic supervision, yet such datasets have mostly appeared as by-products of broader experiments rather than as…
The number of biomedical research articles published has doubled in the past 20 years. Search engine based systems naturally center around searching, but researchers may not have a clear goal in mind, or the goal may be expressed in a query…
Retrieval-augmented question answering over heterogeneous corpora requires connected evidence across text, tables, and graph nodes. While entity-level knowledge graphs support structured access, they are costly to construct and maintain,…
The web contains vast repositories of unstructured text. We investigate the opportunity for building a knowledge graph from these text sources. We generate a set of triples which can be used in knowledge gathering and integration. We define…
An important goal of online platforms is to enable content discovery, i.e. allow users to find a catalog entity they were not familiar with. A pre-requisite to discover an entity, e.g. a book, with a search engine is that the entity is…
This paper studies fast fusion of dense retrieval and sparse lexical retrieval, and proposes a cluster-based selective dense retrieval method called CluSD guided by sparse lexical retrieval. CluSD takes a lightweight cluster-based approach…
Retrieval-Augmented Generation (RAG) systems critically depend on retrieval quality, yet no systematic comparison of modern retrieval methods exists for heterogeneous documents containing both text and tabular data. We benchmark ten…
The main aim of an information retrieval system is to extract appropriate information from an enormous collection of data based on users need. The basic concept of the information retrieval system is that when a user sends out a query, the…
Scientific knowledge discovery increasingly relies on large language models, yet many existing scholarly assistants depend on proprietary systems with tens or hundreds of billions of parameters. Such reliance limits reproducibility and…
Document classification for text, images and other applicable entities has long been a focus of research in academia and also finds application in many industrial settings. Amidst a plethora of approaches to solve such problems,…
Passage retrieval addresses the problem of locating relevant passages, usually from a large corpus, given a query. In practice, lexical term-matching algorithms like BM25 are popular choices for retrieval owing to their efficiency. However,…
Most of the current methods for mining parallel texts from the web assume that web pages of web sites share same structure across languages. We believe that there still exists a non-negligible amount of parallel data spread across sources…
HC4 is a new suite of test collections for ad hoc Cross-Language Information Retrieval (CLIR), with Common Crawl News documents in Chinese, Persian, and Russian, topics in English and in the document languages, and graded relevance…
Commercial web search engines employ near-duplicate detection to ensure that users see each relevant result only once, albeit the underlying web crawls typically include (near-)duplicates of many web pages. We revisit the risks and…
A publicly available dataset for federated search reflecting a real web environment has long been absent, making it difficult for researchers to test the validity of their federated search algorithms for the web setting. We present several…
Augmenting large language models (LLMs) with browsing tools substantially improves their potential as deep search agents to solve complex, real-world tasks. Yet, open LLMs still perform poorly in such settings due to limited long-horizon…
Retrieval-augmented generation over semi-structured sources such as HTML is constrained by a mismatch between document structure and the flat, sequence-based interfaces of today's embedding and generative models. Retrieval pipelines often…
Detectives frequently engage in information detection and reasoning simultaneously when making decisions across various cases, especially when confronted with a vast amount of information. With the rapid development of large language…
The search for research datasets is as important as laborious. Due to the importance of the choice of research data in further research, this decision must be made carefully. Additionally, because of the growing amounts of data in almost…