Showing papers on "Human–computer information retrieval published in 2015"

The Nature of Relevance in Information Retrieval: An Empirical Study

Abstract: Experimental research in information retrieval (IR) depends on the idea of relevance. Because of its key role in IR, recent questions about relevance have raised issues of methodological concern and have shaken the philosophical foundations of IR theory development. Despite an existing set of theoretical definitions of this concept, our understanding of relevance from users' perspectives is still limited. Using naturalistic inquiry methodology, this article reports an empirical study of user-based relevance interpretations. A model is presented that reflects the nature of the thought processes of users who are evaluating bibliographic citations produced by a document retrieval system. Three major categories of variables affecting relevance assessments-internal context, external context, and problem context-are identified and described. Users' relevance assessments involve multiple layers of interpretations that are derived from individuals' experiences, perceptions, and private knowledge related to the pa...

Spoken content retrieval: beyond cascading speech recognition with text retrieval

Abstract: Spoken content retrieval refers to directly indexing and retrieving spoken content based on the audio rather than text descriptions. This potentially eliminates the requirement of producing text descriptions for multimedia content for indexing and retrieval purposes, and is able to precisely locate the exact time the desired information appears in the multimedia. Spoken content retrieval has been very successfully achieved with the basic approach of cascading automatic speech recognition (ASR) with text information retrieval: after the spoken content is transcribed into text or lattice format, a text retrieval engine searches over the ASR output to find desired information. This framework works well when the ASR accuracy is relatively high, but becomes less adequate when more challenging real-world scenarios are considered, since retrieval performance depends heavily on ASR accuracy. This challenge leads to the emergence of another approach to spoken content retrieval: to go beyond the basic framework of cascading ASR with text retrieval in order to have retrieval performances that are less dependent on ASR accuracy. This overview article is intended to provide a thorough overview of the concepts, principles, approaches, and achievements of major technical contributions along this line of investigation. This includes five major directions: 1) Modified ASR for Retrieval Purposes: cascading ASR with text retrieval, but the ASR is modified or optimized for spoken content retrieval purposes; 2) Exploiting the Information not present in ASR outputs: to try to utilize the information in speech signals inevitably lost when transcribed into phonemes and words; 3) Directly Matching at the Acoustic Level without ASR: for spoken queries, the signals can be directly matched at the acoustic level, rather than at the phoneme or word levels, bypassing all ASR issues; 4) Semantic Retrieval of Spoken Content: trying to retrieve spoken content that is semantically related to the query, but not necessarily including the query terms themselves; 5) Interactive Retrieval and Efficient Presentation of the Retrieved Objects: with efficient presentation of the retrieved objects, an interactive retrieval process incorporating user actions may produce better retrieval results and user experiences.

Fielded Sequential Dependence Model for Ad-Hoc Entity Retrieval in the Web of Data

Abstract: Previously proposed approaches to ad-hoc entity retrieval in the Web of Data (ERWD) used multi-fielded representation of entities and relied on standard unigram bag-of-words retrieval models. Although retrieval models incorporating term dependencies have been shown to be significantly more effective than the unigram bag-of-words ones for ad hoc document retrieval, it is not known whether accounting for term dependencies can improve retrieval from the Web of Data. In this work, we propose a novel retrieval model that incorporates term dependencies into structured document retrieval and apply it to the task of ERWD. In the proposed model, the document field weights and the relative importance of unigrams and bigrams are optimized with respect to the target retrieval metric using a learning-to-rank method. Experiments on a publicly available benchmark indicate significant improvement of the accuracy of retrieval results by the proposed model over state-of-the-art retrieval models for ERWD.

Scalable Mobile Image Retrieval by Exploring Contextual Saliency

Abstract: Nowadays, it is very convenient to capture photos by a smart phone. As using, the smart phone is a convenient way to share what users experienced anytime and anywhere through social networks, it is very possible that we capture multiple photos to make sure the content is well photographed. In this paper, an effective scalable mobile image retrieval approach is proposed by exploring contextual salient information for the input query image. Our goal is to explore the high-level semantic information of an image by finding the contextual saliency from multiple relevant photos rather than solely using the input image. Thus, the proposed mobile image retrieval approach first determines the relevant photos according to visual similarity, then mines salient features by exploring contextual saliency from multiple relevant images, and finally determines contributions of salient features for scalable retrieval. Compared with the existing mobile-based image retrieval approaches, our approach requires less bandwidth and has better retrieval performance. We can carry out retrieval with <200-B data, which is <5% of existing approaches. Most importantly, when the bandwidth is limited, we can rank the transmitted features according to their contributions to retrieval. Experimental results show the effectiveness of the proposed approach.

Non-rigid 3D shape retrieval

Abstract: Non-rigid 3D shape retrieval has become a research hotpot in communities of computer graphics, computer vision, pattern recognition, etc. In this paper, we present the results of the SHREC'15 Track: Non-rigid 3D Shape Retrieval. The aim of this track is to provide a fair and effective platform to evaluate and compare the performance of current non-rigid 3D shape retrieval methods developed by different research groups around the world. The database utilized in this track consists of 1200 3D watertight triangle meshes which are equally classified into 50 categories. All models in the same category are generated from an original 3D mesh by implementing various pose transformations. The retrieval performance of a method is evaluated using 6 commonly-used measures (i.e., PR-plot, NN, FT, ST, E-measure and DCG.). Totally, there are 37 submissions and 11 groups taking part in this track. Evaluation results and comparison analyses described in this paper not only show the bright future in researches of non-rigid 3D shape retrieval but also point out several promising research directions in this topic.

Introduction to Information Retrieval and Quantum Mechanics

Abstract: This book introduces the quantum mechanical framework to information retrieval scientists seeking a new perspective on foundational problems As such, it concentrates on the main notions of the quantum mechanical framework and describes an innovative range of concepts and tools for modeling information representation and retrieval processes The book is divided into four chapters Chapter 1 illustrates the main modeling concepts for information retrieval (including Boolean logic, vector spaces, probabilistic models, and machine-learning based approaches), which will be examined further in subsequent chapters Next, chapter 2 briefly explains the main concepts of the quantum mechanical framework, focusing on approaches linked to information retrieval such as interference, superposition and entanglement Chapter 3 then reviews the research conducted at the intersection between information retrieval and the quantum mechanical framework The chapter is subdivided into a number of topics, and each description ends with a section suggesting the most important reference resources Lastly, chapter 4 offers suggestions for future research, briefly outlining the most essential and promising research directions to fully leverage the quantum mechanical framework for effective and efficient information retrieval systems This book is especially intended for researchers working in information retrieval, database systems and machine learning who want to acquire a clear picture of the potential offered by the quantum mechanical framework in their own research area Above all, the book offers clear guidance on whether, why and when to effectively use the mathematical formalism and the concepts of the quantum mechanical framework to address various foundational issues in information retrieval

Information Retrieval with Verbose Queries

Abstract: Recently, the focus of many novel search applications shifted from short keyword queries to verbose natural language queries. Examples include question answering systems and dialogue systems, voice search on mobile devices and entity search engines like Facebook's Graph Search or Google's Knowledge Graph. However the performance of textbook information retrieval techniques for such verbose queries is not as good as that for their shorter counterparts. Thus, effective handling of verbose queries has become a critical factor for adoption of information retrieval techniques in this new breed of search applications. Over the past decade, the information retrieval community has deeply explored the problem of transforming natural language verbose queries using operations like reduction, weighting, expansion, reformulation and segmentation into more effective structural representations. However, thus far, there was not a coherent and organized tutorial on this topic. In this tutorial, we aim to put together various research pieces of the puzzle, provide a comprehensive and structured overview of various proposed methods, and also list various application scenarios where effective verbose query processing can make a significant difference.

Temporal Information Retrieval

Abstract: Temporal dynamics and how they impact upon various components of information retrieval IR systems have received a large share of attention in the last decade. In particular, the study of relevance in information retrieval can now be framed within the so-called temporal IR approaches, which explain how user behavior, document content and scale vary with time, and how we can use them in our favor in order to improve retrieval effectiveness. This survey provides a comprehensive overview of temporal IR approaches, centered on the following questions: what are temporal dynamics, why do they occur, and when and how to leverage temporal information throughout the search cycle and architecture. We first explain the general and wide aspects associated to temporal dynamics by focusing on the web domain, from content and structural changes to variations of user behavior and interactions. Next, we pinpoint several research issues and the impact of such temporal characteristics on search, essentially regarding processing dynamic content, temporal query analysis and time-aware ranking. We also address particular aspects of temporal information extraction for instance, how to timestamp documents and generate temporal profiles of text. To this end, we present existing temporal search engines and applications in related research areas, e.g., exploration, summarization, and clustering of search results, as well as future event retrieval and prediction, where the time dimension also plays an important role.

Semantic-Aware Co-Indexing for Image Retrieval

Abstract: In content-based image retrieval, inverted indexes allow fast access to database images and summarize all knowledge about the database. Indexing multiple clues of image contents allows retrieval algorithms search for relevant images from different perspectives, which is appealing to deliver satisfactory user experiences. However, when incorporating diverse image features during online retrieval, it is challenging to ensure retrieval efficiency and scalability. In this paper, for large-scale image retrieval, we propose a semantic-aware co-indexing algorithm to jointly embed two strong cues into the inverted indexes: 1) local invariant features that are robust to delineate low-level image contents, and 2) semantic attributes from large-scale object recognition that may reveal image semantic meanings. Specifically, for an initial set of inverted indexes of local features, we utilize semantic attributes to filter out isolated images and insert semantically similar images to this initial set. Encoding these two distinct and complementary cues together effectively enhances the discriminative capability of inverted indexes. Such co-indexing operations are totally off-line and introduce small computation overhead to online retrieval, because only local features but no semantic attributes are employed for the query. Hence, this co-indexing is different from existing image retrieval methods fusing multiple features or retrieval results. Extensive experiments and comparisons with recent retrieval methods manifest the competitive performance of our method.

An ontology-based CBR approach for personalized itinerary search systems for sustainable urban freight transport

Abstract: Novel information retrieval system for personalized itinerary search in urban freight transport.Integration of CBR, Choquet integral and ontology for personalized retrieval mechanism.User-oriented ontologies to extract knowledge from the overwhelming urban traffic information.Introduction of a new similarity measures method in the retrieval step of the CBR.Considers textual and numerical features for improved quality of information retrieval. This paper presents a novel information retrieval approach for personalized itinerary search in urban freight transport systems. The proposed approach is based on the integration of three techniques: Case Base Reasoning, Choquet integral and ontology. It has the following advanced features: (1) user-oriented ontology is used as source of knowledge to extract pertinent information about stakeholder's preferences and needs; (2) semantic web rule language is considered to provide the system with enhanced semantic capabilities and support personalized case representation; (3) a CBR-personalized retrieval mechanism is designed to provide a user with an optimum itinerary that meets his personal needs and preferences. The above features lead to a personalized and optimum itinerary search that meets the user's needs as specified in their queries such as fuel consumption, environmental impact, optimum route, time management etc. This has the potential to effectively manage fright movement according to stakeholder's needs and alleviate congestion problems in urban areas. The proposed intelligent decision support system (Onto-CBR) is implemented to an itinerary search problem for freight transportation users in urban areas. Its performance is further compared to an itineraries search system that was proposed by the authors in an earlier publication. Both approaches are compared in terms of their ability to meet user's personal preferences and achieve accuracy in case retrieval. The experimental results showed the ability of the proposed system to improve the accuracy of case retrieval and reduce retrieval time prominently. The ability of the proposed system tailor the search to stakeholders needs, improve the accuracy of case retrieval and facilitate the search process are among the main positive features of the proposed intelligent decision support system.

The use of text retrieval and natural language processing in software engineering

Abstract: This technical briefing presents the state of the art Text Retrieval and Natural Language Processing techniques used in Software Engineering and discusses their applications in the field.

Finding people, papers, and posts: Vertical search algorithms and evaluation

Abstract: There is a growing diversity of information access applications. While general web search has been dominant in the past few decades, a wide variety of so-called vertical search tasks and applications have come to the fore. Vertical search is an often used term for search that targets specific content. Examples include YouTube video search, Facebook graph search, Spotify music recommendation, product search, expertise retrieval, and scientific literature search. In a vertical search application, typically, some background knowledge is available about the context in which search is taking place. We may know something about the user population, about the tasks they wish to perform, about their information needs, and about the information objects in the collection we make available to them. This knowledge can inform adaptation of retrieval algorithms and evaluation methodology, to provide a better ranking of information objects, or to organize search results more effectively. This dissertation showcases the need, as well as many opportunities, to leverage background knowledge in three vertical search scenarios: finding people, finding scientific papers, and finding microblog posts. Its five research chapters provide pointers on how background knowledge may be used to help understand user information needs, organize search results, evaluate retrieval algorithms, and automatically generate ground truth.

Care episode retrieval: distributional semantic models for information retrieval in the clinical domain.

Abstract: Patients' health related information is stored in electronic health records (EHRs) by health service providers. These records include sequential documentation of care episodes in the form of clinical notes. EHRs are used throughout the health care sector by professionals, administrators and patients, primarily for clinical purposes, but also for secondary purposes such as decision support and research. The vast amounts of information in EHR systems complicate information management and increase the risk of information overload. Therefore, clinicians and researchers need new tools to manage the information stored in the EHRs. A common use case is, given a - possibly unfinished - care episode, to retrieve the most similar care episodes among the records. This paper presents several methods for information retrieval, focusing on care episode retrieval, based on textual similarity, where similarity is measured through domain-specific modelling of the distributional semantics of words. Models include variants of random indexing and the semantic neural network model word2vec. Two novel methods are introduced that utilize the ICD-10 codes attached to care episodes to better induce domain-specificity in the semantic model. We report on experimental evaluation of care episode retrieval that circumvents the lack of human judgements regarding episode relevance. Results suggest that several of the methods proposed outperform a state-of-the art search engine (Lucene) on the retrieval task.

Image-Mediated Learning for Zero-Shot Cross-Lingual Document Retrieval

Abstract: We propose an image-mediated learning approach for cross-lingual document retrieval where no or only a few parallel corpora are available. Using the images in image-text documents of each language as the hub, we derive a common semantic subspace bridging two languages by means of generalized canonical correlation analysis. For the purpose of evaluation, we create and release a new document dataset consisting of three types of data (English text, Japanese text, and images). Our approach substantially enhances retrieval accuracy in zero-shot and few-shot scenarios where text-to-text examples are scarce.

Bibliometrics-aided retrieval: where information retrieval meets scientometrics

Abstract: This paper attempts to sketch the interrelation between information retrieval and scientometrics pointing at possible synergy effects provided by some recently developed bibliometric methods in the context of subject delineation and clustering. Examples of specific search strategies based on both traditional retrieval techniques and bibliometric methods are used to illustrate this approach. Special attention is paid to hybrid techniques and the use of `core documents'. The latter ones are defined merely on the basis of bibliometric similarities, but have by definition properties that make `core documents' also interesting and attractive for information retrieval.

Information retrieval for ecological syntheses.

Abstract: Research syntheses are increasingly being conducted within the fields of ecology and environmental management. Information retrieval is crucial in any synthesis in identifying data for inclusion whilst potentially reducing biases in the dataset gathered, yet the nature of ecological information provides several challenges when compared with medicine that should be considered when planning and undertaking searches. We present ten recommendations for anyone considering undertaking information retrieval for ecological research syntheses that highlight the main differences with medicine and, if adopted, may help reduce biases in the dataset retrieved, increase search efficiency and improve reporting standards. They are as follows: (1) plan for information retrieval at an early stage, (2) identify and use sources of help, (3) clearly define the question to be addressed, (4) ensure that provisions for managing, recording and reporting the search are in place, (5) select an appropriate search type, (6) identify sources to be used, (7) identify limitations of the sources, (8) ensure that the search vocabulary is appropriate, (9) identify limits and filters that can help direct the search, and (10) test the strategy to ensure that it is realistic and manageable. These recommendations may be of value for other disciplines where search infrastructures are not yet sufficiently well developed. Copyright © 2014 John Wiley & Sons, Ltd.

Information Retrieval as Card Playing: A Formal Model for Optimizing Interactive Retrieval Interface

Abstract: We propose a novel formal model for optimizing interactive information retrieval interfaces To model interactive retrieval in a general way, we frame the task of an interactive retrieval system as to choose a sequence of interface cards to present to the user At each interaction lap, the system's goal is to choose an interface card that can maximize the expected gain of relevant information for the user while minimizing the effort of the user with consideration of the user's action model and any desired constraints on the interface card We show that such a formal interface card model can not only cover the Probability Ranking Principle for Interactive Information Retrieval as a special case by making multiple simplification assumptions, but also be used to derive a novel formal interface model for adaptively optimizing navigational interfaces in a retrieval system Experimental results show that the proposed model is effective in automatically generating adaptive navigational interfaces, which outperform the baseline pre-designed static interfaces

Image retrieval based on multi-concept detector and semantic correlation

Abstract: With the rapid development of future network, there has been an explosive growth in multimedia data such as web images. Hence, an efficient image retrieval engine is necessary. Previous studies concentrate on the single concept image retrieval, which has limited practical usability. In practice, users always employ an Internet image retrieval system with multi-concept queries, but, the related existing approaches are often ineffective because the only combination of single-concept query techniques is adopted. At present semantic concept based multi-concept image retrieval is becoming an urgent issue to be solved. In this paper, a novel Multi-Concept image Retrieval Model (MCRM) based on the multi-concept detector is proposed, which takes a multi-concept as a whole and directly learns each multi-concept from the rearranged multi-concept training set. After the corresponding retrieval algorithm is presented, and the log-likelihood function of predictions is maximized by the gradient descent approach. Besides, semantic correlations among single-concepts and multiconcepts are employed to improve the retrieval performance, in which the semantic correlation probability is estimated with three correlation measures, and the visual evidence is expressed by Bayes theorem, estimated by Support Vector Machine (SVM). Experimental results on Corel and IAPR data sets show that the approach outperforms the state-of-the-arts. Furthermore, the model is beneficial for multi-concept retrieval and difficult retrieval with few relevant images.

Overview of the SBS 2015 Interactive Track

Abstract: Users looking for books online are confronted with both professional meta-data and user-generated content. The goal of the Interactive Social Book Search Track was to investigate how users used these two sources of information, when looking for books in a leisure context. To this end participants recruited by four teams performed two different tasks using one of two book-search interfaces. Additionally one of the two interfaces also investigated whether user performance can be improved by providing a user-interface that supports multiple search stages.

Overview of the CLEF 2015 Social Book Search Lab

Abstract: The Social Book Search SBS Lab investigates book search in scenarios where users search with more than just a query, and look for more than objective metadata. Real-world information needs are generally complex, yet almost all research focuses instead on either relatively simple search based on queries or recommendation based on profiles. The goal is to research and develop techniques to support users in complex book search tasks. The SBS Lab has two tracks. The aim of the Suggestion Track is to develop test collections for evaluating ranking effectiveness of book retrieval and recommender systems. The aim of the Interactive Track is to develop user interfaces that support users through each stage during complex search tasks and to investigate how users exploit professional metadata and user-generated content.

Retrieval‐Based Learning: Research at the Interface between Cognitive Science and Education

Abstract: This essay reviews research on retrieval-based learning, which refers to the general finding that practicing active retrieval enhances long-term, meaningful learning. The idea that retrieval promotes learning has existed for centuries, and the first experiments demonstrating retrieval practice effects were carried out near the beginning of experimental research on learning and memory. Interest in retrieval practice was sporadic during the past century, but the topic has received intense interest in recent years as part of a broader movement to integrate research from cognitive science with educational practice. The essay provides a selective review of foundational research and contemporary work that has been aimed at deepening our theoretical knowledge about retrieval practice and integrating retrieval-based learning within educational activities and settings. Keywords: retrieval; active learning; meaningful learning; education; metacognition

Understanding tourists' collaborative information retrieval behavior to inform design

Abstract: With the rapid development of information and communication technologies, people are increasingly referring to web information to assist in their travel planning and decision making. Research shows that people conduct collaborative information searches while planning their travel activities online. However, little is known in depth about tourists' online collaborative search. This study examines tourists' collaborative information search behavior in detail, including their search stages, online search strategies, and information flow breakdowns. The data for analysis included pre- and postsearch questionnaires, web search and chat logs, and postsearch interviews. A model of tourist collaborative information retrieval was developed. The model identified collaborative planning, collaborative information searching, sharing of information, and collaborative decision making as four stages of tourists' collaborative search. The results show that tourists collaborated by planning their search strategies, dividing search tasks into subtasks and allocating workload, using search queries and URL links recommended by teammates, and discussing search results together. Related personal knowledge and experiences appeared important in trip planning and collaborative information search. During the collaborative search, tourists also encountered various information flow breakdowns in different search stages. These were classified and their effects on collaborative information search were reported. Implications for system design in support of collaborative information retrieval in travel contexts are also discussed.

Supporting the Modern Polyglot: A Comparison of Multilingual Search Interfaces

Abstract: The unrelenting rise in online user diversification has generated tremendous new challenges for search system providers. Among these, the need to address multiple user language abilities and preferences is paramount. The majority of research on multilingual search has so far focused on improving retrieval and translation techniques in cross-language information retrieval. However, less research has focused on the human-computer interaction aspects of multilingual search, particularly in terms of multilingual result display interfaces. To address this research gap, this paper presents a comparison of 5 different search interface designs for multilingual search. We analyze and evaluate these interfaces through a crowd-based experiment involving 885 participants. Our results show that the common approach of interleaving multilingual results is in fact the least preferred, whereas single-page displays with clear language separation are most preferred. In addition, we show that user proficiency and search content type play an important role in user preferences, and that different interfaces elicit different user behaviors.

Multimedia information retrieval based on late semantic fusion approaches- experiments on a wikipedia image collection

Abstract: This paper proposes an improved system using a textual pre-filtering combined with an image re-ranking in a Multimedia Information Retrieval task. Three different sub systems Text based subsystem, content based subsystem and fusion of both subsystems is used for multimedia information retrieval processes to overcome semantic gap in a given query. To get the accurate result we use Multimedia information retrieval on publicly available Image CLEF Wikipedia Collection. Keywords—Content-based information retrieval, multimedia information, multimedia retrieval, text-based image retrieval

Retrieving haystacks: a data driven information needs model for faceted search

Abstract: The research aim was to develop an understanding of information need characteristics for word co-occurrence-based search result filters (facets). No prior research has been identified into what enterprise searchers may find useful for exploratory search and why. Various word co-occurrence techniques were applied to results from sample queries performed on industry membership content. The results were used in an international survey of 54 practising petroleum engineers from 32 organizations. Subject familiarity, job role, personality and query specificity are possible causes for survey response variation. An information needs model is presented: Broad, Rich, Intriguing, Descriptive, General, Expert and Situational (BRIDGES). This may help professionals to more effectively meet their information needs and stimulate new needs, improving a system's ability to facilitate serendipity. This research has implications for faceted search in enterprise search and digital library deployments.