@inproceedings{Martinez:2008, title = {Facilitating biomedical systematic reviews using ranked text retrieval and classification}, address = {Hobart}, author = {David Martinez and Sarvnaz Karimi and Lawrence Cavedon and Timothy Baldwin}, booktitle = {{ADCS} 2008 Proceedings}, pages = {53--60}, year = 2008, url = {http://es.csiro.au/adcs2008/proceedings/p09-martinez.pdf}, abstract = {Searching and selecting articles to be included in systematic reviews is a real challenge for healthcare agencies responsible for publishing these reviews. The current practice of manually reviewing all papers returned by complex hand-crafted boolean queries is human labour-intensive and difficult to maintain. We demonstrate a two-stage searching system that takes advantage of ranked queries and support-vector machine text classification to assist in the retrieval of relevant articles, and to restrict results to higher-quality documents. Our proposed approach shows significant work saved in the systematic review process over a baseline of a keyword-based retrieval system.}, biburl = {http://www.bibsonomy.org/bibtex/2a233b1fcd321fc4e77e4d7e23159e64e/diego_ma}, keywords = {EBM inf_retrieval}, } @article{salton:1975, title = {A Vector Space Model for Automatic Indexing}, author = {Gerard Salton and Anita Wong and Chung-Shu Yang}, journal = {Communications of the ACM}, note = {The paper where vector space model for IR was introduced}, number = 11, pages = {613-–620}, volume = 18, year = 1975, key = {Salton et al.}, abstract = {In a document retrieval, or other pattern matching environment where stored entities (documents) are compared with each other or with incoming patterns (search requests), it appears that the best indexing (property) space is one where each entity lies as far away from the others as possible; in these circumstances the value of an indexing system may be expressible as a function of the density of the object space; in particular, retrieval performance may correlate inversely with space density. An approach based on space density computations is used to choose an optimum indexing vocabulary for a collection of documents. Typical evaluation results are shown, demonstating the usefulness of the model.}, biburl = {http://www.bibsonomy.org/bibtex/21096b4711e20c4523f8830bb90e2cfe6/diego_ma}, keywords = {inf_retrieval}, } @inproceedings{Tellex:2003, title = {Quantitavie Evaluation of Passage Retrieval Algorithms for Question Answering}, address = {New York}, author = {Stefanie Tellex and Boris Katz and Jimmy Lin and Aaron Fernandes and Gregory Marton}, booktitle = {{SIGIR'03}: Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval}, pages = {41-47}, publisher = {ACM Press}, year = 2003, biburl = {http://www.bibsonomy.org/bibtex/2000c55d058a0ceb97a689bfa8afc5a89/diego_ma}, keywords = {QA inf_retrieval tobibsonomy}, } @inproceedings{Wilkinson:2003, title = {Efficient {RDF} Storage and Retrieval in {Jena2}}, author = {Kevin Wilkinson and Craig Sayers and Harumi Kuno and Dave Reynolds}, booktitle = {Proc. First International Workshop on Semantic Web and Databases}, year = 2003, url = {http://www.cs.uic.edu/~ifc/SWDB/papers/Wilkinson_etal.pdf}, abstract = {RDF and related Semantic Web technologies have been the recent focus of much research activity. This work has led to new specifications for RDF and OWL. However, efficient implementations of these standards are needed to realize the vision of a world-wide semantic Web. In particular, implementations that scale to large, enterprise-class data sets are required. Jena2 is the second generation of Jena, a leading semantic web programmers' toolkit. This paper describes the persistence subsystem of Jena2 which is intended to support large datasets. This paper describes its features, the changes from Jena1, relevant details of the implementation and performance tuning issues. Query optimization for RDF is identified as a promising area for future research.}, biburl = {http://www.bibsonomy.org/bibtex/2a5d346acd4fdd67bd2fcebd7245e7733/diego_ma}, keywords = {semantic_web RDF inf_retrieval}, } @misc{Hertel:2008, title = {{RDF} Storage and Retrieval Systems}, author = {Alice Hertel and Jeen Broekstra and Heiner Stuckenschmidt}, howpublished = {On-line}, year = 2008, url = {http://ki.informatik.uni-mannheim.de/fileadmin/publication/Hertel08RDFStorage.pdf}, abstract = {Ontologies are often used to improve data access. For this purpose, existing data has to be linked to an ontology and appropriate access mechanisms have to be provided. In this chapter, we review RDF storage and retrieval technologies as a common approach for accessing ontology-based data. We discuss different storage models, typical functionalities of RDF middleware such as data model support and reasoning capabilities and RDF query languages with a special focus on SPARQL as an emerging standard. We also discuss some trends such as support for expressive ontology and rule languages.}, biburl = {http://www.bibsonomy.org/bibtex/24db931ca8fe9d9c95bfd281d04c57a98/diego_ma}, keywords = {semantic_web inf_retrieval RDF web}, } @inproceedings{Pizzato:2008, title = {Indexing on Semantic Roles for Question Answering}, author = {Luiz Pizzato and Diego Moll{\'a}}, booktitle = {Proc. COLING Workshop on Information Retrieval for Question Answering}, pages = {8 pages}, year = 2008, abstract = {Semantic Role Labeling (SRL) has been used successfully in several stages of automated Question Answering (QA) systems but its inherent slow procedures make it difficult to use at the indexing stage of the document retrieval component. In this paper we confirm the intuition that SRL at indexing stage improves the performance of QA and propose a simplified technique named the Question Prediction Language Model (QPLM), which provides similar information with a much lower cost. The methods were tested on four different QA systems and the results suggest that QPLM can be used as a good compromise between speed and accuracy.}, biburl = {http://www.bibsonomy.org/bibtex/2cc132a9e1fda44b9f205512d8975952c/diego_ma}, keywords = {question_answering molla_publication AnswerFinder inf_retrieval}, } @inproceedings{Pizzato:2006, title = {Pseudo Relevance Feedback Using Named Entities for Question Answering}, author = {Luiz Pizzato and Diego Moll{\'a} and C{\'e}cile Paris}, booktitle = {Proceedings ALTW}, pages = {83-90}, volume = 4, year = 2006, url = {http://www.alta.asn.au/events/altw2006/alta-2006-online-proceedings.html}, abstract = {Relevance feedback has already proven its usefulness in probabilistic information retrieval (IR). In this research we explore whether a pseudo relevance feedback technique on IR can improve the Question Answering task (QA). The basis of our exploration is the use of relevant named entities from the top retrieved documents as clues of relevance. We discuss two interesting findings from these experiments: the reasons the results were not improved, and the fact that today's metrics of IR evalu ation on QA do not reflect the results obtained by a QA system.}, biburl = {http://www.bibsonomy.org/bibtex/25ddeca10bfa22885c0c1a6a429ae5ed9/diego_ma}, keywords = {AnswerFinder inf_retrieval molla_publication}, } @inproceedings{Hersh:2007, title = {{TREC} 2006 Genomics Track Overview}, author = {William Hersh and Aaron M. Cohen and Phoebe Roberts and Hari Krishna Rekapalli}, crossref = {X-TREC:2007}, year = 2007, url = {http://trec.nist.gov/pubs/trec15/papers/GEO06.OVERVIEW.pdf}, abstract = {The TREC Genomics Track implemented a new task in 2006 that focused on passage retrieval for question answering using full-text documents from the biomedical literature. A test collection of 162,259 full-text documents and 28 topics expressed as questions was assembled. Systems were required to return passages that contained answers to the questions. Expert judges determined the relevance of passages and grouped them into aspects identified by one or more Medical Subject Headings (MeSH) terms. Document relevance was defined by the presence of one or more relevant aspects. The performance of submitted runs was scored using mean average precision (MAP) at the passage, aspect, and document level. In general, passage MAP was low, while aspect and document MAP were somewhat higher.}, biburl = {http://www.bibsonomy.org/bibtex/28ff460ce1e1f16a43ff8e480b4ca7f86/diego_ma}, keywords = {biomedical question_answering inf_retrieval}, } @proceedings{X-TREC:2007, title = {The Fifteenth {Text} {REtrieval} {Conference} ({TREC} 2006) Proceedings}, booktitle = {Proceedings {TREC} 2006}, editor = {Ellen M. Voorhees}, volume = {SP 500-272}, year = 2007, url = {http://trec.nist.gov/pubs/trec15/t15_proceedings.html}, biburl = {http://www.bibsonomy.org/bibtex/2ea23d02a52185ec3958b78b2fe3c1992/diego_ma}, keywords = {inf_retrieval question_answering}, } @inproceedings{Pizzato:2007, title = {Question Prediction Language Model}, author = {Luiz Pizzato and Diego Moll{\'a}}, booktitle = {Proceedings ALTW}, pages = {92-99}, volume = 5, year = 2007, url = {http://www.ics.mq.edu.au/~diego/answerfinder/}, abstract = {This paper proposes the use of a language representation that specifies the relationship between terms of a sentence using question words. The proposed representation is tailored to help the search for documents containing an answer for a natural language question. This study presents the construction of this language model, the framework where it is used, and its evaluation.}, biburl = {http://www.bibsonomy.org/bibtex/23eb2ff36ad09d69729f2e7583357824f/diego_ma}, keywords = {AnswerFinder inf_retrieval molla_publication}, } @book{Jacobs:1992, title = {Text-based Intelligent Systems: current research and practice in information extraction and retrieval}, address = {Hillsdale (New Jersey), Hove and London}, editor = {Paul S. Jacobs}, publisher = {Lawrence Erlbaum}, year = 1992, biburl = {http://www.bibsonomy.org/bibtex/2054cc1a1012f52eded8daadb49f3fa8d/diego_ma}, keywords = {inf_extraction inf_retrieval}, } @proceedings{ZZZ-TREC6, title = {The Sixth {Text} {REtrieval} {Conference} ({TREC}-6)}, booktitle = {Proc. {TREC-6}}, editor = {Ellen M. Voorhees and Donna Harman}, number = {500-240}, organization = {NIST-DARPA}, publisher = {Government Printing Office}, series = {NIST Special Publication}, year = 1997, url = {http://trec.nist.gov/pubs.html}, biburl = {http://www.bibsonomy.org/bibtex/2da74225ccdfc9d54338999b88006b35f/diego_ma}, keywords = {inf_retrieval}, } @proceedings{ZZZ-TREC7, title = {The Seventh {Text} {REtrieval} {Conference} ({TREC-7})}, booktitle = {Proc. {TREC-7}}, editor = {Ellen M. Voorhees and Donna Harman}, number = {500-242}, publisher = {NIST}, series = {NIST Special Publication}, year = 1998, url = {http://trec.nist.gov/pubs.html}, biburl = {http://www.bibsonomy.org/bibtex/28a6e2f1ce7ce2ac7dde05a5ce89c68bf/diego_ma}, keywords = {inf_retrieval}, } @proceedings{ZZZ-TREC8, title = {The Eighth {Text} {REtrieval} {Conference} ({TREC-8})}, booktitle = {Proc. {TREC-8}}, editor = {Ellen M. Voorhees and Donna K. Harman}, number = {500-246}, publisher = {NIST}, series = {NIST Special Publication}, year = 1999, url = {http://trec.nist.gov/pubs.html}, biburl = {http://www.bibsonomy.org/bibtex/2ed0a6d93fc9408ffd988effab6d7dd43/diego_ma}, keywords = {inf_retrieval}, } @book{ZZZ-Strzalkowski:1999, title = {Natural Language Information Retrieval}, address = {Dordrecht, The Netherlands}, editor = {Tomek Strzalkowski}, publisher = {Kluwer}, year = 1999, biburl = {http://www.bibsonomy.org/bibtex/266722f58f34908d113e39be8a96969a2/diego_ma}, keywords = {NLP inf_retrieval}, } @proceedings{ZZZ-TREC9, title = {The Ninth {Text} {REtrieval} {Conference} ({TREC-9})}, booktitle = {Proc. {TREC-9}}, editor = {Ellen M. Voorhees and Donna K. Harman}, number = {500-249}, publisher = {NIST}, series = {NIST Special Publication}, year = 2000, url = {http://trec.nist.gov/pubs.html}, biburl = {http://www.bibsonomy.org/bibtex/232355d508802aeb327b4e27cf3b85ba6/diego_ma}, keywords = {inf_retrieval}, } @proceedings{ZZZ-NLPIR, title = {Proceedings of the Workshop on Recent Advances in Natural Language Processing and Information Retrieval}, booktitle = {Proc. ACL workshop in Recent Advances in NLP and IR}, editor = {Judith Klavan and Julio Gonzalo}, organization = {ACL}, year = 2000, biburl = {http://www.bibsonomy.org/bibtex/2d80d8cfda5389d167cf5295950bc343d/diego_ma}, keywords = {NLP inf_retrieval}, } @proceedings{ZZZ-TREC10, title = {The Tenth {Text} {REtrieval} {Conference} ({TREC 2001})}, address = {Gaithersburg, Maryland}, booktitle = {Proc. {TREC 2001}}, editor = {Ellen M. Voorhees and Donna K. Harman}, number = {500-250}, publisher = {NIST}, series = {NIST Special Publication}, year = 2001, url = {http://trec.nist.gov/pubs.html}, biburl = {http://www.bibsonomy.org/bibtex/2d7bec4ab40cbb1ab5dd1a9de27e2d2ca/diego_ma}, keywords = {inf_retrieval}, } @proceedings{ZZZ-TREC11, title = {The Eleventh {Text} {REtrieval} {Conference} ({TREC 2002})}, booktitle = {Proc. {TREC 2002}}, editor = {Ellen M. Voorhees and Lori P. Buckland}, number = {500-251}, publisher = {NIST}, series = {NIST Special Publication}, year = 2002, url = {http://trec.nist.gov/pubs.html}, biburl = {http://www.bibsonomy.org/bibtex/2e13701acb0241f62d33c863706113fb1/diego_ma}, keywords = {inf_retrieval}, } @proceedings{ZZZ-TREC12, title = {The Twelfth {Text} {REtrieval} {Conference} ({TREC 2003})}, booktitle = {Proc. {TREC 2003}}, editor = {Ellen M. Voorhees and Lori P. Buckland}, number = {500-255}, publisher = {NIST}, series = {NIST Special Publication}, year = 2004, url = {http://trec.nist.gov/pubs.html}, biburl = {http://www.bibsonomy.org/bibtex/2cc33a5087b8ff5858957198c5842a11a/diego_ma}, keywords = {inf_retrieval}, }