@article{Athenikos:2010, abstract = {Objectives In this survey, we reviewed the current state of the art in biomedical QA (Question Answering), within a broader framework of semantic knowledge-based QA approaches, and projected directions for the future research development in this critical area of intersection between Artificial Intelligence, Information Retrieval, and Biomedical Informatics. Materials and methods We devised a conceptual framework within which to categorize current QA approaches. In particular, we used “semantic knowledge-based QA” as a category under which to subsume QA techniques and approaches, both corpus-based and knowledge base (KB)-based, that utilize semantic knowledge-informed techniques in the QA process, and we further classified those approaches into three subcategories: (1) semantics-based, (2) inference-based, and (3) logic-based. Based on the framework, we first conducted a survey of open-domain or non-biomedical-domain QA approaches that belong to each of the three subcategories. We then conducted an in-depth review of biomedical QA, by first noting the characteristics of, and resources available for, biomedical QA and then reviewing medical QA approaches and biological QA approaches, in turn. The research articles reviewed in this paper were found and selected through online searches. Results Our review suggested the following tasks ahead for the future research development in this area: (1) Construction of domain-specific typology and taxonomy of questions (biological QA), (2) Development of more sophisticated techniques for natural language (NL) question analysis and classification, (3) Development of effective methods for answer generation from potentially conflicting evidences, (4) More extensive and integrated utilization of semantic knowledge throughout the QA process, and (5) Incorporation of logic and reasoning mechanisms for answer inference. Conclusion Corresponding to the growth of biomedical information, there is a growing need for QA systems that can help users better utilize the ever-accumulating information. Continued research toward development of more sophisticated techniques for processing NL text, for utilizing semantic knowledge, and for incorporating logic and reasoning mechanisms, will lead to more useful QA systems.}, added-at = {2011-12-07T06:54:37.000+0100}, author = {Athenikos, Sofia J. and Han, Hyoil}, biburl = {http://www.bibsonomy.org/bibtex/2b5bf313e10975f54bec54bc2085680f1/diego_ma}, interhash = {a3168b136eba45c912bb0f9185b3e6b6}, intrahash = {b5bf313e10975f54bec54bc2085680f1}, journal = {Computer Methods and Programs in Biomedicine}, keywords = {biomedicalquestion_answering}, library = {Bibsonomy}, pages = {1-24}, timestamp = {2011-12-07T06:54:37.000+0100}, title = {Biomedical Question Answering: A Survey}, url = {http://www.sciencedirect.com/science/article/pii/S0169260709002879}, volume = 99, year = 2010 } @inproceedings{Molla:2011, abstract = {In this paper we introduce some of the key NLP-related problems related to the practice of Evidence Based Medicine and propose the task of multi-document query-focused summarisation as a key approach to solve these problems. We have completed a corpus for the development of such multi-document query-focused summarisation task. The process to build the corpus combined the use of automated extraction of text, manual annotation, and crowdsourcing to find the reference IDs. We perform a statistical analysis of the corpus for the particular use of single-document summarisation and show that there is still a lot of room for improvement from the current baselines.}, added-at = {2011-11-16T08:49:50.000+0100}, author = {Moll{\'a}, Diego and Santiago-Mart{\'i}nez, Maria Elena}, biburl = {http://www.bibsonomy.org/bibtex/2b9f0fa9d3e81750dd3731220af28b784/diego_ma}, booktitle = {Proceedings ALTA 2011}, interhash = {792e5066d52bf4464616ec08bc5eacbe}, intrahash = {b9f0fa9d3e81750dd3731220af28b784}, keywords = {corpus biomedical molla_publication}, timestamp = {2011-11-16T08:49:50.000+0100}, title = {Development of a Corpus for Evidence Based Medicine Summarisation}, year = 2011 } @inproceedings{Ibekwe-Sanjuan:2008, abstract = {We present a methodology combining surface NLP and Machine Learning techniques for ranking asbtracts and generating summaries based on annotated corpora. The corpora were annotated with meta-semantic tags indicating the category of information a sentence is bearing (objective, findings, newthing, hypothesis, conclusion, future work, related work). The annotated corpus is fed into an automatic summarizer for query-oriented abstract ranking and multi- abstract summarization. To adapt the summarizer to these two tasks, two novel weighting functions were devised in order to take into account the distribution of the tags in the corpus. Results, although still preliminary, are encouraging us to pursue this line of work and find better ways of building IR systems that can take into account semantic annotations in a corpus.}, added-at = {2011-10-28T09:19:50.000+0200}, address = {Glasgow}, author = {Ibekwe-Sanjuan, Fidelia and Silvia, Fernandez and Eric, Sanjuan and Eric, Charton}, biburl = {http://www.bibsonomy.org/bibtex/2b20cf8edf0e3fca373328bc564ce75bd/diego_ma}, booktitle = {ECIR'08 Workshop on: Exploiting Semantic Annotations for Information Retrieval}, interhash = {c98454a960afc8fa501120904dcc24b8}, intrahash = {b20cf8edf0e3fca373328bc564ce75bd}, keywords = {text_categorisation summarisation EBM,inf_retrieval biomedical}, pages = 14, timestamp = {2011-10-28T09:19:50.000+0200}, title = {Annotation of Scientific Summaries for Information Retrieval}, url = {http://arxiv.org/abs/1110.5722}, year = 2008 } @article{Kim:2011, added-at = {2011-10-24T09:22:52.000+0200}, author = {Kim, Su Nam and Martinez, David and Cavedon, Lawrence and Yencken, Lars}, biburl = {http://www.bibsonomy.org/bibtex/229d1e1511ceed95324986db8b3c04efb/diego_ma}, interhash = {cda5fb1dd6f6a6b3ec99e8c5cbe6082f}, intrahash = {29d1e1511ceed95324986db8b3c04efb}, journal = {BMC Bioinformatics}, keywords = {EBM classification}, number = {Suppl 2}, pages = {S5}, timestamp = {2011-10-24T09:22:52.000+0200}, title = {Automatic classification of sentences to support Evidence Based Medicine}, volume = 12, year = 2011 } @book{Gosall:2009, added-at = {2011-10-24T08:07:54.000+0200}, address = {Knutsford Cheshire}, author = {Gosall, N. and Gosall, G.}, biburl = {http://www.bibsonomy.org/bibtex/2290871cbc76c450706cd50302873a1f6/diego_ma}, edition = 2, interhash = {e4ce63ebd8cb91dacf3fff6de12fd528}, intrahash = {290871cbc76c450706cd50302873a1f6}, keywords = {EBM}, publisher = {PasTest Ltd.}, timestamp = {2011-10-24T08:07:54.000+0200}, title = {The Doctors' Guide to Critical Appraisal}, year = 2009 } @article{Elhadad:2005, abstract = {{OBJECTIVE:} We present the summarization system in the {PErsonalized} Retrieval and Summarization of Images, Video and Language {(PERSIVAL)} medical digital library. Although we discuss the context of our summarization research within the {PERSIVAL} platform, the primary focus of this article is on strategies to define and generate customized summaries. {METHODS} {AND} {MATERIAL:} Our summarizer employs a unified user model to create a tailored summary of relevant documents for either a physician or lay person. The approach takes advantage of regularities in medical literature text structure and content to fulfill identified user needs. {RESULTS:} The resulting summaries combine both machine-generated text and extracted text that comes from multiple input documents. Customization includes both group-based modeling for two classes of users, physician and lay person, and individually driven models based on a patient record. {CONCLUSIONS:} Our research shows that customization is feasible in a medical digital library.}, added-at = {2011-09-26T09:11:47.000+0200}, author = {Elhadad, N. and Kan, {M.-Y.} and Klavans, J. L. and {McKeown}, K. R.}, biburl = {http://www.bibsonomy.org/bibtex/2579b6aa445684c552e861f38db271e3b/diego_ma}, doi = {10.1016/j.artmed.2004.07.018}, interhash = {7b37645d82ee5a4964695d77e6497e2b}, intrahash = {579b6aa445684c552e861f38db271e3b}, issn = {0933-3657}, journal = {Artificial Intelligence in Medicine}, keywords = {Abstracting\_and\_Indexing\_as\_TopicAutomatic\_Data\_ProcessingComputer\_SystemsDatabases\_as\_TopicHumansInformation\_Storage\_and\_RetrievalMedical\_InformaticsNeural\_Networks\_(Computer)PubMed}, month = {#feb#}, note = {{PMID:} 15811784}, number = 2, pages = {179--198}, timestamp = {2011-09-26T09:11:47.000+0200}, title = {Customization in a unified framework for summarizing medical literature}, url = {http://www.ncbi.nlm.nih.gov/pubmed/15811784}, volume = 33, year = 2005 } @article{Dickersin:1994, abstract = {{OBJECTIVE--To} examine the sensitivity and precision of Medline searching for randomised clinical trials. {DESIGN--Comparison} of results of Medline searches to a "gold standard" of known randomised clinical trials in ophthalmology published in 1988; systematic review (meta-analysis) of results of similar, but separate, studies from many fields of medicine. {POPULATIONS--Randomised} clinical trials published in 1988 in journals indexed in Medline, and those not indexed in Medline and identified by hand search, comprised the gold standard. Gold standards for the other studies combined in the meta-analysis were based on: randomised clinical trials published in any journal, whether indexed in Medline or not; those published in any journal indexed in Medline; or those published in a selected group of journals indexed in Medline. {MAIN} {OUTCOME} {MEASURE--Sensitivity} (proportion of the total number of known randomised clinical trials identified by the search) and precision (proportion of publications retrieved by Medline that were actually randomised clinical trials) were calculated for each study and combined to obtain weighted means. Searches producing the "best" sensitivity were used for sensitivity and precision estimates when multiple searches were performed. {RESULTS--The} sensitivity of searching for ophthalmology randomised clinical trials published in 1988 was 82\%, when the gold standard was for any journal, 87\% for any journal indexed in Medline, and 88\% for selected journals indexed in Medline. Weighted means for sensitivity across all studies were 51\%, 77\%, and 63\%, respectively. The weighted mean for precision was 8\% (median 32.5\%). Most searchers seemed not to use freetext subject terms and truncation of those terms. {CONCLUSION--Although} the indexing terms available for searching Medline for randomised clinical trials have improved, sensitivity still remains unsatisfactory. A mechanism is needed to "'register" known trials, preferably by retrospective tagging of Medline entries, and incorporating trials published before 1966 and in journals not indexed by Medline into the system.}, added-at = {2011-09-26T09:09:45.000+0200}, author = {Dickersin, K. and Scherer, R. and Lefebvre, C.}, biburl = {http://www.bibsonomy.org/bibtex/28d1228ef8177127c849924016f051669/diego_ma}, interhash = {6418d6c6deb1f53f699cd11f30473a6f}, intrahash = {8d1228ef8177127c849924016f051669}, issn = {0959-8138}, journal = {{BMJ} {(Clinical} Research Ed.)}, keywords = {Abstracting\_and\_Indexing\_as\_TopicEvaluation\_Studies\_as\_TopicMEDLINERandomized\_Controlled\_Trials\_as\_TopicSensitivity\_and\_SpecificitySubject\_HeadingsUnited\_States}, month = {#nov#}, note = {{PMID:} 7718048}, number = 6964, pages = {1286--1291}, timestamp = {2011-09-26T09:09:45.000+0200}, title = {Identifying relevant studies for systematic reviews}, url = {http://www.ncbi.nlm.nih.gov/pubmed/7718048}, volume = 309, year = 1994 } @article{Shojania:2001, abstract = {{CONTEXT:} Systematic reviews of the literature are an important resource for clinicians. Unfortunately, the few published strategies for identifying these articles involve {MEDLINE} interfaces not widely available outside of academic medicine. In addition, the performance of these strategies is unknown. {OBJECTIVE:} To develop and evaluate a search strategy for identifying systematic reviews by using a publicly available {MEDLINE} interface {(PubMed).} {DESIGN:} Diagnostic test assessment. {DEFINITION} {OF} {SENSITIVITY:} The proportion of recognized systematic reviews (indexed in the Cochrane Library's Database of Abstracts of Reviews of Effectiveness {[DARE]} or in {ACP} Journal Club) that are identified by the search strategy. {DEFINITION} {OF} {POSITIVE} {PREDICTIVE} {VALUE:} The proportion of articles identified in one of three sample searches (screening for colorectal cancer, thrombolytic therapy for venous thromboembolism, and treatment of dementia) that meet a minimum definition of systematic review. {RESULTS:} Our {PubMed} search strategy identified 93 of 100 {DARE-indexed} systematic reviews, a sensitivity of 93\% (95\% {CI,} 86\% to 97\%). For the sample of systematic reviews drawn from {ACP} Journal Club (n = 103), the {PubMed} strategy achieved a sensitivity of 97\% {(CI,} 91\% to 99\%). When the three sample search strings were used, approximately 50\% of retrieved articles met our minimum definition of systematic review. In contrast, the similar precision of a {PubMed} search restricted to review-type articles (as indexed by {MEDLINE)} was less than 10\%. {CONCLUSIONS:} This search strategy identified most systematic reviews without over-whelming users with numerous false-positive results. A "single-click" filter based on this strategy is now available as part of the Clinical Queries feature of {PubMed.}}, added-at = {2011-09-26T09:07:17.000+0200}, author = {Shojania, Kaveh G. and Bero, Lisa A.}, biburl = {http://www.bibsonomy.org/bibtex/29a8af561090ffd9c519a278a1fe3d2d5/diego_ma}, interhash = {5c98e6ff8fb0e5f02e9526f76967f578}, intrahash = {9a8af561090ffd9c519a278a1fe3d2d5}, issn = {1099-8128}, journal = {Effective Clinical Practice: {ECP}}, keywords = {Evidence-Based\_MedicineHumansInformation\_Storage\_and\_RetrievalMEDLINEMeta-Analysis\_as\_TopicReview\_Literature\_as\_TopicsearchSensitivity\_and\_SpecificitySubject\_HeadingsUser-Computer\_Interface}, month = {#aug#}, note = {{PMID:} 11525102}, number = 4, pages = {157--162}, timestamp = {2011-09-26T09:07:17.000+0200}, title = {Taking advantage of the explosion of systematic reviews: an efficient {MEDLINE} search strategy}, url = {http://www.ncbi.nlm.nih.gov/pubmed/11525102}, volume = 4, year = 2001 } @book{Sackett:2000, added-at = {2011-09-26T09:05:07.000+0200}, author = {Sackett, David L. and Straus, Sharon E. and Richardson, W. Scott and Rosenberg, William and Haynes, R. Brian}, biburl = {http://www.bibsonomy.org/bibtex/2f0f3ed8e0494377572cecb9ccc90f2c9/diego_ma}, edition = 2, interhash = {75567759e1db204e34f5aef3507a9e82}, intrahash = {f0f3ed8e0494377572cecb9ccc90f2c9}, keywords = {EBM}, publisher = {Churchill Livingstone}, timestamp = {2011-09-26T09:05:07.000+0200}, title = {Evidence-Based Medicine: How to Practice and Teach EBM}, year = 2000 } @article{Nakayama:2005, abstract = {{BACKGROUND:} The use of a structured abstract has been recommended in reporting medical literature to quickly convey necessary information to editors and readers. The use of structured abstracts increased during the mid-1990s; however, recent practice has yet to be analyzed. {OBJECTIVES:} This article explored actual reporting patterns of abstracts recently published in selected medical journals and examined what these journals required of abstracts (structured or otherwise and, if structured, which format). {METHODS:} The top thirty journals according to impact factors noted in the {"Medicine,} General and Internal" category of the {ISI} Journal Citation Reports (2000) were sampled. Articles of original contributions published by each journal in January 2001 were examined. Cluster analysis was performed to classify the patterns of structured abstracts objectively. Journals' instructions to authors for writing an article abstract were also examined. {RESULTS:} Among 304 original articles that included abstracts, 188 (61.8\%) had structured and 116 (38.2\%) had unstructured abstracts. One hundred twenty-five (66.5\%) of the abstracts used the introduction, methods, results, and discussion {(IMRAD)} format, and 63 (33.5\%) used the 8-heading format proposed by Haynes et al. Twenty-one journals requested structured abstracts in their instructions to authors; 8 journals requested the 8-heading format; and 1 journal requested it only for intervention studies. {CONCLUSIONS:} Even in recent years, not all abstracts of original articles are structured. The eight-heading format was neither commonly used in actual reporting patterns nor noted in journal instructions to authors.}, added-at = {2011-09-26T09:05:05.000+0200}, author = {Nakayama, Takeo and Hirai, Nobuko and Yamazaki, Shigeaki and Naito, Mariko}, biburl = {http://www.bibsonomy.org/bibtex/2427aa1817001ce89ac6fa4dc7addb907/diego_ma}, interhash = {c54bd6ec75890656b40ea8db695dc361}, intrahash = {427aa1817001ce89ac6fa4dc7addb907}, issn = {1536-5050}, journal = {Journal of the Medical Library Association: {JMLA}}, keywords = {Abstracting_and_ndexing_as_TopicBibliographicDatabasesHumansJournalismMedicalPeriodicals_as_TopicQuality_ControlReference_StandardsUnited_StatesWritingEBM}, month = {#apr#}, note = {{PMID:} 15858627}, number = 2, pages = {237--242}, timestamp = {2011-09-26T09:05:05.000+0200}, title = {Adoption of structured abstracts by general medical journals and format for a structured abstract}, url = {http://www.ncbi.nlm.nih.gov/pubmed/15858627}, volume = 93, year = 2005 } @article{Haynes:1994, abstract = {{OBJECTIVE:} To develop optimal {MEDLINE} search strategies for retrieving sound clinical studies of the etiology, prognosis, diagnosis, prevention, or treatment of disorders in adult general medicine. {DESIGN:} Analytic survey of operating characteristics of search strategies developed by computerized combinations of terms selected to detect studies meeting basic methodologic criteria for direct clinical use in adult general medicine. {MEASURES:} The sensitivities, specificities, precision, and accuracy of 134,264 unique combinations of search terms were determined by comparison with a manual review of all articles (the "gold standard") in ten internal medicine and general medicine journals for 1986 and 1991. {RESULTS:} Less than half of the studies of the topics of interest met basic criteria for scientific merit for testing clinical applications. Combinations of search terms reached peak sensitivities of 82\% for sound studies of etiology, 92\% for prognosis, 92\% for diagnosis, and 99\% for therapy in 1991. Compared with the best single terms, multiple terms increased sensitivity for sound studies by over 30\% (absolute increase), but with some loss of specificity when sensitivity was maximized. For 1986, combinations reached peak sensitivities of 72\% for etiology, 95\% for prognosis, 86\% for diagnosis, and 98\% for therapy. When search terms were combined to maximize specificity, over 93\% specificity was achieved for all purpose categories in both years. Compared with individual terms, combined terms achieved near-perfect specificity that was maintained with modest increases in sensitivity in all purpose categories except therapy. Increases in accuracy were achieved by combining terms for all purpose categories, with peak accuracies reaching over 90\% for therapy in 1986 and 1991. {CONCLUSIONS:} The retrieval of studies of important clinical topics cited in {MEDLINE} can be substantially enhanced by selected combinations of indexing terms and textwords.}, added-at = {2011-09-26T09:05:01.000+0200}, author = {Haynes, R. Brian and Wilczynski, Nancy L. and {McKibbon}, K. Ann and Walker, Cynthia J. and Sinclair, John C.}, biburl = {http://www.bibsonomy.org/bibtex/2c41eb6aa125356175a6cf6af8b194f4a/diego_ma}, interhash = {c1fa8154deeddda9f4b6838f6ba78ca6}, intrahash = {c41eb6aa125356175a6cf6af8b194f4a}, issn = {1067-5027}, journal = {Journal of the American Medical Informatics Association: {JAMIA}}, keywords = {DiagnosisEBMEpidemiologic\_MethodsMEDLINEPrognosisResearch\_DesignsearchTerminology\_as\_TopicTherapeutics}, month = {#dec#}, note = {{PMID:} 7850570}, number = 6, pages = {447--458}, timestamp = {2011-09-26T09:05:01.000+0200}, title = {Developing optimal search strategies for detecting clinically sound studies in {MEDLINE}}, url = {http://www.ncbi.nlm.nih.gov/pubmed/7850570}, volume = 1, year = 1994 } @article{Haynes:2005, abstract = {{OBJECTIVE:} To develop and test optimal Medline search strategies for retrieving sound clinical studies on prevention or treatment of health disorders. {DESIGN:} Analytical survey. {DATA} {SOURCES:} 161 clinical journals indexed in Medline for the year 2000. {MAIN} {OUTCOME} {MEASURES:} Sensitivity, specificity, precision, and accuracy of 4862 unique terms in 18 404 combinations. {RESULTS:} Only 1587 (24.2\%) of 6568 articles on treatment met criteria for testing clinical interventions. Combinations of search terms reached peak sensitivities of 99.3\% (95\% confidence interval 98.7\% to 99.8\%) at a specificity of 70.4\% (69.8\% to 70.9\%). Compared with best single terms, best multiple terms increased sensitivity for sound studies by 4.1\% (absolute increase), but with substantial loss of specificity (absolute difference 23.7\%) when sensitivity was maximised. When terms were combined to maximise specificity, 97.4\% (97.3\% to 97.6\%) was achieved, about the same as that achieved by the best single term (97.6\%, 97.4\% to 97.7\%). The strategies newly reported in this paper outperformed other validated search strategies except for two strategies that had slightly higher specificity (98.1\% and 97.6\% v 97.4\%) but lower sensitivity (42.0\% and 92.8\% v 93.1\%). {CONCLUSION:} New empirical search strategies have been validated to optimise retrieval from Medline of articles reporting high quality clinical studies on prevention or treatment of health disorders.}, added-at = {2011-09-26T09:05:00.000+0200}, author = {Haynes, R. Brian and {McKibbon}, K. Ann and Wilczynski, Nancy L. and Walter, Stephen D. and Werre, Stephen R.}, biburl = {http://www.bibsonomy.org/bibtex/25c89306808174f061c1f27d8704e6e02/diego_ma}, doi = {10.1136/bmj.38446.498542.8F}, interhash = {31369c6feea04f3f29484ade72ce6f8d}, intrahash = {5c89306808174f061c1f27d8704e6e02}, issn = {1468-5833}, journal = {{BMJ} {(Clinical} Research Ed.)}, keywords = {Information\_Storage\_and\_RetrievalMedical\_Subject\_HeadingsMEDLINESensitivity\_and\_Specificity}, month = {#may#}, note = {{PMID:} 15894554}, number = 7501, pages = 1179, timestamp = {2011-09-26T09:05:00.000+0200}, title = {Optimal search strategies for retrieving scientifically strong studies of treatment from Medline: analytical survey}, url = {http://www.ncbi.nlm.nih.gov/pubmed/15894554}, volume = 330, year = 2005 } @article{Allen:1999, added-at = {2011-09-26T08:54:38.000+0200}, author = {Allen, I. Elaine and Olkin, Ingram}, biburl = {http://www.bibsonomy.org/bibtex/225183421b9faa7020542516964d68f06/diego_ma}, interhash = {8d5afb70e0fa42a643dda53e353b002f}, intrahash = {25183421b9faa7020542516964d68f06}, issn = {0098-7484}, journal = {{JAMA:} The Journal of the American Medical Association}, keywords = {Meta-Analysis\_as\_Topic Evidence-Based\_MedicineInformation\_Storage\_and\_Retrieval Time\_Factors Reproducibility\_of\_Results}, month = {#aug#}, note = {{PMID:} 10517715}, number = 7, pages = {634--635}, timestamp = {2011-09-26T08:54:38.000+0200}, title = {Estimating time to conduct a meta-analysis from number of citations retrieved}, url = {http://www.ncbi.nlm.nih.gov/pubmed/10517715}, volume = 282, year = 1999 } @inproceedings{Tang:2009, abstract = {The problem of low-quality information on the Web is nowhere more important than in the domain of health, where unsound information and misleading advice can have serious consequences. The quality of health web sites can be rated by subject experts against evidence-based guidelines. We previously developed an automated quality rating technique (AQA) for depression websites and showed that it correlated 0.85 with such expert ratings. In this paper, we use AQA to filter or rerank Google results returned in response to queries relating to depression. We compare this to an unrestricted quality-oriented (AQA based) focused crawl starting from an Open Directory category and a conventional crawl with manually constructed seedlist and inclusion rules. The results show that post-processed Google outperforms other forms of search engine restricted to the domain of depressive illness on both relevance and quality.}, added-at = {2011-09-23T03:57:21.000+0200}, address = {Berlin, Heidelberg}, author = {Tang, Thanh and Hawking, David and Sankaranarayana, Ramesh and Griffiths, Kathleen M. and Craswell, Nick}, biburl = {http://www.bibsonomy.org/bibtex/2e10fc5b26bc35d58785f9ec62ad2ce47/diego_ma}, booktitle = {ECIR '09 Proceedings of the 31th European Conference on IR Research on Advances in Information Retrieval}, citeseerurl = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.156.5337}, interhash = {a67f3616ba84a8dd377a1db1e6b1bb9d}, intrahash = {e10fc5b26bc35d58785f9ec62ad2ce47}, keywords = {EBM search evidence retrieval}, library = {Web}, publisher = {Springer}, timestamp = {2011-09-23T03:57:21.000+0200}, title = {Quality-oriented Search for Depression Portals}, year = 2009 } @inproceedings{Sarker:2011, abstract = {The practice of Evidence Based Medicine requires practitioners to extract evidence from published medical literature and grade the extracted evidence in terms of quality. With the goal of automating the time-consuming grading process, we assess the effects of a number of factors on the grading of the evidence. The factors include the publication types of individual articles, publication years, journal information and article titles. We model the evidence grading problem as a supervised classification problem and show, using several machine learning algorithms, that the use of publication types alone as features gives an accuracy close to 70%. We also show that the other factors do not have any notable effects on the evidence grades.}, added-at = {2011-09-19T10:29:21.000+0200}, address = {Bled, Slovenia}, author = {Sarker, Abeed and Moll{\'a}, Diego and Paris, C{\'e}cile}, biburl = {http://www.bibsonomy.org/bibtex/2b53d63481104185cc39045b7202993cf/diego_ma}, booktitle = {Proceedings of the Third International Workshop on Health Document Text Mining and Information Analysis (LOUHI 2011)}, interhash = {7e48f7312be0e074e4b947d0f1ab256b}, intrahash = {b53d63481104185cc39045b7202993cf}, keywords = {molla_publicationEBMSORTappraisalmolla_medicalnlp}, pages = {51-58}, timestamp = {2011-09-19T10:29:21.000+0200}, title = {Towards Automatic Grading of Evidence}, url = {http://www.ics.mq.edu.au/~diego/publications/Louhi2011.pdf}, year = 2011 } @inproceedings{Daume:2006, abstract = {We present BAYESUM (for ???Bayesian summarization???), a model for sentence extraction in query-focused summarization. BAYESUM leverages the common case in which multiple documents are relevant to a single query. Using these documents as reinforcement for query terms, BAYESUM is not afflicted by the paucity of information in short queries. We show that approximate inference in BAYESUM is possible on large data sets and results in a stateof-the-art summarization system. Furthermore, we show how BAYESUM can be understood as a justified query expansion technique in the language modeling for IR framework.}, added-at = {2011-08-05T10:08:44.000+0200}, author = {Ill, Hal Daum{\'e} and Marcu, Daniel}, biburl = {http://www.bibsonomy.org/bibtex/250b0b54c7a9a2e56b3ef3e95142c753b/diego_ma}, crossref = {ZZZ-COLINGACL:2006}, interhash = {fba42b320e9d083f1708c36262c30877}, intrahash = {50b0b54c7a9a2e56b3ef3e95142c753b}, keywords = {summarisation}, library = {Mine (October 2006)}, pages = {305--312}, review = {Key idea: 1. Extract and GENERALISE patterns. The patterns are generalised by creating word classes on the basis of their distributional similarity. 2. Validate the extracted patterns. The patterns are ranked by examining the frequencies of words in their prefix, infix and postfix. Candidate facts are ranked by checking whether they belong to some class as known (seed) facts.}, timestamp = {2011-08-05T10:08:44.000+0200}, title = {Bayesian Query-Focused Summarization}, url = {http://www.isi.edu/\~{}marcu/papers.html}, year = 2006 } @inproceedings{Vliegendhart:2011, abstract = {This paper reports useful observations made during the design and test of a crowdsourcing task with a high “imaginative load”, a term we introduce to designate a task that requires workers to answer questions from a hypothetical point of view that is beyond their daily experiences. We find that workers are able to deliver high quality responses to such HITs, but that it is important that the HIT title allows workers to formulate accurate expectations of the task. Also important is the inclusion of free-text justification questions that target specific items in a pattern that is not obviously predictable. These findings were supported by a small-scale experiment run on several crowdsourcing platforms.}, added-at = {2011-08-05T09:29:31.000+0200}, author = {Vliegendhart, Raynor and Larson, Martha and Kofler, Christoph and Eickhoff, Carsten and Pouwelse, Johan}, biburl = {http://www.bibsonomy.org/bibtex/2af3af7288096816eefa1233787179a14/diego_ma}, booktitle = {Proceedings WSDM 2011 Workshop on Crowdsourcing for Search and Data Mining (CSDM 2011)}, interhash = {274cc2e94c8dd5f5d5b907b12deef604}, intrahash = {af3af7288096816eefa1233787179a14}, keywords = {mechanical_turk}, library = {MQRDG2010 (August 2011)}, pages = {27-30}, timestamp = {2011-08-05T09:29:31.000+0200}, title = {Investigating Factors Influencing Crowdsourcing Tasks with High Imaginative Load}, year = 2011 } @inproceedings{Gillick:2010, abstract = {We provide evidence that intrinsic evaluation of summaries using Amazon’s Mechanical Turk is quite difficult. Experiments mirroring evaluation at the Text Analysis Conference’s summarization track show that nonexpert judges are not able to recover system rankings derived from experts.}, added-at = {2011-08-05T09:25:15.000+0200}, author = {Gillick, Dan and Liu, Yang}, biburl = {http://www.bibsonomy.org/bibtex/2e349ad3abc82bbbd253bc5d94fdd20e7/diego_ma}, booktitle = {Proceedings NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk}, interhash = {82fe8aa6efa6c742f04c207373ef284e}, intrahash = {e349ad3abc82bbbd253bc5d94fdd20e7}, keywords = {summarisation mechanical_turk}, library = {Bibsonomy, MQRDG2010 (August 2011)}, pages = {148-151}, timestamp = {2011-08-05T09:25:15.000+0200}, title = {Non-Expert Evaluation of Summarization Systems is Risky}, year = 2010 } @inproceedings{Thomas:2010, added-at = {2011-03-12T03:13:38.000+0100}, author = {Thomas, Paul and Noak, Katherine and Paris, Cecile}, biburl = {http://www.bibsonomy.org/bibtex/2d19bed71532c5644365d5233cb551d6b/diego_ma}, booktitle = {Proceedings Information Interaction in Context (IIiX)}, interhash = {0c51830f012555d67dafb613fc309f94}, intrahash = {d19bed71532c5644365d5233cb551d6b}, keywords = {evaluation}, library = {Cecile's? (March 2011)}, timestamp = {2011-03-12T03:13:38.000+0100}, title = {Evaluating Interfaces for Government Metasearch}, year = 2010 } @manual{Schmidberger:2009, added-at = {2011-03-02T05:41:50.000+0100}, author = {Schmidberger, Gabi and Hall, Mark and Kirkby, Richard and Frank, Eibe and Witten, Ian H.}, biburl = {http://www.bibsonomy.org/bibtex/2d7d600300e80b456555a56cb2ac0366a/diego_ma}, interhash = {e19ed875e6be827316654734de1f68f2}, intrahash = {d7d600300e80b456555a56cb2ac0366a}, keywords = {machine\_learning classification Weka}, library = {See bibsonomy file (Feb 2011)}, month = {July}, note = {Selected tutorial notes}, organization = {University of Waikato}, review = {I have the following notes: Tutorial 1: Introduction to the WEKA Explorer Tutorial 2: Nearest Neighbor Learning and Decision Trees Tutorial 3: Classification Boundaries Tutorial 4: Preprocessing and Parameter Tuning Tutorial 5: Document Classification Tutorial 6: Mining Association Rules}, timestamp = {2011-03-02T05:41:50.000+0100}, title = {Practical Data Mining (COMP321)}, year = 2009 }