Entity Centric Information Retrieval

The paper introduces a model for interactive image retrieval utilising the geometrical framework of information retrieval (IR). We tackle the problem of image retrieval based on an expressive user information need in form of a textual-visual query, where a user is attempting to find an image similar to the picture in their mind during querying. The user information need is expressed using guided visual feedback based on Information Foraging which lets the user perception embed within the model via semantic Hilbert space (SHS). This framework is based on the mathematical formalism of quantum probabilities and aims to understand the relationship between user textual and image input, where the image in the input is considered a form of visual feedback. We propose SHS, a quantum-inspired approach where the textual-visual query is regarded analogously to a physical system that allows for modelling different system states and their dynamic changes thereof based on observations (such as queries, relevance judgements). We will be able to learn the input multimodal representation and relationships between textual-image queries for retrieving images. Our experiments are conducted on the MIT States and Fashion200k datasets that demonstrate the effectiveness of finding particular images autocratically when the user inputs are semantically expressive.

This minitrack addresses a broad range of issues related to the design of the next generation of information retrieval systems, especially related to improving web search effectiveness from the user perspective. The core of this research is how to help the user access and make use of digital data. These issues are of prime interest to researchers, developers, and information managers. The multidisciplinary nature of this emerging area allows us to engage as a community of participants with a wide range of interests, including retrieval design, HCI, information seeking behavior, and information management. Information Retrieval supports the computerized search of large document and digital media collections (millions or billions of items) to select small subsets of those documents relevant to a user's information need. Such algorithms are the basis for internet search engines and question-answering systems. At the same time, we know relatively little about the users who deal with a multi-billion-page Web. Further research is needed to address the user issues related to effectiveness and quality of experience when interacting with search engines. New metrics and methodologies are needed for retrieval evaluation as both the data sets of interest and user expectations grow exponentially. A focus on the user perspective allows us to align the user focus and the system focus in a multi-disciplinary forum that includes theoretical foundations, evaluation measures, methodologies, case studies and user study results. This year in the Information Access & Retrieval MiniTrack we include papers that cover this multidisciplinary approach. One paper, Appropriate Software Components for Mobile End-User Devices Executive Information Systems Up Close and Personalized as an Example, presents design principles for the design of interfaces for mobile devices. Two papers, Building Support for Web Information Gathering Tasks, and Characterizing Queries in Different Search Tasks, explore user behavior related to web search. The first paper examines characteristics of search specific to longer gathering tasks. The second of these papers explores the more general issue of types of tasks for a range of web information needs. The paper, Determinants of Information Channel Choice: The Impact of Task Complexity and Dispositional Character Traits, is a behavioral study of how made channel choice. The final paper, Cobre: A Comparative Book Reader for Los Primeros Libros, presents a novel reader model based on film strip metaphor. 2012 45th Hawaii International Conference on System Sciences

Relevance is the central concept of information retrieval. Although its important role is unanimously accepted among researchers, numerous different definitions of the term have emerged over the years. Considerable effort has been put into creating consistent and universally applicable descriptions of relevance in the form of relevance frameworks. Across these various formal systems of relevance, a wide range of relevance criteria has been identified. The probably most frequently used single criterion, that in some applications even becomes a synonym for relevance, is topicality. It expresses a document's topical overlap with the user's information need. For textual resources, it is often estimated based on term co-occurrences between query and document. There is, however, a significant number of further noteworthy relevance criteria. Prominent specimen are: (Currency) determines how recent and up to date the document is. Outdated information may have become invalid over time.(Availability) expresses how easy it is to obtain the document. Users might not want to invest more than a threshold amount of resources (e.g., disk space, downloading time or money) to get the document.(Readability) describes the document's readability and understandability. A document with a high topical relevance towards a given information need can become irrelevant if the user is not able to extract the desired information from it.(Credibility) contains criteria such as the document author's expertise, the publication's reputation and the document's general trustworthiness.(Novelty) describes the document's contribution to satisfying an information need with respect to the user's context. E.g., previous search results or general knowledge about the domain.It is evident that these criteria can have very different scopes. Some of them are static characteristics of the document or the author, others depend on the concrete information need at hand or even the user's search context. Currently, state-of-the-art retrieval models often treat relevance (regardless which interpretation of the term was chosen) as an atomic concept that can be expressed through topical overlap between document and query or a plain linear combination of multiple scores. Considering the broad audiences a web search engine has to serve, such a method does not seem optimal as the concrete composition of relevance will vary from person to person depending on social and educational context. Furthermore, each individual can be expected to have situational preference for certain combinations of relevance facets depending on the information need at hand. We investigate combination schemes which respect the dimension-specific relevance distributions. In particular, we developed a risk-aware method of combining relevance criteria inspired by the economic Portfolio theory. As a first stage, we applied this method for result set diversification across dimensions.

User studies in information science have recognised relevance as a multidimensional construct. An implication of multidimensional relevance is that a user's information need should be modeled by multiple data structures to represent different relevance dimensions. While the extant literature has attempted to model multiple dimensions of a user's information need, the fundamental assumption that a multidimensional model is better than a uni-dimensional model has not been addressed. This study seeks to test this assumption. Our results indicate that a retrieval system that models both topicality and the novelty dimension of a users' information need outperforms a system with a uni-dimensional model.

Personalized Web search is an effective means of providing specific results to different users when they submit the same query. How to obtain user's real-time information need is a key issue in personalized search. Existing methods concentrate more on the building user profile based on Web pages/documents which affects the efficiency of search engine. In addition, dynamics of user profile is often ignored. To address this problem, we introduce an approach that captures the user context to accurately provide preferences of users for effective personalized search in this paper. First, short-term query context is generated from Web-snippets to play a role of semantic background of user's search behavior, identifying related concepts of the query. Second, user context snap is built based on query context according to user's interactive search behavior. Finally, evolution of user context is considered by introducing forgetting factor to merge the independent user context snap in a user session. The experimental results fully demonstrate that our approach can successfully build user context according to individual user information need.

There is a growing need to access and retrieve relevant information across media, across languages and across modalities. The research context concerning information access and retrieval aims at modelling, designing and implementing systems able to provide a fast and effective content-based access to a large amount of multimedia information. The aim of such systems is to estimate the relevance of documents to a user information need. This is a very hard and complex task due to several distinct reasons that a large volume of research has attempted to analyse and tackle. Information Retrieval (IR) can be considered as the first historical research area aimed at defining systems for the automatic access to huge amounts of information (together with DBMSs whose main aim is to manage and access huge amounts of data).

This research is motivated by the lack of empirical studies that discuss the existence of libraries as a fulfillment of information needs, especially in the secretariat library of the West Sumatra provincial DPRD. The purpose of this study is to describe the extent of the relationship between the Existence of Libraries and the Information Needs of Users. This type of research is quantitative with a descriptive method. The population in this study were all registered users at the Secretariat Library of the West Sumatra Provincial DPRD. Samples were taken using simple random sampling, and data were collected through observation, interviews, and questionnaires. The results of the analysis showed that the existence of the library was in the good category with an average score of 3.01. The information needs of users were in the good category with an average score of 2.93. Based on the Pearson correlation test, it showed a positive relationship between the existence of the library and the information needs of users of 0.643, including in the interval scale of 0.60-0.799. This shows that the existence of the library has a significant relationship with the information needs of users. These results emphasize that the existence of libraries has a direct influence on the information needs of users, especially institutional libraries where users are members of the institution who have jobs in certain categories.

The explosive growth of information on the web demands effective intelligent search and filtering methods. Consequently, techniques have been developed that extract conceptual information from the document and use the conceptual information in the user profile to form part of the user's information intent from his/her query. In a similar vein, we build the profile without user interaction, automatically monitoring the user's browsing habits. These profiles, in turn, are used to automatically learn the semantic context of user's information need. These sets of categories can serve as a context to disambiguate the words in the user's query. In this paper, we present a framework for assisting the user in one of the most difficult information retrieval tasks, i.e., that of formulating an effective search query. Our experimental results show that implicit measurements of user interests, combined with the semantic knowledge embedded in a concept hierarchy, can be used effectively to infer the user context and to improve the results of information retrieval.

A set of words is often insufficient to express a user's information need. In order to account for various information needs associated with a query, diversification seems to be a reasonable strategy. By diversifying the result set, we increase the probability of results being relevant to the user's information needs when the given query is ambiguous. A diverse result set must contain a set of documents that cover various subtopics for a given query. We propose a graph based method which exploits the link structure of the web to return a ranked list that provides complete coverage for a query. Our method not only provides diversity to the results set, but also avoids excessive redundancy. Moreover, the probability of relevance of a document is conditioned on the documents that appear before it in the result list. We show the effectiveness of our method by comparing it with a query-likelihood model as the baseline.

Our objective is to enhance the effectiveness and efficiency of ad hoc and routing retrieval for large scale textbases. Effective retrieval means ranking relevant answer documents of a user's information need high on the output list. Our text processing and retrieval system PIRCS (Probabilisitc Indexing and Retrieval -Components- System) handles English text in a domain independent fashion, and is based on a probabilistic model but extended with the concept of document components as discussed in our last year's site report. Our focus for enhancing effectiveness remains on three areas: 1) improvements on document representation; 2) combination of retrieval algorithms; and 3) network implementation with learning capabilities. Using representation with more restricted contexts such as phrases or subdocument units help to decrease ambiguity in both retrieval and learning. Combining evidences from different retrieval algorithms is known to improve results. Viewing retrieval in a network helps to implement query-focused and document-focused retrieval and feedback, as well as query expansion.

As the Web has become one of the biggest repository of knowledge easily accessible for everyone, information retrieval has stopped to be an exclusive field of information sciences specialists, and it has become a field related with any person. Although users do not have to know information retrieval techniques, the proposal of this work is to improve query results by using a that implements these techniques. For this, a semantic refiner is proposed. This refiner acts as a specialist in information sciences and prepares, using linguistic resources, an appropriate search strategy that represents the user's information need. The semantic refinement consists on three steps. First, it guides the user for sense disambiguation of the words submitted by him. Then, it allows the user to select concepts hierarchically related to reduce the amount of documents to retrieve. Finally, it expands semantically concepts to increase the amount of documents to be retrieved. A prototype is implemented using WordNet as linguistic resource, and experimental results are analyzed.

As a method for information retrieval (IR) on the Web, search engines have become the tool of choice for most online users. However, despite the variety of next generation approaches to Web search we have seen recently (e.g. [1,2]), the problems of information overload, vague user queries and spam still have the effect that many search sessions end in user frustration. Generally search engines are criticised for returning result lists that have low precision, where the user's information need is not satisfied by any of the returned result pages.

The Information Retrieval (IR) problem can be described as the quest to find the set of relevant information objects corresponding to a given information need, which is represented by a request. IR begins with a user who wishes to satisfy an information need. The information need is typically formulated in the form of a request, denoted by q. The intention is that the request q be as good as possible description of the information need N. The information being queried is modelled as a set of information carriers, or documents. An often used premise in IR is the following: if a given document d is about the request q, then there is a high likelihood that d is relevant with respect to the associated information need. Thus, the IR problem is reduced to deciding the aboutness relation between documents and requests. Many IR models have been developed, and there is a wide variation in how they determine aboutness. A common approach is to equate aboutness with overlap, meaning if there is sufficient overlap between the document and the query, the document is deemed to be about the query. The degree of overlap determined by the retrieval model is usually expressed as a real number between zero (no overlap) and unity (complete overlap). In most models, “sufficient” overlap is not prescribed by the model but by experimentation within a given IR setting. Such experimentation may lead to the conclusion, say, that sufficient overlap is apparent when the overlap measure is greater than α, 0 < α ≤ 1. The value α varies from setting to setting.

This paper describes and evaluates the use of Geographical Knowledge Re-Ranking, Linguistic Processing, and Query Expansion techniques to improve Geographical Information Retrieval effectiveness. Geographical Knowledge Re-Ranking is performed with Geographical Gazetteers and conservative Toponym Disambiguation techniques that boost the ranking of the geographically relevant documents retrieved by standard state-of-the-art Information Retrieval algorithms. Linguistic Processing is performed in two ways: 1) Part-of-Speech tagging and Named Entity Recognition and Classification are applied to analyze the text collections and topics to detect toponyms, 2) Stemming (Porter’s algorithm) and Lemmatization are also applied in combination with default stopwords filtering. The Query Expansion methods tested are the Bose-Einstein (Bo1) and Kullback-Leibler term weighting models. The experiments have been performed with the English Monolingual test collections of the GeoCLEF evaluations (from years 2005, 2006, 2007, and 2008) using the TF-IDF, BM25, and InL2 Information Retrieval algorithms over unprocessed texts as baselines. The experiments have been performed with each GeoCLEF test collection (25 topics per evaluation) separately and with the fusion of all these collections (100 topics). The results of evaluating separately Geographical Knowledge Re-Ranking, Linguistic Processing (lemmatization, stemming, and the combination of both), and Query Expansion with the fusion of all the topics show that all these processes improve the Mean Average Precision (MAP) and RPrecision effectiveness measures in all the experiments and show statistical significance over the baselines in most of them. The best results in MAP and RPrecision are obtained with the InL2 algorithm using the following techniques: Geographical Knowledge Re-Ranking, Lemmatization with Stemming, and Kullback-Leibler Query Expansion. Some configurations with Geographical Knowledge Re-Ranking, Linguistic Processing and Query Expansion have improved the MAP of the best official results at GeoCLEF evaluations of 2005, 2006, and 2007.KeywordsInformation retrievalGeographical gazetteersNatural language processingToponym disambiguationQuery expansionEfectiveness measures

The objective of the paper is to amalgamate theories of text retrieval from various research traditions into a cognitive theory for information retrieval interaction. Set in a cognitive framework, the paper outlines the concept of polyrepresentation applied to both the user's cognitive space and the information space of IR systems. The concept seeks to represent the current user's information need, problem state, and domain work task or interest in a structure of causality. Further, it implies that we should apply different methods of representation and a variety of IR techniques of different cognitive and functional origin simultaneously to each semantic full‐text entity in the information space. The cognitive differences imply that by applying cognitive overlaps of information objects, originating from different interpretations of such objects through time and by type, the degree of uncertainty inherent in IR is decreased. Polyrepresentation and the use of cognitive overlaps are associated with, but not identical to, data fusion in IR. By explicitly incorporating all the cognitive structures participating in the interactive communication processes during IR, the cognitive theory provides a comprehensive view of these processes. It encompasses the ad hoc theories of text retrieval and IR techniques hitherto developed in mainstream retrieval research. It has elements in common with van Rijsbergen and Lalmas' logical uncertainty theory and may be regarded as compatible with that conception of IR. Epistemologically speaking, the theory views IR interaction as processes of cognition, potentially occurring in all the information processing components of IR, that may be applied, in particular, to the user in a situational context. The theory draws upon basic empirical results from information seeking investigations in the operational online environment, and from mainstream IR research on partial matching techniques and relevance feedback. By viewing users, source systems, intermediary mechanisms and information in a global context, the cognitive perspective attempts a comprehensive understanding of essential IR phenomena and concepts, such as the nature of information needs, cognitive inconsistency and retrieval overlaps, logical uncertainty, the concept of ‘document’, relevance measures and experimental settings. An inescapable consequence of this approach is to rely more on sociological and psychological investigative methods when evaluating systems and to view relevance in IR as situational, relative, partial, differentiated and non‐linear. The lack of consistency among authors, indexers, evaluators or users is of an identical cognitive nature. It is unavoidable, and indeed favourable to IR. In particular, for full‐text retrieval, alternative semantic entities, including Salton et al.'s ‘passage retrieval’, are proposed to replace the traditional document record as the basic retrieval entity. These empirically observed phenomena of inconsistency and of semantic entities and values associated with data interpretation support strongly a cognitive approach to IR and the logical use of polyrepresentation, cognitive overlaps, and both data fusion and data diffusion.