BibSonomyburst/user/flint63/retrievalBibSonomy RSS feed for /user/flint63/retrieval2012-02-16T18:52:17+01:00http://www.bibsonomy.org/bibtex/2661aa393f3479315fe0fa0ba6efd752e/flint63flint632011-09-30T14:16:53+02:00google acm v1010 paper data processing retrieval analysis database network algorithm <span class="authorEditorList"><a href="/author/Melnik">Sergey Melnik</a>, <a href="/author/Gubarev">Andrey Gubarev</a>, <a href="/author/Long">Jing Jing Long</a>, <a href="/author/Romer">Geoffrey Romer</a>, <a href="/author/Shivakumar">Shiva Shivakumar</a>, <a href="/author/Tolton">Matt Tolton</a>, and <a href="/author/Vassilakis">Theo Vassilakis</a> </span><em>Communications of the ACM</em> (<em>June 2011</em>)Fri Sep 30 14:16:53 CEST 2011Communications of the ACM#jun#114–123Dremel: Interactive Analysis of Web-scale Datasets542011google acm v1010 paper data processing retrieval analysis database network algorithm Dremel is a scalable, interactive ad hoc query system for analysis of read-only nested data. By combining multilevel execution trees and columnar data layout, it is capable of running aggregation queries over trillion-row tables in seconds. The system scales to thousands of {CPUs} and petabytes of data, and has thousands of users at Google. In this paper, we describe the architecture and implementation of Dremel, and explain how it complements MapReduce-based computing. We present a novel columnar storage representation for nested records and discuss experiments on few-thousand node instances of the system.http://www.bibsonomy.org/bibtex/2de6fd22e85bde98db3e05157db52f125/flint63flint632011-09-22T15:48:12+02:00knowledge springer v1010 paper processing retrieval zzz.th.c4 ontology database rules <span class="authorEditorList"><a href="/author/LePendu">Paea LePendu</a>, and <a href="/author/Dou">Dejing Dou</a> </span><em>Journal of Intelligent Information Systems</em> <em>37(2):217-244</em> (<em>October 2011</em>)Thu Sep 22 15:48:12 CEST 2011Journal of Intelligent Information Systems#oct#2217-244Using Ontology Databases for Scalable Query Answering, Inconsistency Detection, and Data Integration372011knowledge springer v1010 paper processing retrieval zzz.th.c4 ontology database rules An ontology database is a basic relational database management system that models an ontology plus its instances. To reason over the transitive closure of instances in the subsumption hierarchy, for example, an ontology database can either unfold views at query time or propagate assertions using triggers at load time. In this paper, we use existing benchmarks to evaluate our method---using triggers---and we demonstrate that by forward computing inferences, we not only improve query time, but the improvement appears to cost only more space (not time). However, we go on to show that the true penalties were simply opaque to the benchmark, i.e., the benchmark inadequately captures load-time costs. We have applied our methods to two case studies in biomedicine, using ontologies and data from genetics and neuroscience to illustrate two important applications: first, ontology databases answer ontology-based queries effectively; second, using triggers, ontology databases detect instance-based inconsistencies---something not possible using views. Finally, we demonstrate how to extend our methods to perform data integration across multiple, distributed ontology databases.http://www.bibsonomy.org/bibtex/250aa7a024f3a0e944ebcc8fadd3f5644/flint63flint632011-09-22T15:17:45+02:00springer v1010 paper rdf semantic retrieval web zzz.th.c4 <span class="authorEditorList"><a href="/author/De Virgilio">Roberto De Virgilio</a>, <a href="/author/Del Nostro">Pierluigi Del Nostro</a>, <a href="/author/Gianforme">Giorgio Gianforme</a>, and <a href="/author/Paolozzi">Stefano Paolozzi</a> </span><em>World Wide Web</em> <em>14(5-6):599-622</em> (<em>October 2011</em>)Thu Sep 22 15:17:45 CEST 2011World Wide Web#oct#5-6599-622A Scalable and Extensible Framework for Query Answering over {RDF}142011springer v1010 paper rdf semantic retrieval web zzz.th.c4 The Semantic Web is gaining increasing interest to fulfill the need of sharing, retrieving, and reusing information. In this context, the Resource Description Framework (RDF) has been conceived to provide an easy way to represent any kind of data and metadata, according to a lightweight model and syntaxes for serialization (RDF/XML, N3, etc.). Despite RDF has the advantage of being general and simple, it cannot be used as a storage model as it is, since it can be easily shown that even simple management operations involve serious performance limitations. In this paper we present a framework which provides a flexible and persistent layer relying on a novel storage model that guarantees good scalability and performance of query evaluation. The approach is based on the notion of construct, that represents a concept of the domain of interest. This makes the approach easily extensible and independent from the specific knowledge representation language. Based on this representation, reasoning capabilities are supported by a rule-based engine. Finally we present experimental results over real world scenarios to demonstrate the feasibility of the approach.http://www.bibsonomy.org/bibtex/2fbef5692f7b6fbb9b9253a14fb3033e1/flint63flint632011-09-22T14:02:57+02:00information springer adaptive paper retrieval interface zzz.th.c4 ai multimedia v1010 device user mobile <span class="authorEditorList"><a href="/author/Viana">Windson Viana</a>, <a href="/author/Miron">Alina Dia Miron</a>, <a href="/author/Moisuc">Bogdan Moisuc</a>, <a href="/author/Gensel">Jérôme Gensel</a>, <a href="/author/Villanova-Oliver">Marlène Villanova-Oliver</a>, and <a href="/author/Martin">Hervè Martin</a> </span><em>Multimedia Tools and Applications</em> <em>53(2):391-429</em> (<em>June 2011</em>)Thu Sep 22 14:02:57 CEST 2011Multimedia Tools and Applications#jun#2391-429Towards the Semantic and Context-aware Management of Mobile Multimedia532011information springer adaptive paper retrieval interface zzz.th.c4 ai multimedia v1010 device user mobile Users of mobile devices can nowadays easily create large quantities of mobile multimedia documents tracing significant events attended, places visited or, simply, moments of their everyday life. However, they face the challenge of organizing these documents in order to facilitate searching through them at a later time and sharing them with other users. We propose using context awareness and semantic technologies in order to improve and facilitate the organization, annotation, retrieval and sharing of personal mobile multimedia documents. Our approach combines metadata extracted and enriched automatically from the users' context with annotations provided manually by the users and with annotations inferred by applying user-defined rules to context features. These new contextual metadata are integrated into the processes of annotation, sharing and keyword-based retrieval.http://www.bibsonomy.org/bibtex/2384093a25d687f5d989dd92ee314b453/flint63flint632011-04-04T09:42:04+02:00information pattern v1010 recognition data book processing retrieval language analysis <span class="authorEditorList"><a href="/author/Berry">Michael W. Berry</a>, and <a href="/author/Kogan">Jacob Kogan</a> (Eds.). </span><em>Wiley, </em><em>Chichester, UK, </em>(<em>2010</em>)Mon Apr 04 09:42:04 CEST 2011Chichester, UKText Mining: Applications and Theory2010information pattern v1010 recognition data book processing retrieval language analysis The book presents the state-of-the-art algorithms for text mining from both the academic and industrial perspectives. The contributors span several countries and scientific domains: universities, industrial corporations, and government laboratories, and demonstrate the use of techniques from machine learning, knowledge discovery, natural language processing and information retrieval to design computational models for automated text analysis and mining. This volume demonstrates how advancements in the fields of applied mathematics, computer science, machine learning, and natural language processing can collectively capture, classify, and interpret words and their contexts. As suggested in the preface, text mining is needed when words are not enough.http://www.bibsonomy.org/bibtex/20ea841b3345156d6404c2abeda89a1dd/flint63flint632011-02-18T17:13:15+01:00information ai multimedia acm zzz.th v1010 book retrieval conference <span class="authorEditorList"><a href="/author/N.N."> N.N.</a> (Eds.). </span><em>New York, </em><em>ACM, </em>(<em>2010</em>)Fri Feb 18 17:13:15 CET 2011New YorkMIR 2010: Proceedings of the ACM SIGMM International Conference on Multimedia Information Retrieval, Philadelphia, PA, USAProceedings of the ACM SIGMM International Conference on Multimedia Information Retrieval, MIR 2010, Philadelphia, PA, USA, March 29--312010information ai multimedia acm zzz.th v1010 book retrieval conference The goal of MIR is to illuminate new paradigms, theories, and insights in the area of multimedia information retrieval. Topics of special interest included exploration of media archives; interfaces for multimedia exploration; indexing and search of multimedia data: digital life experience analysis and retrieval; video surveillance browsing and retrieval; learning and relevance feedback in multimedia retrieval; and diverse applications in culture, society, and science.http://www.bibsonomy.org/bibtex/2e02a8cbc541a52f5a818a2eece3469e0/flint63flint632011-02-17T10:56:53+01:00information ai acm zzz.th v1010 paper processing retrieval language <span class="authorEditorList"><a href="/author/Anthes">Gary Anthes</a> </span><em>Communications of the ACM</em> <em>53(12):16–18</em> (<em>December 2010</em>)Thu Feb 17 10:56:53 CET 2011Communications of the ACM#dec#1216–18Topic Models vs.\ Unstructured Data532010information ai acm zzz.th v1010 paper processing retrieval language With topic modeling, scientists can explore and understand huge collections of unlabeled information.http://www.bibsonomy.org/bibtex/2075b437679349ff9cb3d498438995a97/flint63flint632011-02-17T09:19:11+01:00information zzz.th.c46 ai ieee search v1010 paper service processing retrieval web zzz.th.c4 <span class="authorEditorList"><a href="/author/Ceri">Stefano Ceri</a>, <a href="/author/Abid">Adnan Abid</a>, <a href="/author/Helou">Mamoun Abu Helou</a>, <a href="/author/Barbieri">Davide Barbieri</a>, <a href="/author/Bozzon">Alessandro Bozzon</a>, <a href="/author/Braga">Daniele Braga</a>, <a href="/author/Brambilla">Marco Brambilla</a>, <a href="/author/Campi">Alessandro Campi</a>, <a href="/author/Corcoglioniti">Francesco Corcoglioniti</a>, <a href="/author/Valle">Emanuele Della Valle</a>, <a href="/author/Eynard">Davide Eynard</a>, <a href="/author/Fraternali">Piero Fraternali</a>, <a href="/author/Grossniklaus">Michael Grossniklaus</a>, <a href="/author/Martinenghi">Davide Martinenghi</a>, <a href="/author/Ronchi">Stefania Ronchi</a>, <a href="/author/Tagliasacchi">Marco Tagliasacchi</a>, and <a href="/author/Vadacca">Salvatore Vadacca</a> </span><em>IEEE Internet Computing</em> <em>14(6):14-22</em> (<em>2010</em>)Thu Feb 17 09:19:11 CET 2011IEEE Internet Computing614-22Search Computing: Managing Complex Search Queries142010information zzz.th.c46 ai ieee search v1010 paper service processing retrieval web zzz.th.c4 Search computing focuses on building answers to complex search queries (for example, Where can I attend an interesting conference in my field near a sunny beach? by interacting with a constellation of cooperating search services, and using result ranking and joining as the dominant factors for service composition. The service computing paradigm has so far been neutral to the specific features of search applications and services. To address this weakness, search computing advocates a new approach in which search, join, and ranking are the central aspects for service composition.http://www.bibsonomy.org/bibtex/20e4b9499d392117c3396edcb44f16284/flint63flint632011-02-14T15:39:03+01:00information ai v1010 paper semantic processing retrieval web language <span class="authorEditorList"><a href="/author/Wilks">Yorick Wilks</a>, and <a href="/author/Brewster">Christopher Brewster</a> </span><em>Foundations and Trends in Web Science</em> <em>1(3–4):199-327</em> (<em>2007</em>)Mon Feb 14 15:39:03 CET 2011Foundations and Trends in Web Science3–4199-327Natural Language Processing as a Foundation of the Semantic Web12007information ai v1010 paper semantic processing retrieval web language The main argument of this paper is that Natural Language Processing (NLP) does, and will continue to, underlie the Semantic Web (SW), including its initial construction from unstructured sources like the World Wide Web (WWW), whether its advocates realise this or not. Chiefly, we argue, such NLP activity is the only way up to a defensible notion of meaning at conceptual levels (in the original SW diagram) based on lower level empirical computations over usage. Our aim is definitely not to claim logic-bad, NLP-good in any simple-minded way, but to argue that the SW will be a fascinating interaction of these two methodologies, again like the WWW (which has been basically a field for statistical NLP research) but with deeper content. Only NLP technologies (and chiefly information extraction) will be able to provide the requisite RDF knowledge stores for the SW from existing unstructured text databases in the WWW, and in the vast quantities needed. There is no alternative at this point, since a wholly or mostly hand-crafted SW is also unthinkable, as is a SW built from scratch and without reference to the WWW. We also assume that, whatever the limitations on current SW representational power we have drawn attention to here, the SW will continue to grow in a distributed manner so as to serve the needs of scientists, even if it is not perfect. The WWW has already shown how an imperfect artefact can become indispensable.http://www.bibsonomy.org/bibtex/22f3048eabcb2da4f1ebec55e0179ef14/flint63flint632011-01-06T09:40:21+01:00zzz.th.c4w information ieee search v1010 paper retrieval web <span class="authorEditorList"><a href="/author/schraefel">m. c. schraefel</a> </span><em>Computer</em> <em>42(3):52-59</em> (<em>2009</em>)Thu Jan 06 09:40:21 CET 2011Computer352-59Building Knowledge: What's beyond Keyword Search?422009zzz.th.c4w information ieee search v1010 paper retrieval web The success of the search engine may be our Newtonian paradigm for the Web. It enables us to do so much information discovery that it is difficult to imagine what we cannot do with it.http://www.bibsonomy.org/bibtex/2d7eb40bcfdb97546efd605ab8099eaad/flint63flint632010-12-10T15:47:30+01:00information ai knowledge zzz.th v1010 social paper learn semantic retrieval web <span class="authorEditorList"><a href="/author/Hotho">Andreas Hotho</a>, and <a href="/author/Stumme">Gerd Stumme</a> </span><em>Semantic Web</em> <em>1(1-2):117-119</em> (<em>2010</em>)Fri Dec 10 15:47:30 CET 2010Semantic Web1-2117-119Towards the Ubiquitous Web12010information ai knowledge zzz.th v1010 social paper learn semantic retrieval web Today, we observe the amalgamation of the Social Web and the Mobile Web, which will ultimately lead to a Ubiquitous Web. The integration and aggregation of the different kinds of available data, and the extraction of useful knowledge and its representation has become an important challenge for researchers from the Semantic Web, Web 2.0, social network analysis and machine learning communities. We discuss the Ubiquitous Web vision, by addressing the challenge of bridging the gap between Web 2.0 and the Semantic Web, before widening the scope to mobile applications.http://www.bibsonomy.org/bibtex/23b54b998c5369d6029bbca5be5881d04/flint63flint632010-11-07T15:34:33+01:00information ai knowledge v1010 paper answer processing retrieval language zzz.th.c4 aaai <span class="authorEditorList"><a href="/author/Tunstall-Pedoe">William Tunstall-Pedoe</a> </span><em>AI Magazine</em> <em>31(3):80-92</em> (<em>2010</em>)Sun Nov 07 15:34:33 CET 2010AI Magazine380-92{True Knowledge}: Open-Domain Question Answering Using Structured Knowledge and Inference312010information ai knowledge v1010 paper answer processing retrieval language zzz.th.c4 aaai This article gives a detailed description of True Knowledge: a commercial, open-domain question answering platform. The system combines a large and growing structured knowledge base of common sense, factual and lexical knowledge; a natural language translation system that turns user questions into internal language-independent queries and an inference system that can answer those queries using both directly represented and inferred knowledge. The system is live and answers millions of questions per month asked by internet users.http://www.bibsonomy.org/bibtex/204dd5aadfa897511a903c31b50b741d0/flint63flint632010-11-07T15:34:33+01:00information ai v1010 paper answer learn processing retrieval language zzz.th.c4 ontology aaai <span class="authorEditorList"><a href="/author/Soderland">Stephen Soderland</a>, <a href="/author/Roof">Brendan Roof</a>, <a href="/author/Qin">Bo Qin</a>, <a href="/author/Xu">Shi Xu</a>, <a href="/author/Mausam"> Mausam</a>, and <a href="/author/Etzioni">Oren Etzioni</a> </span><em>AI Magazine</em> <em>31(3):93-102</em> (<em>2010</em>)Sun Nov 07 15:34:33 CET 2010AI Magazine393-102Adapting Open Information Extraction to Domain-Specific Relations312010information ai v1010 paper answer learn processing retrieval language zzz.th.c4 ontology aaai Information extraction (IE) can identify a set of relations from free text to support question answering (QA). Until recently, IE systems were domain-specific and needed a combination of manual engineering and supervised learning to adapt to each target domain. A new paradigm, Open IE operates on large text corpora without any manual tagging of relations, and indeed without any pre-specified relations. Due to its open-domain and open-relation nature, Open IE is purely textual and is unable to relate the surface forms to an ontology, if known in advance. We explore the steps needed to adapt Open IE to a domain-specific ontology and demonstrate our approach of mapping domain-independent tuples to an ontology using domains from DARPA’s Machine Reading Project. Our system achieves precision over 0.90 from as few as 8 training examples for an NFL-scoring domain.http://www.bibsonomy.org/bibtex/2460a61110ebf98c22be4669f6b8fe7fe/flint63flint632010-11-07T15:34:32+01:00information ai v1010 paper answer processing retrieval architecture language zzz.th.c4 aaai <span class="authorEditorList"><a href="/author/Ferrucci">David Ferrucci</a>, <a href="/author/Brown">Eric Brown</a>, <a href="/author/Chu-Carroll">Jennifer Chu-Carroll</a>, <a href="/author/Fan">James Fan</a>, <a href="/author/Gondek">David Gondek</a>, <a href="/author/Kalyanpur">Aditya A. Kalyanpur</a>, <a href="/author/Lally">Adam Lally</a>, <a href="/author/Murdock">J. William Murdock</a>, <a href="/author/Nyberg">Eric Nyberg</a>, <a href="/author/Prager">John Prager</a>, <a href="/author/Schlaefer">Nico Schlaefer</a>, and <a href="/author/Welty">Chris Welty</a> </span><em>AI Magazine</em> <em>31(3):59-79</em> (<em>2010</em>)Sun Nov 07 15:34:32 CET 2010AI Magazine359-79Building {Watson}: An Overview of the {DeepQA} Project312010information ai v1010 paper answer processing retrieval architecture language zzz.th.c4 aaai IBM Research undertook a challenge to build a computer system that could compete at the human champion level in real time on the American TV Quiz show, Jeopardy! The extent of the challenge includes fielding a real-time automatic contestant on the show, not merely a laboratory exercise. The Jeopardy! Challenge helped us address requirements that led to the design of the DeepQA architecture and the implementation of Watson. After 3 years of intense research and development by a core team of about 20 researches, Watson is performing at human expert-levels in terms of precision, confidence and speed at the Jeopardy! Quiz show. Our results strongly suggest that DeepQA is an effective and extensible architecture that may be used as a foundation for combining, deploying, evaluating and advancing a wide range of algorithmic techniques to rapidly advance the field of QA.http://www.bibsonomy.org/bibtex/25530aabcaab3d3a6202e8c026b18dec5/flint63flint632010-11-07T15:34:32+01:00information ai knowledge v1010 paper answer processing retrieval language zzz.th.c4 science aaai <span class="authorEditorList"><a href="/author/Gunning">David Gunning</a>, <a href="/author/Chaudhri">Vinay K. Chaudhri</a>, <a href="/author/Clark">Peter E. Clark</a>, <a href="/author/Barker">Ken Barker</a>, <a href="/author/Chaw">Shaw-Yi Chaw</a>, <a href="/author/Greaves">Mark Greaves</a>, <a href="/author/Grosof">Benjamin Grosof</a>, <a href="/author/Leung">Alice Leung</a>, <a href="/author/McDonald">David D. McDonald</a>, <a href="/author/Mishra">Sunil Mishra</a>, <a href="/author/Pacheco">John Pacheco</a>, <a href="/author/Porter">Bruce Porter</a>, <a href="/author/Spaulding">Aaron Spaulding</a>, <a href="/author/Tecuci">Dan Tecuci</a>, and <a href="/author/Tien">Jing Tien</a> </span><em>AI Magazine</em> <em>31(3):33-58</em> (<em>2010</em>)Sun Nov 07 15:34:32 CET 2010AI Magazine333-58Project {Halo} Update---Progress Toward Digital {Aristotle}312010information ai knowledge v1010 paper answer processing retrieval language zzz.th.c4 science aaai In the winter, 2004 issue of AI Magazine, we reported Vulcan Inc.'s first step toward creating a question-answering system called Digital Aristotle. The goal of that first step was to assess the state of the art in applied Knowledge Representation and Reasoning (KRR) by asking AI experts to represent 70 pages from the advanced placement (AP) chemistry syllabus and to deliver knowledge-based systems capable of answering questions from that syllabus. This paper reports the next step toward realizing a Digital Aristotle: we present the design and evaluation results for a system called AURA, which enables domain experts in physics, chemistry, and biology to author a knowledge base and that then allows a different set of users to ask novel questions against that knowledge base. These results represent a substantial advance over what we reported in 2004, both in the breadth of covered subjects and in the provision of sophisticated technologies in knowledge representation and reasoning, natural language processing, and question answering to domain experts and novice users.http://www.bibsonomy.org/bibtex/2181771e269cdc4e75c38d2019bb17d25/flint63flint632010-11-07T15:34:31+01:00information ai v1010 paper answer processing retrieval language zzz.th.c4 interface user aaai <span class="authorEditorList"><a href="/author/Gunning">David Gunning</a>, <a href="/author/Chaudhri">Vinay K. Chaudhri</a>, and <a href="/author/Welty">Chris Welty</a> </span><em>AI Magazine</em> <em>31(3):11-12</em> (<em>2010</em>)Sun Nov 07 15:34:31 CET 2010AI Magazine311-12Introduction to the Special Issue on Question Answering312010information ai v1010 paper answer processing retrieval language zzz.th.c4 interface user aaai This special issue issue of AI Magazine presents six articles on some of the most interesting question answering systems in development today. Included are articles on Project, the Semantic Research, Watson, True Knowledge, and TextRunner (University of Washington’s clever use of statistical NL techniques to answer questions across the open web).http://www.bibsonomy.org/bibtex/2daaf1ed5747e28c5ad6ef9693cc3d00b/flint63flint632010-11-07T15:34:31+01:00information knowledge paper answer retrieval ontology health zzz.th.c4 ai v1010 zzz.th.med processing language aaai <span class="authorEditorList"><a href="/author/Lenat">Douglas Lenat</a>, <a href="/author/Witbrock">Michael Witbrock</a>, <a href="/author/Baxter">David Baxter</a>, <a href="/author/Blackstone">Eugene Blackstone</a>, <a href="/author/Deaton">Chris Deaton</a>, <a href="/author/Schneider">Dave Schneider</a>, <a href="/author/Scott">Jerry Scott</a>, and <a href="/author/Shepard">Blake Shepard</a> </span><em>AI Magazine</em> <em>31(3):13-32</em> (<em>2010</em>)Sun Nov 07 15:34:31 CET 2010AI Magazine313-32Harnessing {Cyc} to Answer Clinical Researchers' Ad Hoc Queries312010information knowledge paper answer retrieval ontology health zzz.th.c4 ai v1010 zzz.th.med processing language aaai By extending Cyc’s ontology and KB approximately 2 percent, Cycorp and Cleveland Clinic Foundation (CCF) have built a system to answer clinical researchers' ad hoc queries. The query may be long and complex, hence only partially understood at first, parsed into a set of CycL (higher-order logic) fragments with open variables. But, surprisingly often, after applying various constraints (medical domain knowledge, common sense, discourse pragmatics, syntax), there is only one single way to fit those fragments together, one semantically meaningful formal query P. The system, SRA (for Semantic Research Assistant), dispatches a series of database calls and then combines, logically and arithmetically, their results into answers to P. Seeing the first few answers stream back, the user may realize that they need to abort, modify, and re-ask their query. Even before they push ASK, just knowing approximately how many answers would be returned can spark such editing. Besides real-time ad hoc query-answering, queries can be bundled and persist over time. One bundle of 275 queries is rerun quarterly by CCF to produce the procedures and outcomes data it needs to report to STS (Society of Thoracic Surgeons, an external hospital accreditation and ranking body); another bundle covers ACC (American College of Cardiology) reporting. Until full articulation/answering of precise, analytical queries becomes as straight-forward and ubiquitous as text search, even partial understanding of a query empowers semantic search over semi-structured data (ontology-tagged text), avoiding many of the false positives and false negatives that standard text searching suffers from.http://www.bibsonomy.org/bibtex/26d08f5980f14420c1b4129c09eddd93e/flint63flint632010-10-31T22:48:56+01:00information lexicon answer learn web retrieval ai v1010 book processing language conference aaai <span class="authorEditorList"><a href="/author/Bunescu">Razvan Bunescu</a>, <a href="/author/Gabrilovich">Evgeniy Gabrilovich</a>, and <a href="/author/Mihalcea">Rada Mihalcea</a> (Eds.). </span><em> WS-08-15, </em><em>Menlo Park, CA, </em><em>AAAI Press, </em>(<em>2008</em>)Sun Oct 31 22:48:56 CET 2010Menlo Park, CAWS-08-15Technical ReportWikipedia and Artificial Intelligence: An Evolving Synergy, Papers from the 2008 AAAI Workshop2008information lexicon answer learn web retrieval ai v1010 book processing language conference aaai Wikipedia has become one of the largest and fastest growing online sources of encyclopedic knowledge. As a large-scale repository of structured knowledge, Wikipedia can be a valuable resource for a diverse set of srtificial intelligence (AI) applications. Major conferences in natural language processing and machine learning have recently witnessed a significant number of approaches that use Wikipedia for tasks ranging from text categorization and clustering to word sense disambiguation, information retrieval, information extraction and question answering. On the other hand, Wikipedia can greatly benefit from numerous algorithms and representation models developed during decades of AI research, as illustrated recently in tasks such as estimating the reliability of authors' contributions, automatic linking of articles, or intelligent matching of Wikipedia tasks with potential contributors. The goal of this workshop was to foster the research and dissemination of ideas on the mutually beneficial interaction between Wikipedia and AI. The workshop was intended to be highly interdisciplinary.http://www.bibsonomy.org/bibtex/2336ad9a8a4b56c2ce91bd790c63568d8/flint63flint632010-10-31T22:48:41+01:00information text springer image assist retrieval health analysis multimedia v1010 zzz.th.med book processing language conference <span class="authorEditorList"><a href="/author/Caputo">Barbara Caputo</a>, <a href="/author/Müller">Henning Müller</a>, <a href="/author/Syeda-Mahmood">Tanveer Fathima Syeda-Mahmood</a>, <a href="/author/Duncan">James S. Duncan</a>, <a href="/author/Wang">Fei Wang</a>, and <a href="/author/Kalpathy-Cramer">Jayashree Kalpathy-Cramer</a> (Eds.). </span><em>Lecture Notes in Computer Science </em><em>Springer, </em><em>Berlin, </em>(<em>2010</em>)Sun Oct 31 22:48:41 CET 2010BerlinLecture Notes in Computer ScienceMedical Content-Based Retrieval for Clinical Decision Support: First MICCAI International Workshop, MCBR-CDS 2009, London, UK, September 20, 2009, Revised Selected Papers58532010information text springer image assist retrieval health analysis multimedia v1010 zzz.th.med book processing language conference This book constitutes the refereed proceedings of the first MICCAI Workshop on Medical Content-Based Retrieval for Clinical Decision Support, MCBR-CDS 2009, held in London, UK, in September 2009. The 10 revised full papers were carefully reviewed and selected from numerous submissions. The papers are divide on several topics on medical image retrieval, clinical decision making and multimodal fusion.http://www.bibsonomy.org/bibtex/2ad2bfff52de43b626512d05d66f9b6ca/flint63flint632010-10-31T22:48:34+01:00information development paper tool interaction retrieval architecture zzz.th.c4 interface ai v1010 processing language user <span class="authorEditorList"><a href="/author/Cunningham">Hamish Cunningham</a>, <a href="/author/Maynard">Diana Maynard</a>, <a href="/author/Bontcheva">Kalina Bontcheva</a>, and <a href="/author/Tablan">Valentin Tablan</a> </span><em>Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Philadelphia, PA, USA, </em>(<em>2002</em>)Sun Oct 31 22:48:34 CET 2010Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Philadelphia, PA, USA{GATE}: A Framework and Graphical Development Environment for Robust {NLP} Tools and Applications.2002information development paper tool interaction retrieval architecture zzz.th.c4 interface ai v1010 processing language user In this paper we present GATE, a framework and graphical development environment which enables users to develop and deploy language engineering components and resources in a robust fashion. The GATE architecture has enabled us not only to develop a number of successful applications for various language processing tasks (such as Information Extraction), but also to build and annotate corpora and carry out evaluations on the applications generated. The framework can be used to develop applications and resources in multiple languages, based on its thorough Unicode support.