31 Hits in 10.7 sec

Essie: A Concept-based Search Engine for Structured Biomedical Text

N. C. Ide, R. F. Loane, D. Demner-Fushman
2007 JAMIA Journal of the American Medical Informatics Association  
Essie shows that a judicious combination of exploiting document structure, phrase searching, and concept based query expansion is a useful approach for information retrieval in the biomedical domain.  ...  Essie is a phrase-based search engine with term and concept query expansion and probabilistic relevancy ranking.  ...  Essie approached the task as document retrieval, indexing each paragraph as a document and applying the standard Essie retrieval strategies to queries created for each question.  ... 
doi:10.1197/jamia.m2233 pmid:17329729 pmcid:PMC2244877 fatcat:l3dg4ofxtnakbdhijktzci4p5i

State-of-the-art in biomedical literature retrieval for clinical cases: a survey of the TREC 2014 CDS track

Kirk Roberts, Matthew Simpson, Dina Demner-Fushman, Ellen Voorhees, William Hersh
2015 Information retrieval (Boston)  
In this article, we provide an overview of the task, a survey of the information retrieval methods employed by the participants, an analysis of the results, and a discussion on the future directions for  ...  Providing access to relevant biomedical literature in a clinical setting has the potential to bridge a critical gap in evidence-based medicine.  ...  The authors would also like to thank the following participants for providing feedback and clarifications: Raymond Wan, Paul McNamee, Jean Garcia-Gathright, Joao Palotti, Eva D'hondt, Dawit Girmay, Afshin  ... 
doi:10.1007/s10791-015-9259-x fatcat:vshyzquam5gxdb2zntfrfishl4

Context-based literature digital collection search

Nattakarn Ratprasartporn, Jonathan Po, Ali Cakmak, Sulieman Bani-Ahmad, Gultekin Ozsoyoglu
2008 The VLDB journal  
Using genomics-oriented PubMed publications as the testbed and Gene Ontology terms as contexts, our experiments indicate that the proposed context-based search approach produces search results with up  ...  We identify two issues with searching literature digital collections within digital libraries: (a) there are no effective paper-scoring and ranking mechanisms.  ...  For the papers that do not reside in any selected contexts, group those papers together into a "remainder context" (d) Re-rank search results and return the located publications The CBS (and CBS_all) approach  ... 
doi:10.1007/s00778-008-0099-9 fatcat:tuxto4i7gfdftljf6r4vqbdg24

Adaptation of machine translation for multilingual information retrieval in the medical domain

Pavel Pecina, Ondřej Dušek, Lorraine Goeuriot, Jan Hajič, Jaroslava Hlaváčová, Gareth J.F. Jones, Liadh Kelly, Johannes Leveling, David Mareček, Michal Novák, Martin Popel, Rudolf Rosa (+2 others)
2014 Artificial Intelligence in Medicine  
The IR methods include morphological normalization and using multiple translation variants for query expansion.  ...  Methods and Data. Our MT system is Moses, a state-of-the-art phrase-based statistical machine translation system.  ...  They use two techniques: SMT tuning on genre-specific data and discriminative re-ranking of n-best lists optimizing retrieval effectiveness.  ... 
doi:10.1016/j.artmed.2014.01.004 pmid:24680188 fatcat:zcxf36ln6zgzzkdjvoq56h5thm

A Framework for Enhancing the Query and Medical Record Representations for Patient Search

Nut Limsopatham
2015 SIGIR Forum  
Limsopatham, Nut (2014) A framework for enhancing the query and medical record representations for patient search. PhD thesis.  ...  Typically, LTR re-ranks an initial ranking (the so-called sample) retrieved using an IR approach to promote documents with the desired factors to the top ranks.  ...  Specifically, for a given query q and a patient p, we adapt xQuAD (Santos et al., 2010a) to iteratively re-rank the medical records in R p by maximising the mixture of the relevance and the coverage  ... 
doi:10.1145/2795403.2795420 fatcat:4z7m4dv4jvho5gy2hq5tqgyiyi

Event Extraction from Biomedical Literature [article]

Abdur Rahman M.A. Basher, Alexander S. Purdy, Inanc Birol
2015 bioRxiv   pre-print
NLP approaches to the automatic extraction of biomedical entities and relationships may assist the development of explanatory models that can comprehensively scan and summarize biomedical articles for  ...  PubMed, the leading repository for biomedical literature, currently holds over 26 million records, and is growing at a rate of over 1.2 million records per year, with about 300 records added daily that  ...  Acknowledgment We thank the Sequencing Lab and the Bioinformatics Technology Lab (BTL) at Genome Sciences Centre, British Columbia Cancer Agency for their assistance with this article.  ... 
doi:10.1101/034397 fatcat:uq5y7yop2nhyfg4ijjy34mwd6e

Comparing citation contexts for information retrieval

Anna Ritchie, Stephen Robertson, Simone Teufel
2008 Proceeding of the 17th ACM conference on Information and knowledge mining - CIKM '08  
Chapter 3 discusses the test collection paradigm for evaluation of information retrieval systems and describes how and why we built our test collection.  ...  This thesis investigates taking words from around citations to scientific papers in order to create an enhanced document representation for improved information retrieval.  ...  Retrieved pages can then be re-ranked by their PageRank.  ... 
doi:10.1145/1458082.1458113 dblp:conf/cikm/RitchieRT08 fatcat:bd4azphahbhj3mrn3gfjvozkhy

EMBnet.journal 18 Suppl. B

EMBnet Journal
2012 EMBnet journal  
This paper revises and extends the paper "ONCO-i2b2: improve patients selection through case-based information retrieval techniques", by D.  ...  Carlo Bernasconi and the Collegio Ghislieri in Pavia for their active support.  ...  Fourth, we observed that the re-ranking based on citation networks improved results for the three benchmarks, but mainly for the related patent search (Table 1) .  ... 
doi:10.14806/ej.18.b.592 fatcat:wlwsmbdlfzbjtk7vyhiabdov6q

Using UMLS-based Re-Weighting Terms as a Query Expansion Strategy

Weizhong Zhu, Xuheng Xu, Xiaohua Hu, Il-Yeol Song, R.B. Allen
2006 IEEE International Conference on Granular Computing  
These search engines, however, still return many results that are irrelevant to the intention of a user's query. To improve precision and recall, various query expansion strategies are widely used.  ...  In this paper, we explore the three widely used query expansion strategieslocal analysis, global analysis, and ontology-based term reweighting across various search engines.  ...  Re-Ranking Search Engine Ranked Documents 1.  ... 
doi:10.1109/grc.2006.1635786 dblp:conf/grc/ZhuXHSA06 fatcat:6jh364454zbgfpor7zlpuqdega

Recent advances in methods of lexical semantic relatedness – a survey

2012 Natural Language Engineering  
DEDICATION This thesis is dedicated to my brilliant wife, Yaxin Liu, for her infinite love and support throughout the course of this work.  ...  Resolving ambiguity concerns recognising the true referent entity of a name reference, essentially a further named entity 'recognition' step and often a compulsory pro-VI  ...  used for Information Retrieval tasks, and transfers the scores to useful features for learning NER.  ... 
doi:10.1017/s1351324912000125 fatcat:b62qbqwrqfaf3gytw22yktc5ae

Exploring topic structure

Jiyin He
2012 SIGIR Forum  
Exploring topic structure: Coherence, diversity and relatedness He, J. Link to publication Citation for published version (APA): He, J. (2011).  ...  Exploring topic structure: Coherence, diversity and relatedness General rights It is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or  ...  We can look at this desirable behavior as local re-ranking in contrast to global re-ranking, which allows for a document to take a brutal jump from the very bottom to the very top of the final ranking.  ... 
doi:10.1145/2215676.2215690 fatcat:mh34cmstt5cr3phgj2cltgikie

Biomedical Natural Language ProcessingKevin Bretonnel Cohen and Dina Demner-Fushman (University of Colorado School of Medicine, and National Library of Medicine)John Benjamins Publishing (Book series on Natural Language Processing, edited by Ruslan Mitkov, volume 11), 2014, 160 pp; hardbound, ISBN 978-90-272-4997-5

Jin-Dong Kim
2017 Computational Linguistics  
Acknowledgments We would like to thank all members of our research group, IT for Health, for their support and input.  ...  Acknowledgments The work presented in this paper comes from a 3 year project (ALADIN) started in 2009 and funded by the French Agence Nationale de la Recherche (National Research Agency -ANR) in the context  ...  a word in the document are included in the final re-ranking phase.  ... 
doi:10.1162/coli_r_00281 fatcat:6abwqppd3bgyvkzfc2mq6kzo6u

What Makes a Top-Performing Precision Medicine Search Engine? Tracing Main System Features in a Systematic Way [article]

Erik Faessler, Michel Oleynik, Udo Hahn
2020 pre-print
and keyword boosting.  ...  From 2017 to 2019 the Text REtrieval Conference (TREC) held a challenge task on precision medicine using documents from medical publications (PubMed) and clinical trials.  ...  Their system supports terminology-based query expansion (related to genes and diseases), ranking models (different variants of Learning-to-Rank (LTR) and BM25) and re-ranking strategies based on citation  ... 
doi:10.1145/3397271.3401048 arXiv:2006.02785v1 fatcat:i42e34gjqjgufmzszb5bdxfjyi

A Roadmap for Big Model [article]

Sha Yuan, Hanyu Zhao, Shuai Zhao, Jiahong Leng, Yangxiao Liang, Xiaozhi Wang, Jifan Yu, Xin Lv, Zhou Shao, Jiaao He, Yankai Lin, Xu Han (+88 others)
2022 arXiv   pre-print
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.  ...  At present, there is a lack of research work that sorts out the overall progress of BMs and guides the follow-up research.  ...  There are two lines of research for statistics-based methods [1318] . The first one re-ranks candidate output during text generating by training a n-gram model [1316] or syntactic model [1316] .  ... 
arXiv:2203.14101v4 fatcat:rdikzudoezak5b36cf6hhne5u4

The People's Encyclopedia Under the Gaze of the Sages: A Systematic Review of Scholarly Research on Wikipedia

Chitu Okoli, Mohamad Mehdi, Mostafa Mesgari, Finn Årup Nielsen, Arto Lanamäki
2012 Social Science Research Network  
Wikipedia has become one of the ten most visited sites on the Web, and the world's leading source of Web reference information.  ...  This article presents a systematic review of scholarly research on Wikipedia. We describe our detailed, rigorous methodology for identifying over 450 scholarly studies of Wikipedia.  ...  Rodríguez-Posada (emijrp) for his model WikiPapers site, upon which much of WikiLit was based.  ... 
doi:10.2139/ssrn.2021326 fatcat:egbnz5qzcjbfbnzxlz75x4ktz4
« Previous Showing results 1 — 15 out of 31 results