Search Results for « Information Retrieval »

Generative information retrieval (GenIR) is a promising neural retrieval paradigm that formulates document retrieval as a document identifier (docid) generation task, allowing for end-to-end optimization toward a unified global retrieval objective. However, existing GenIR models suffer from token-level misalignment, where models trained to predict the next token often fail to capture document-level relevance effectively. While reinforcement learning-based methods, such as reinforcement learning from relevance feedback (RLRF), aim to address this misalignment through reward modeling, they introduce significant complexity, requiring the optimization of an auxiliary reward function followed by reinforcement fine-tuning, which is computationally expensive and often unstable. To address these challenges, we propose direct document relevance optimization (DDRO), which aligns token-level docid generation with document-level relevance estimation through direct optimization via pairwise ranking, eliminating the need for explicit reward modeling and reinforcement learning. Experimental results on benchmark datasets, including MS MARCO document and Natural Questions, show that DDRO outperforms reinforcement learning-based methods, achieving a 7.4% improvement in MRR@10 for MS MARCO and a 19.9% improvement for Natural Questions. These findings highlight DDRO's potential to enhance retrieval effectiveness with a simplified optimization approach. By framing alignment as a direct optimization problem, DDRO simplifies the ranking optimization pipeline of GenIR models while offering a viable alternative to reinforcement learning-based methods.

Class-tested and coherent, this textbook teaches classical and web information retrieval, including web search and the related areas of text classification and text clustering from basic concepts. It gives an up-to-date treatment of all aspects of the design and implementation of systems for gathering, indexing, and searching documents; methods for evaluating systems; and an introduction to the use of machine learning methods on text collections. All the important ideas are explained using examples and figures, making it perfect for introductory courses in information retrieval for advanced undergraduates and graduate students in computer science. Based on feedback from extensive classroom experience, the book has been carefully structured in order to make teaching more natural and effective. Slides and additional exercises (with solutions for lecturers) are also available through the book's supporting website to help course instructors prepare their lectures.

Many questions cannot be answered simply; their answers must include numerous nuanced details and additional context. Complex Answer Retrieval (CAR) is the retrieval of answers to such questions. In their simplest form, these questions are constructed from a topic entity (e.g., `cheese') and a facet (e.g., `health effects'). While topic matching has been thoroughly explored, we observe that some facets use general language that is unlikely to appear verbatim in answers. We call these low-utility facets. In this work, we present an approach to CAR that identifies and addresses low-utility facets. We propose two estimators of facet utility. These include exploiting the hierarchical structure of CAR queries and using facet frequency information from training data. To improve the retrieval performance on low-utility headings, we also include entity similarity scores using knowledge graph embeddings. We apply our approaches to a leading neural ranking technique, and evaluate using the TREC CAR dataset. We find that our approach perform significantly better than the unmodified neural ranker and other leading CAR techniques. We also provide a detailed analysis of our results, and verify that low-utility facets are indeed more difficult to match, and that our approach improves the performance for these difficult queries.

Information filtering is a name used to describe a variety of processes involving the delivery of information to people who need it.Although this term is appearing quite often in popular and technical articles describing applications such as electronic mail, multimedia distributed systems, and electronic office documents, the distinction between filtering and related processes such as retrieval, routing, categorization, and extraction is often not dear.It is only by making that distinction, however, that the specific research issues associated with filtering can be identified and addressed.A reasonable first step in defining information filtering is to list the typical characteristics or features of this process.The following features are the most commonly mentioned:• An information filtering system is an information system designed for unstructured or semistructured data.This contrasts with a typical database application that involves very structured data, such as employee records.The notion of structure being used here is not only that the data conforms to a format such as a record type description, but also that the fields of the records consist of simple data types with well-defined meanings.It is possible, for example, to define a database type for a complex document, such as a journal article, but the meaning of the text, figure and table components of that type ¢ONNUNle.INI, TIQNI Opllllil~-IMl/Decem}~er 1992/Vo| .35,No.

Theoretical frameworks like the Probability Ranking Principle and its more recent Interactive Information Retrieval variant have guided the development of ranking and retrieval algorithms for decades, yet they are not capable of helping us model problems in Dynamic Information Retrieval which exhibit the following three properties; an observable user signal, retrieval over multiple stages and an overall search intent. In this paper a new theoretical framework for retrieval in these scenarios is proposed. We derive a general dynamic utility function for optimizing over these types of tasks, that takes into account the utility of each stage and the probability of observing user feedback. We apply our framework to experiments over TREC data in the dynamic multi page search scenario as a practical demonstration of its effectiveness and to frame the discussion of its use, its limitations and to compare it against the existing frameworks.

Certain aspects of science communication are of especial importance to information retrieval. The exponential growth of science raises many questions related to increasing specialization. "Quality identification" is suggested as a critical issue. All approaches to information retrieval share a common set of basic problem areas and solutions. Semantics and redundancy are key conceptual issues and give rise to difficulties more likely to be overcome by meticulous thesaurus compilation than by any sudden insight or "breakthrough." The effectiveness of present retrieval capabilities is largely unknown, though certain recent studies are illuminating. Presentation and display to the user are suggested as important approaches to problems of information digestibility.

This workshop brings together experts of communities which often have been perceived as different once: bibliometrics / scientometrics / informetrics on the one side and information retrieval on the other. Our motivation as organizers of the workshop started from the observation that main discourses in both fields are different, that communities are only partly overlapping and from the belief that a knowledge transfer would be profitable for both sides. Bibliometric techniques are not yet widely used to enhance retrieval processes in digital libraries, although they offer value-added effects for users. On the other side, more and more information professionals, working in libraries and archives are confronted with applying bibliometric techniques in their services. This way knowledge exchange becomes more urgent. The first workshop set the research agenda, by introducing in each other methods, reporting about current research problems and brainstorming about common interests. This follow-up workshop continues the overall communication, but also puts one problem into the focus. In particular, we will explore how statistical modelling of scholarship can improve retrieval services for specific communities, as well as for large, cross-domain collections like Mendeley or ResearchGate. This second BIR workshop continues to raise awareness of the missing link between Information Retrieval (IR) and bibliometrics and contributes to create a common ground for the incorporation of bibliometric-enhanced services into retrieval at the scholarly search engine interface.

Lexical ambiguity is a pervasive problem in natural language processing. However, little quantitative information is available about the extent of the problem or about the impact that it has on information retrieval systems. We report on an analysis of lexical ambiguity in information retrieval test collections and on experiments to determine the utility of word meanings for separating relevant from nonrelevant documents. The experiments show that there is considerable ambiguity even in a specialized database. Word senses provide a significant separation between relevant and nonrelevant documents, but several factors contribute to determining whether disambiguation will make an improvement in performance. For example, resolving lexical ambiguity was found to have little impact on retrieval effectiveness for documents that have many words in common with the query. Other uses of word sense disambiguation in an information retrieval context are discussed.

Extracting useful information from the user history to clearly understand informational needs is a crucial feature of a proactive information retrieval system. Regarding understanding information and relevance, Wikipedia can provide the background knowledge that an intelligent system needs. This work explores how exploiting the context of a query using Wikipedia concepts can improve proactive information retrieval on noisy text. We formulate two models that use entity linking to associate Wikipedia topics with the relevance model. Our experiments around a podcast segment retrieval task demonstrate that there is a clear signal of relevance in Wikipedia concepts while a ranking model can improve precision by incorporating them. We also find Wikifying the background context of a query can help disambiguate the meaning of the query, further helping proactive information retrieval.

ND BUSINESSMAN CALVIN MOORES COINED the term information retrieval [10] to describe the process through which a prospective user of information can convert a request for information into a useful collection of references. "Information retrieval," he wrote, "embraces the intellectual aspects of the description of information and its specification for search, and also whatever systems, techniques, or machines that are employed Amarnath Gupta and Ramesh Jain 72 May 1997/Vol. 40, No. 5 COMMUNICATIONS OF THE ACM lar expressions to describe a clip. There is also a deeper reason: The information sought is inherently in the form of imagery that a textual language, however powerful, is unable to express adequately, making query processing inefficient. HE ROLE OF THE EMERGING FIELD OF visual information retrieval (VIR) systems is to go beyond text-based descri