BibSonomy publications for /user/flint63/retrievalTue Jul 22 11:53:40 CEST 2008Communications of the ACM752-58Beyond Relational Databases512008v0805 persistence mobile acm database retrieval management xml device data paper web There is more to data access than SQL.Mon Jul 07 13:47:29 CEST 2008DordrechtText, Speech and Language TechnologyAdvances in Open Domain Question Answering322006v0805 ai language information book answer retrieval springer processing Automated question answering---the ability of a machine to answer questions, simple or complex, posed in ordinary human language---is one of today’s most exciting technological developments. It has all the markings of a disruptive technology, one that is poised to displace the existing search methods and establish new standards for user-centered access to information. This book gives a comprehensive and detailed look at the current approaches to automated question answering. The level of presentation is suitable for newcomers to the field as well as for professionals wishing to study this area and/or to build practical QA systems. The book can serve as a how-to handbook for IT practitioners and system developers. It can also be used to teach advanced graduate courses in Computer Science, Information Science and related disciplines. The readers will acquire in-depth practical knowledge of this critical new technology.Mon Jul 07 13:47:29 CEST 2008DordrechtText, Speech and Language TechnologyMultimodal Intelligent Information Presentation272005information interface v0805 user multimodal springer retrieval interaction ai book Intelligent Multimodal Information Presentation relates to the ability of a computer system to automatically produce interactive information presentations, taking into account the specifics about the user, such as needs, interests and knowledge, and engaging in a collaborative interaction that helps the retrieval of relevant information and its understanding on the part of the user. The volume includes descriptions of some of the most representative recent works on Intelligent Information Presentation and a view of the challenges ahead.Mon Jul 07 13:47:29 CEST 2008DordrechtText, Speech and Language TechnologyEvaluation of Text and Speech Systems372007test v0805 retrieval ai language processing synthesis interface agent dialog speech answer information recognition book In its nine chapters, this book provides an overview of the state-of-the-art and best practice in several sub-fields of evaluation of text and speech systems and components. The evaluation aspects covered include speech and speaker recognition, speech synthesis, animated talking agents, part-of-speech tagging, parsing, and natural language software like machine translation, information retrieval, question answering, spoken dialogue systems, data resources, and annotation schemes. With its broad coverage and original contributions this book is unique in the field of evaluation of speech and language technology.Mon Jul 07 13:47:29 CEST 2008Internet Computing424-34Architectural Alternatives for Information Filtering in Structured Overlays112007middleware ieee p2p v0805 retrieval information paper Content providers are naturally distributed and produce large amounts of new information every day. Peer-to-peer information filtering is a promising approach that offers scalability, adaptivity to high dynamics, and failure resilience. The authors developed two approaches that utilize the chord distributed hash table as the routing substrate, but one stresses retrieval effectiveness, whereas the other relaxes recall guarantees to achieve lower message traffic and thus better scalability. This article highlights the two approaches' main characteristics, presents the issues and trade-offs involved in their design, and compares them in terms of scalability, efficiency, and filtering effectiveness.Mon Jul 07 13:47:29 CEST 2008DordrechtEvaluation of Text and Speech Systems163-186Text, Speech and Language TechnologyAn Overview of Evaluation Methods in {TREC} Ad Hoc Information Retrieval and {TREC} Question Answering372007language information answer retrieval springer v0805 processing ai paper This chapter gives an overview of the current evaluation strategies and problems in the fields of information retrieval (IR) and question answering (QA), as instantiated in the Text Retrieval Conference (TREC). Whereas IR has a long tradition as a task, QA is a relatively new task which had to quickly develop its evaluation metrics, based on experiences gained in IR. This chapter will contrast the two tasks, their difficulties, and their evaluation metrics. We will end this chapter by pointing out limitations of the current evaluation strategies and potential future developments.Mon Jul 07 13:47:29 CEST 2008Proc. of INTERSPEECH 2006 -- ICSLP, Ninth International Conference on Spoken Language Processing, Pittsburgh, PA, USA, September 17-21, 2006paper 2044-Wed2FoP.7Evaluation of Content Presentation Strategies for an In-car Spoken Dialogue System2006icsa knowledge v0805 processing ai information traffic interface speech paper retrieval language dialog In this paper we present a framework for managing information presentation in spoken dialogue systems. We describe a content optimization module that makes use of ontological relationships in information-seeking dialogues in order to organize knowledge base items and perform adjustments such as relaxing or tightening user constraints. We present the results of an experimental evaluation comparing two response strategies: (a) one that uses the content optimization module to offer suggestions and (b) one that gives no suggestions. The results indicate that giving such suggestions is preferred when a user query matches either no items or many items in the knowledge base, and may also lead to more efficient dialogues.Mon Jul 07 13:47:29 CEST 2008KI -- Künstliche Intelligenz311-16Bridging Languages for Question Answering20052005retrieval paper processing answer ai information language v0805 In this paper we focus on resources and techniques available for Multilingual and Cross-language Question Answering (QA). First, we show that in the last years a number of tools and resources, such as lexical databases and the Web, have become standard constituents in QA systems development. Then, we present an overview of the possible uses of such resources in the general QA framework, focusing on the portability issue. In this direction, we elaborate on the potentialities offered by the MultiWordNet lexical database and the World Wide Web in the construction of a cross-language QA system for English and Italian.Mon Jul 07 13:47:29 CEST 2008it -- Information Technology140-48Semantic Interpretation of Natural Language User Input to Improve Search in Multimedia Knowledge Base492007processing knowledge v0805 management language ai multimedia information retrieval answer paper In this article we present an e-librarian service which is able to retrieve multimedia resources from a knowledge base in a more efficient way than by browsing through an index or by using a simple keyword search. Our premise is that more pertinent results would be retrieved if the e-librarian service had a semantic search engine which understood the sense of the user's query. We explored the approach to allow the user to formulate a complete question in natural language. We present our background theory, which is composed of three steps. Firstly, there is the linguistic pre-processing of the user question. Secondly, there is the semantic interpretation of the user question into a logical and unambiguous form, i. e., ALC terminology. Thirdly, there is the generation of a semantic query, and the retrieval of pertinent documents. The background theory was implemented in two prototypes. We report on experiments that confirm the feasibility, the quality and the benefits of such an e-librarian service. From 229 different user questions, the system returned for 97 answer, and for nearly half of the questions only one answer (the best one). Semantische Interpretation einer Benutzer-Eingabe in natürlicher Sprache für eine verbesserte Suche in einer multimedialen Wissensdatenbank: In diesem Artikel stellen wir unseren E-Bibliothekar Dienst vor, der in der Lage ist, multimediale Ressourcen aus einer Wissensdatenbank in einer effizienteren Weise zu finden als es durch das Suchen in einem Index oder durch Benutzen einer Stichwortsuche möglich ist. Wir sind überzeugt, dass konkretere Resultate gefunden werden, wenn der E-Bibliothekar Dienst über eine semantische Suchmaschine verfügt, die den Sinn der Benutzeranfrage versteht. Wir erforschen die Möglichkeit der Benutzereingabe einer ganzen Frage in natürlicher Sprache. Unsere Lösung besteht aus drei Schritten. Erstens gibt es die linguistische Aufbereitung der Benutzerfrage. Zweitens gibt es die semantische Interpretation der Benutzerfrage in eine logische und eindeutige Form, in unserem Fall in eine ALC Terminologie. Drittens gibt es die Erzeugung einer semantischen Frage und das Finden der passenden Dokumente. Unsere Lösung wurde in zwei Prototypen implementiert. Wir berichten über Experimente, die die Durchführbarkeit, die Qualität und den Nutzen eines solchen E-Bibliothekar Dienstes bestätigen. Von 229 unterschiedlichen Benutzerfragen fand unser System in 97 Fälle die passende Antwort und für die Hälfte der Fragen nur eine einzige -- und zwar die beste -- Antwort.Mon Jul 07 13:47:29 CEST 2008München2{Wissensmanagement: Grundlagen, Methoden und technische Unterstützung}2008softskills business enterprise v0805 information management book ai process science retrieval knowledge Dieses Buch vermittelt Ihnen einen systematischen und fundierten Überblick über die Konzepte, Methoden und technischen Hilfsmittel des Wissensmanagements. Anhand zahlreicher Beispiele zeigt Ihnen der Autor den Einsatz in der Praxis. Das Buch vermittelt Studenten der Wirtschaftsinformatik, der Betriebswirtschaftslehre und der Informatik die Grundlagen des Wissensmanagements, die sie für ihr Studium benötigen. Die zweite Auflage wurde durchgehend aktualisiert. Die Darstellung der Grundlagen wurde an die aktuelle Entwicklung angepasst, neue Methoden (z.B. zur Diagnose) aufgenommen, die praktischen Erfahrungen systematischer dargestellt und um neue Beispiele ergänzt.Mon Jul 07 13:47:29 CEST 2008Computer452--59Analysis and Semantic Querying in Large Biomedical Image Datasets412008rdf spatial paper retrieval image ieee v0805 health grid information semantic ai analysis Biomedical image analysis plays an important role in diagnosing, prognosing, and treating complex diseases. The authors describe a set of techniques for analyzing, processing, and querying large image datasets using semantic and spatial information.Mon Jul 07 13:47:29 CEST 2008Computer242-50{EventWeb:} Developing a Human-Centered Computing System412008v0805 interface ieee spatial data temporal retrieval user management paper multimodal information Dealing with emerging applications of computing requires taking a fresh look at our tools. Designing human-centered computing systems that give users a compelling experience combines quality content, carefully planned data organization and access mechanisms, and powerful presentation approaches.Mon Jul 07 13:47:29 CEST 2008Berlin, HeidelbergXpert.press{Open Source Knowledge Management}2006management wiki software book retrieval knowledge freeware springer v0805 team information Das Buch präsentiert die vielfältigen Möglichkeiten von Open Source Software zur Unterstützung von Wissensmanagement. Der Autor erläutert die Grundlagen und Einsatzmöglichkeiten von Open Source Software beim Knowledge Management und entwickelt auf Grund von Analysen konkreter Open Source Produkte Entscheidungskriterien und Anleitungen für die Einführung und Verbesserung von Knowledge Management und Open Source Software. Kosteneinsparungen und Effizienz finden dabei besondere Beachtung. Die unverzichtbare organisatorische Basis wird ebenso beleuchtet wie die Möglichkeiten einer schrittweisen Einführung in einer konkreten Organisation. Damit beleuchtet der Autor auch direkt umsetzbare Teillösungen.Mon Jul 07 13:47:29 CEST 2008DordrechtRecent Trends in Discourse and Dialogue219-246Text, Speech and Language TechnologyDoes This Answer Your Question?392008information ai springer v0805 processing paper language dialog retrieval answer Interactive Restricted Domain Question Answering Systems combine the interactivity of dialogue systems with the information retrieval features of question answering systems. The main problem when going from task-oriented dialogue systems to interactive restricted domain question answering systems is that the lack of task structure prohibits making simplifying assumptions as in taskoriented dialogue systems. In order to address this issue, we propose a solution that combines representations based on keywords extracted from the user utterances with machine learning to learn the dialogue management function. More specifically, we propose to use Support Vector Machines to classify the dialogue state containing the extracted keywords in order to determine the next action to be taken by the dialogue manager. Much of the content selection for clarification question usually found in dialogue managers is moved to an instance-based generation component. The proposed method has the advantage that it does not rely on an explicit representation of task structure as is necessary for task-oriented dialogue systems.Mon Jul 07 13:47:29 CEST 2008DordrechtMultimodal Intelligent Information Presentation325-340Text, Speech and Language TechnologyFusion and Coordination for Multimodal Interactive Information Presentation272005dfki multimodal user interface language paper v0805 retrieval interaction ai processing architecture springer information Users require more effective and efficient means of interaction with increasingly complex information and new interactive devices. This document summarizes the results of the international Dagstuhl Seminar on Coordination and Fusion in Multimodal Interaction that took place at Schloss Dagstuhl in Germany October 27 through November 2, 2001. We first outline a research roadmap in the near and long term. Next we describe requirements and an abstract architecture for this class of systems. We then detail requirements for semantic representations and languages necessary to enable these systems. Finally, we describe data, annotation methodologies and tools necessary to further advance the field. We conclude with a recommended action plan for forward progress in the community.Mon Jul 07 13:47:29 CEST 2008Informatik-Spektrum140-44{Anfragesprachen für das Semantic Web}282005web springer paper ontology format ai semantic v0805 knowledge retrieval protocol Das Semantic Web wird seit dem visionären Artikel von Berners-Lee, Hendler und Lassila allgemein als die nächste Evolutionsstufe des World Wide Web betrachtet.Mon Jul 07 13:47:29 CEST 2008Web Semantics161-69Bridging the semantic Web and Web 2.0 with {Representational State Transfer (REST)}62008v0805 rest knowledge web retrieval ai service paper software community rdf semantic Semantic Web technologies must integrate with Web 2.0 services for both to leverage each others strengths. We argue that the REST-based design methodologies of the web present the ideal mechanism through which to align the publication of semantic data with the existing web architecture. We present the design and implementation of two solutions that combine REST-based design and RDF data access: one solution for integrating existing web services and one server-side solution for creating RDF REST services. Both of these solutions enable SPARQL to be a unifying data access layer for aligning the Semantic Web and Web 2.0.Mon Jul 07 13:47:29 CEST 2008Berlin, HeidelbergThe Adaptive Web: Methods and Strategies of Web Personalization5BrusilovskyKobsaNejdl2007155-192Lecture Notes in Computer ScienceWeb Document Modeling43212007paper data ai knowledge v0805 information adaptive web document springer retrieval processing A very common issue of adaptive Web-Based systems is the modeling of documents. Such documents represent domain-specific information for a number of purposes. Application areas such as Information Search, Focused Crawling and Content Adaptation (among many others) benefit from several techniques and approaches to model documents effectively. For example, a document usually needs preliminary processing in order to obtain the relevant information in an effective and useful format, so as to be automatically processed by the system. The objective of this chapter is to support other chapters, providing a basic overview of the most common and useful techniques and approaches related with document modeling. This chapter describes high-level techniques to model Web documents, such as the Vector Space Model and a number of AI approaches, such as Semantic Networks, Neural Networks and Bayesian Networks. This chapter is not meant to act as a substitute of more comprehensive discussions about the topics presented. Rather, it provides a brief and informal introduction to the main concepts of document modeling, also focusing on the systems that are presented in the rest of the book as concrete examples of the related concepts.Mon Jul 07 13:47:29 CEST 2008Berlin, HeidelbergThe Adaptive Web: Methods and Strategies of Web Personalization7BrusilovskyKobsaNejdl2007231-262Lecture Notes in Computer ScienceAdaptive Focused Crawling43212007adaptive v0805 search retrieval paper ai springer information web The large amount of available information on the Web makes it hard for users to locate resources about particular topics of interest. Traditional search tools, e.g., search engines, do not always successfully cope with this problem, that is, helping users to seek the right information. In the personalized search domain, focused crawlers are receiving increasing attention, as a well-founded alternative to search the Web. Unlike a standard crawler, which traverses the Web downloading all the documents it comes across, a focused crawler is developed to retrieve documents related to a given topic of interest, reducing the network and computational resources. This chapter presents an overview of the focused crawling domain and, in particular, of the approaches that include a sort of adaptivity. That feature makes it possible to change the system behavior according to the particular environment and its relationships with the given input parameters during the search.