@InProceedings{Amrani:2004:SAS, author = "Ahmed Amrani and Yves Kodratoff and Oriane Matte-Tailliez", booktitle = "Advances in Knowledge Discovery and Data Mining 8th Pacific-Asia Conference, PAKDD 2004", title = "A Semi-automatic System for Tagging Specialized Corpora", volume = "3056", publisher = "Springer", pages = "670--681", year = "2004", ISBN = "3-540-22064-X", bibsource = "DBLP, http://dblp.uni-trier.de", series = "Lecture Notes in Computer Science", keywords = "POS", } @Article{Ashburner:2000:GOT, author = "M. Ashburner and C. A. Ball and J. A. Blake and D. Botstein and H. Butler and J. M. Cherry and A. P. Davis and K. Dolinski and S. S. Dwight and J. T. Eppig and M. A. Harris and D. P. Hill and L. Issel-Tarver and A. Kasarskis and S. Lewis and J. C. Matese and J. E. Richardson and M. Ringwald and G. M. Rubin \& G. Sherlock", title = "Gene Ontology: tool for the unification of biology", journal = "Nature Genetics", volume = "25", pages = "25--29", month = may, year = "2000", comments = "Three ontologies: Biology process, molecular function and cellular component applied to all eucaryotes", keywords = "ont-corp", } @InProceedings{Baclawski:2000:KRI, author = "K. Baclawski and J. Cigna and M. M. Kokar and P. Mager and B. Indurkhya", booktitle = "Proceedings of the Pacific Symposium on Biocomputing", title = "Knowledge representation and indexing using the unified medical language system", pages = "493--504", year = "2000", comments = "Constructs and index knowledge representations of biomedical documetns using UMLS. The knowledge representation diagrams produced are called keynets based in RDF. Identification of names using heuristic rules (Fukuda etc) combined with UMLS ontology. Uses domain-independent knowledge (for stemming, pos, grammar rules) and the UMLS ontology for the domain-dependent knowledge.", keywords = "relations", } @Article{Blaschke:2002:FBM, author = "C. Blaschke and A. Valencia", title = "The frame-based module of the Suiseki information extraction system", journal = "IEEE Intelligent Systems", number = "17", pages = "14--20", year = "2002", keywords = "relations", pdf = "http://www.pdg.cnb.uam.es/blaschke/publications/finalProofs_x2valencia1.pdf.gz", } @InProceedings{Bodenreider:2003:EAM, author = "Olivier Bodenreider and Serguei V. Pakhomov", editor = "Sophia Ananiadou and Jun'ichi Tsujii", booktitle = "Proceedings of the ACL 2003 Workshop on Natural Language Processing in Biomedicine", title = "Exploring Adjectival Modification in Biomedical Discourse Across Two Genres", pages = "105--112", year = "2003", keywords = "NER", pdf = "http://www.aclweb.org/anthology/W03-1314.pdf", } @Article{Bruijn:2002:GCO, author = "B. Bruijn and J. Martin", title = "Getting to the (c)ore of knowledge: mining biomedical literature", journal = "Int. Journal Medical Informatics", number = "67", pages = "7--18", year = "2002", keywords = "overview", } and Information Extraction from Medical Documents), in press @Article{Bunescu:2004:CEL, author = {Bunescu, R. and Ge, R. and Kate, R.J. and Marcotte, E.M. and Mooney, R.J. and Ramani, A.K. and Wong, Y.W.}, title = {Comparative Experiments on Learning Information Extractors for Proteins and their Interactions}, journal = {Artificial Intelligence in Medicine (Special Issue on Summarization and Information Extraction from Medical Documents)}, year = {2004}, OPTkey = {}, OPTvolume = {}, OPTnumber = {}, OPTpages = {}, OPTmonth = {}, OPTnote = {}, OPTannote = {} } @InProceedings{Castano:2002:ARB, author = "J. Casta\~no and J. Zhang and J. Pustejovsky", booktitle = "International Symposium on Reference Resolution", title = "Anaphora Resolution in Biomedical Literature", year = "2002", keywords = "anaphora", } @TechReport{Cohen:2004:NLP, author = "K. Bretonnel Cohen and Lawrence Hunter", title = "Natural Language Processing and Systems Biology", institution = "University of Colorado School of Medicine Denver, CO, USA", year = "2004", keywords = "overview", } @InProceedings{Collier:2000:ENG, author = "N. Collier and C. Nobata and J. Tsujii", booktitle = "Proceedings of the 18th International Conference on Computational Linguistics (COLING'2000), Saarbrucken, Germany", title = "Extracting the names of genes and gene products with a hidden Markov model", month = jul, year = "2000", approach = "linear interpolating hidden Markov model", comments = "They argue in this paper that models based on HMMs and decision trees are much more generalisable and adaptable to new classes of words than systems based on traditional hand-built patterns and domain specific heuristics rules", corpus = "A 100 Medline abstracts marked-up by domain experts with term classes such as proteins and DNA", groupe = "University of Tokyo", keywords = "NER", } @Article{Collier:2002:AAC, author = "N. Collier and C. Nobata and J. Tsujii", title = "Automatic Acquisition and Classification of Terminology using a Tagged Corpus in the Molecular Biology Domain", journal = "Journal of Terminology, John Benjamins", volume = "7", number = "2", pages = "239--257", year = "2002", keywords = "NER", } @Article{Corney:2004:BEB, author = "D. P. Corney and B. F. Buxton and W. B. Langdon and D. T. Jones", title = "Bio{RAT}: Extracting Biological Information from Full-length Papers", journal = "Bioinformatics", month = jul, year = "2004", keywords = "relations", } @InProceedings{Craven:1999:CBK, author = "M. Craven and J. Kumlien", booktitle = "Proceedings of International Conference on Intelligent Systems for Molecular Biology", title = "Constructing biological knowledge bases by extracting information from text sources", pages = "77--86", year = "1999", comments = "Machine learning approach to find subcellular-localization(protein, Subcellular-Structure) relation. Uses the YPD data set as a training set.", keywords = "relations", } @InProceedings{Cutting:1992:PPS, author = "D. Cutting and J. Kupiec and J. Pedersen and P. Sibun", booktitle = "Proceedings of the Third Conference on Applied Natural Language Processing", title = "A Practical Part-of-Speech Tagger", pages = "133--140", year = "1992", keywords = "POS", ps = "ftp://parcftp.xerox.com/pub/tagger/anlp92.ps", } @Article{Dickman:2003:TM, author = "S. Dickman", title = "Tough Mining", journal = "PLoS Biology", volume = "1", number = "2", pages = "144--147", year = "2003", keywords = "overview", } @InProceedings{Erjavec:2003:EBR, author = "Toma\v{z} Erjavec and Jin-Dong Kim and Tomoko Ohta and Yuka Tateisi and Jun'ichi Tsujii", editor = "Sophia Ananiadou and Jun'ichi Tsujii", booktitle = "Proceedings of the ACL 2003 Workshop on Natural Language Processing in Biomedicine", title = "Encoding Biomedical Resources in {TEI}: The Case of the {GENIA} Corpus", pages = "97--104", year = "2003", URL = "http://www.aclweb.org/anthology/W03-1313.pdf", keywords = "ont-corp", } @Article{Franzen:2002:PNH, author = "K. Franzen and G. Eriksson and F. Olsson and L. Asker and P. Liden and J. Coster", title = "Protein names: how to find them", journal = "Int J Med Inf.", volume = "4", number = "67", pages = "49--61", month = dec, year = "2002", comments = "uses a combination of heuristic pattern matching techniques and a full syntactic analysis to find names of proteins", groupe = "Swedish Institute of Computer Science", keywords = "NER", ontology = "genia", pdf = "Papers/proteinNames.pdf", site = "http://www.sics.se/humble/projects/prothalt", tool = "Yapex", } @Article{Friedman:2001:GNL, author = "C. Friedman and P. Kra M. Krauthammer and H. Yu and A. Rzhetsky", title = "{GENIES}: a natural-langauge processing system for the extraction of molecular pathways from journal articles", journal = "Bioinformatics", volume = "17", number = "1", pages = "74--82", year = "2001", keywords = "relations", } @InProceedings{Fukuda:1998:TIE, author = "K. Fukuda and T. Tsunoda and A. Tamura and T. Takagi", booktitle = "Proc. of the Pacific Symposium on Biocomputing", title = "Toward information extraction: Identifying protein names from biological papers", year = "1998", abstract = "To solve the mystery of the life phenomenon, we must clarify when genes are expressed and how their products interact with each other. But since the amount of continuously updated knowledge on these interactions is massive and is only available in the form of published articles, an intelligent information extraction (IE) system is needed. To extract these information directly from articles, the system must firstly identify the material names. However, medical and biological documents often include proper nouns newly made by the authors, and conventional methods based on domain specific dictionaries cannot detect such unknown words or coinages. In this study, we propose a new method of extracting material names, PROPER, using surface clue on character strings. It extracts material names in the sentence with 94.70% precision and 98.84% recall, regardless of whether it is already known or newly defined.", comments = "Uses the characteristics of proper noun description in the biological field and does not require any specific term dictionary prepared in advance (presence of upper case and special characters)", groupe = "Human Genome Center, Tokyo", keywords = "NER", pdf = "Papers/fukuda_98_psb_3.pdf", site = "http://www.hgc.ims.u-tokyo.ac.jp/service/tooldoc/KeX/intro.html", tool = "KeX", } @InProceedings{Harkema:2004:LST, author = "H. Harkema and R. Gaizauskas and M. Hepple and A. Roberts and I. Roberts and N. Davis and Y. Guo", booktitle = "BionLINK 2004: Linking Biological Literature, Ontologies, and Databases, ACL", title = "A Large-Scale Terminology Resource for Biomedical Text Processing", pages = "53--60", year = "2004", keywords = "NER", } @InProceedings{Hepple:2000:ICA, author = "M. Hepple", booktitle = "Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics (ACL-2000)", title = "Indepedence and Commitment: Assumptions for Rapid Training and Execution of Rule-based {POS} Taggers", pages = "278--285", year = "2000", keywords = "POS", pdf = "ftp://ftp.dcs.shef.ac.uk/home/hepple/papers/acl00.pdf", } @Article{Hirschman:2002:ACL, author = "L. Hirschman and L. Wong {J.C. Park, J. Tsujii} and C. H. Wu", title = "Accomplishments and challenges in literature data mining for biology", journal = "Bioinformatics", volume = "18", number = "12", pages = "1553--1561", year = "2002", keywords = "overview", } @InProceedings{Hou:2003:EPP, author = "Wen-Juan Hou and Hsin-Hsi Chen", editor = "Sophia Ananiadou and Jun'ichi Tsujii", booktitle = "Proceedings of the ACL 2003 Workshop on Natural Language Processing in Biomedicine", title = "Enhancing Performance of Protein Name Recognizers Using Collocation", pages = "25--32", year = "2003", keywords = "NER", pdf = "http://www.aclweb.org/anthology/W03-1304.pdf", } @Article{Hobbs:2004:IEB, author = {Jerry R. Hobbs}, title = {Information Extraction from Biomedical Text}, journal = {Journal of Biomedical Informatics}, year = {2004}, OPTkey = {}, OPTvolume = {}, OPTnumber = {}, OPTpages = {}, OPTmonth = {}, OPTnote = {}, OPTannote = {} } @Article{Huang:2004:DPE, author = "Minlie Huang and Xiaoyan Zhu and Yu Hao and Donald G. Payan and Kunbin Qu and Ming Li", title = "Discovering patterns to extract protein-protein interactions from full texts", journal = "Bioinformatics", volume = "20", number = "18", pages = "3604--3612", month = jul, year = "2004", keywords = "relations", } @Article{Humphreys:1998:UML, author = "B. L. Humphreys and D. A. Lindberg and H. M. Schoolman and G. O. Barnett", title = "The Unified Medical Language System: an informatics research collaboration", journal = "Journal of the American Medical Informatics Assoc.", volume = "5", number = "1", pages = "1--11", year = "1998", keywords = "ont-corp", } @InProceedings{Humphreys:2000:TAI, author = "K. Humphreys and G. Demetriou and R. Gaizauskas", booktitle = "Proceedings of the Pacific Symposium on Biocomputing (PSB-2000)", title = "Two Applications of Information Extraction to Biological Science Journal Articles: Enzyme Interactions and Protein Structures", pages = "505--516", month = jan, year = "2000", comments = "This article shows how an IE system for the newswire domain was adapted to be used in biology domain. The system was developed in Gate. The main information sources usd for terminlogy identification are: case-insensitive terminology lexicons, listing component terms, morphological-cues and hand-constructed grammar rules for each terminology class (Swiss-Prot list of official enzyme names)", keywords = "relations", } @InBook{Hunter:1993:AIM, author = "L. Hunter", editor = "L. Hunter", title = "Artificial Intelligence and Molecular Biology", chapter = "Molecular Biology for Computer Scientists", publisher = "AAAI Press", year = "1993", comments = "excellent introduction to molecular biology", keywords = "overview", pdf = "http://www.aaai.org//Library/Books/Hunter/01-Hunter.pdf", } @InProceedings{Kazama:2001:MET, author = "J. Kazama and Y. Miyao and J. Tsujii", booktitle = "Proceedings of the Sixth Natural Language Processing Pacific Rim Symposium (NLPRS2001)", title = "A Maximum Entropy Tagger with Unsupervised Hidden Markov Models", pages = "333--340", year = "2001", keywords = "POS", } @Article{Kim:2003:GCS, author = "J. D. Kim and T. Ohta and Y. Tatisi and J. Tsujii", title = "{GENIA} corpus - a semantically annotated corups for bio-textmining", journal = "Bioinformatics", volume = "19", number = "1", pages = "180--182", year = "2003", comments = "Construction of a corpus of 2000 medline abstracts to provide a gold standard for the evaluation of text mining systems. Abstracts in the domain of biological reactions concerning transcription factor in human blood cells (substances and sources).Annotation with syntact and semantic information.", keywords = "ont-corp", } @InProceedings{Kulick:2004:IAB, author = "S. Kulick and A. Bies and M. Liberman and M. Mandel and R. McDonald and M. Palmer and A. Schein and L. Ungar", booktitle = "NAACL/HLT Workshop on Linking Biological Literature, Ontologies and Databases: Tools for Users", title = "Integrated Annotation for Biomedical Information Extraction", pages = "61--68", year = "2004", keywords = "relations", } @InProceedings{Lee:2003:TPB, author = "Ki-Joong Lee and Young-Sook Hwang and Hae-Chang Rim", editor = "Sophia Ananiadou and Jun'ichi Tsujii", booktitle = "Proceedings of the ACL 2003 Workshop on Natural Language Processing in Biomedicine", title = "Two-Phase Biomedical {NE} Recognition based on {SVMs}", pages = "33--40", year = "2003", keywords = "NER", pdf = "http://www.aclweb.org/anthology/W03-1305.pdf", } @Article{Leroy:2003:SPB, author = "G. Leroy and H. Chen and J. D. Martinez", title = "A shallow parser based on closed-class words to capture relations in biomedical text", journal = "Journal of Biomedical Informatics", volume = "36", pages = "145--158", year = "2003", comments = "Syntactic approach: all relations are processed without limiting in advance what type of content is to be captured. Patterns based in conjunctions and prepositions. Targeting high precision (biologists distrust software based on incorrect biological information). Details about the noun phraser recognizer. Citations about the evaluations of UMLS. Used by SemGen. Precision and recall of several works in the domain.", keywords = "relations", } @InProceedings{Libbus:2004:UNL, author = "Bisharah Libbus and Halil Kilicoglu and Thomas C. Rindflesch and James G. Mork and Alan R. Aronson", booktitle = "NAACL/HLT Workshop on Linking Biological Literature, Ontologies and Databases: Tools for Users", title = "Using Natural Language Processing, LocusLink and the Gene Ontology to Compare {OMIM} to {MEDLINE}", pages = "69--76", year = "2004", comments = "Limitations of their system to extract the templates (41\% precision) and description of terminological resources used. Filter only sentences that contain molecular biology information.", keywords = "relations", } @Article{McDonald:2004:EGP, author = "D. M. McDonald and H. Chen and H. Su and B. B. Marshall", title = "Extracting gene pathway relations using a hybrid grammar: the Arizona Relation Parser", journal = "Bioinformatics", volume = "20", number = "18", pages = "3370--3378", month = jul, year = "2004", keywords = "relations", } @InProceedings{Morgan:2003:GNE, author = "Alex Morgan and Lynette Hirschman and Alexander Yeh and Marc Colosimo", editor = "Sophia Ananiadou and Jun'ichi Tsujii", booktitle = "Proceedings of the ACL 2003 Workshop on Natural Language Processing in Biomedicine", title = "Gene Name Extraction Using {FlyBase} Resources", pages = "1--8", year = "2003", keywords = "NER", pdf = "http://www.aclweb.org/anthology/W03-1301.pdf", } @Article{Muller:2004:TOB, author = "Hans-Michael M{\"u}ller and Eimear E. Kenny and Paul W. Sternberg", title = "Textpresso: An Ontology-Based Information Retrieval and Extraction System for Biological Literature", journal = "Plos Biology", volume = "2", number = "11", month = nov, year = "2004", keywords = "relations", } @InProceedings{Nenadic:2003:STF, author = "Goran Nenadi\'{c} and Simon Rice and Irena Spasi\'{c} and Sophia Ananiadou and Benjamin Stapley", editor = "Sophia Ananiadou and Jun'ichi Tsujii", booktitle = "Proceedings of the ACL 2003 Workshop on Natural Language Processing in Biomedicine", title = "Selecting Text Features for Gene Name Classification: from Documents to Terms", pages = "121--128", year = "2003", keywords = "NER", pdf = "http://www.aclweb.org/anthology/W03-1316.pdf", } @InProceedings{Nenadic:2003:TDM, author = "G. Nenadi\'c and I. Spasi and S. Ananiadou", booktitle = "Proceedings of the 2003 ACM symposium on Applied computing table of contents Melbourne, Florida", title = "Terminology-driven mining of biomedical literature", publisher = "ACM Press New York, NY, USA", pages = "83--87", year = "2003", keywords = "NER", } @InProceedings{Ohta:2002:GCA, author = "T. Ohta and Y. Tatisi and J. D. Kim", booktitle = "Proceedings of he Human Language Technology Conference (HLT 2002)", title = "{GENIA} Corpus: an Annotated Research Abstract Corpus in Molecular Biology Domain", pages = "73--77", year = "2002", comments = "This paper describes the Genia ontology in detail. It justifies why not using other ontologies (Mesh, GO, etc). The existent ontologies are very specific and some information necessary for information extraction task is out of the scope of these ontologies. Genia ontology is an ontology that covers boader range of concept at shallower level. Genia ontology is an ontology of substances and sources. Sources are biological locations where substances are found and their reactions take place. The classification of substances are based in their chemical structure and not in their function.", keywords = "ont-corp", } @Article{Pearson:2001:BNG, author = "H. Pearson", title = "Biology's name game", journal = "Nature", number = "411", pages = "631--632", month = jun, year = "2001", keywords = "overview", } @Article{Proux:1998:DGS, author = "D. Proux and F. Rechenmann and L. Julliard and V. Pillet and B. Jacq", title = "Detecting Gene Symbols and Names in Biological Texts: {A} First Step toward Pertinent Information Extraction", journal = "Genome Inform Ser Workshop Genome Inform.", volume = "9", pages = "72--80", year = "1998", abstract = "Gathering data on molecular interactions to be fed into a specialized database has motivated the development of a computer system to help extracting pertinent information from texts, relying on advanced linguistic tools, completed with object-oriented knowledge modeling capabilities. As a first step toward this challenging objective, a program for the identification of gene symbols and names inside sentences has been devised. The main difficulty is that these names and symbols do not appear to follow construction rules. The program is thus made up of a series of sieves of different natures, lexical, morphological and semantic, to distinguish among the words of a sentence those which can only be potential gene symbols or names. Its performance has been evaluated, in terms of coverage and precision ratios, on a corpus of texts concerning D. melanogaster for which the list of names of known genes is available for checking.", approach = "cascade of transducers", comments = "program to identify names made up of a series of sieves of different natures: lexical, morphological and semantic", corpus = "FlyBase, the molecular and genetic database devoted to Drosophila", groupe = "Xerox in France", keywords = "NER", } @InProceedings{Pustejovsky:2002:RRP, author = "J. Pustejovsky and J. Castano and J. Zhang", booktitle = "Proceedings of the Pacific Symposium on Biocomputing", title = "Robust Relational Parsing over Biomedical Literature: Extracting Inhibit Relations", pages = "362--373", year = "2002", comments = "Extract limited but biologically important inforamtion from free text with high reliability using a classical natural language processing approach. Uses UMLS.", keywords = "relations", } @InProceedings{Ray:2001:RSS, author = "S. Ray and M. Craven", booktitle = "Proc. of the Int. Joint Conf. on Artificial Intelligence", title = "Representing Sentence Structure in Hidden Markov Models for Information Extraction", year = "2001", keywords = "relations", } @InProceedings{Rindflesch:2000:EED, author = "T. C. Rindflesch and L. Tanabe and J. N. Weinstein and L. Hunter", booktitle = "Proc. Pacific Symposium on Biocomputing", title = "{EDGAR}: Extraction of drugs, genes, and relations from the biomedical literature", pages = "514--525", year = "2000", comments = "Uses UMLS to provide semantic information about the terms found in the Medline abstracts. This article says that UMLS vocabulary is largely for the clinical domain (it does not help in finding genes or cells names, but is good for finding drugs names). Uses lists and contextual information to identify gene and cell names. Try to extract sensitivity and resistance interactions (usually in a single sentence that contains the drug name, a gene name, and a cell anme). The coordination, anaphora and undespecified reference can complicate the task of interpreting sentences expressing sisitivity or resistance relations.", keywords = "relations", } @InProceedings{Rindflesch:2003:SRA, author = "T. C. Rindflesch and L. Bisharah and H. Dimitar and A. R. Aronson;and H. Kilicoglu", booktitle = "Proceedings of the AMIA Annual Symposium", title = "Semantic relations asserting the etiology of genetic diseases", year = "2003", comments = "Uses UMLS. Linguistic approach. Medline abstracts.", keywords = "relations", } @InProceedings{Rosario:2001:CSR, author = "Barbara Rosario and Marti Hearst", booktitle = "Proceedings of 2001 Conference on Empirical Methods in Natural Language Processing, Pittsburgh, PA (EMNLP 2001)", title = "Classifying the Semantic Relations in Noun Compounds via a Domain-Specific Lexical Hierarchy", year = "2001", keywords = "relations", } @Article{Rzhetsky:2000:KMA, author = "A. Rzhetsky and T. Koike and S. Kalachikov and SM. Gomez and M. Krauthammer and SH. Kaplan and P. Kra and JJ. Russo and C. Friedman", title = "A knowledge model for analysis and simulation of regulatory networks", journal = "Bioinformatics", volume = "16", number = "12", pages = "1120--1128", year = "2000", keywords = "ont-corp", } @Article{Sekimizu:1998:IIB, author = "T. Sekimizu and H. S. Park and J. Tsujii", title = "Identifying the Interaction between Genes and Gene Products Based on Frequently Seen Verbs in Medline Abstracts", journal = "Genome Informatics", pages = "62--71", year = "1998", comments = "Examples of sentences. Shallow parser. Noun phrase recognizer. Algorithm to identify the arguments of verbs.", keywords = "relations", } @Article{Shatkay:2003:MBL, author = "H. Shatkay and R. Feldman", title = "Mining the Biomedical Literature in the Genomic Era: An Overview", journal = "Journal of Computational Biology (JCB)", volume = "10", number = "6", pages = "821--856", month = dec, year = "2003", keywords = "overview", } @InProceedings{Shen:2003:EAH, author = "Dan Shen and Jie Zhang and Guodong Zhou and Jian Su and Chew-Lim Tan", editor = "Sophia Ananiadou and Jun'ichi Tsujii", booktitle = "Proceedings of the ACL 2003 Workshop on Natural Language Processing in Biomedicine", title = "Effective Adaptation of Hidden {Markov} Model-based Named Entity Recognizer for Biomedical Domain", pages = "49--56", year = "2003", keywords = "NER", pdf = "http://www.aclweb.org/anthology/W03-1307.pdf", } @InProceedings{Skounakis:2003:HHM, author = "M. Skounakis and M. Craven and S. Ray", title = "Hierarchical {Hidden} {Markov} {Models} for information extraction", booktitle = "Proceedings of the 18th International Joint Conference on Artificial Intelligence, Acapulco, Mexico. Morgan Kaufmann., 2003.", year = "2003", url = "citeseer.ist.psu.edu/skounakis03hierarchical.html" } @Article{Smith:2004:MPS, author = "L. Smith and T. Rindflesch and W. J. Wilbur", title = "MedPost: a part-of-speech tagger for bioMedical text", journal = "Bioinformatics", volume = "20", number = "14", year = "2004", keywords = "POS", } @InProceedings{Takeuchi:2003:BME, author = "Koichi Takeuchi and Nigel Collier", editor = "Sophia Ananiadou and Jun'ichi Tsujii", booktitle = "Proceedings of the ACL 2003 Workshop on Natural Language Processing in Biomedicine", title = "Bio-Medical Entity Extraction using Support Vector Machines", pages = "57--64", year = "2003", keywords = "NER", pdf = "http://www.aclweb.org/anthology/W03-1308.pdf", } @Article{Tanabe:1999:MIT, author = "L. Tanabe and U. Scherf and L. H. Smith and J. K. Lee and L. Hunter and J. N. Weinstein", title = "MedMiner: an Internet Text-Mining Tool for Biomedical Information, with Application to Gene Expression Profiling", journal = "BioTechniques", volume = "27", pages = "1210--1217", year = "1999", comments = "Used by SemGen", keywords = "relations", } @InProceedings{Tateisi:2004:APA, author = "Y. Tateisi and T. Ohta and J. Tsujii", booktitle = "JCNLP-04 workshop on Beyond Shallow Analyses", title = "Annotation of Predicate-argument Structure of Molecular Biology Text", year = "2004", comments = "Describe how to annotate a biomedical text.", keywords = "relations", pdf = "http://www-tsujii.is.s.u-tokyo.ac.jp/bsa/papers/tateisi.pdf", } @InProceedings{Tateisi:2004:PSA, author = "Y. Tateisi and J. Tsujii", booktitle = "Proceedings of 4th International Conference on Language Resource and Evaluation (LREC2004)", title = "Part-of-Speech Annotation of Biology Research Abstracts", pages = "1267--1270", year = "2004", keywords = "POS", } @InProceedings{Thomas:2000:AEP, author = {James Thomas and David Milward and Christos Ouzounis and Stephen Pulman and Mark Carroll}, title = {Automatic Extraction of Protein Interactions from Scientific Abstracts}, year = 2000, booktitle = {Proceedings of the Pacific Symposium on Biocomputing}, pages = {538-549} } @InProceedings{Torii:2003:IVI, author = "Manabu Torii and Sachin Kamboj and K. Vijay-Shanker", editor = "Sophia Ananiadou and Jun'ichi Tsujii", booktitle = "Proceedings of the ACL 2003 Workshop on Natural Language Processing in Biomedicine", title = "An Investigation of Various Information Sources for Classifying Biological names", pages = "113--120", year = "2003", keywords = "NER", pdf = "http://www.aclweb.org/anthology/W03-1315.pdf", } @InProceedings{Tsuruoka:2003:BPR, author = "Yoshimasa Tsuruoka and Jun'ichi Tsujii", editor = "Sophia Ananiadou and Jun'ichi Tsujii", booktitle = "Proceedings of the ACL 2003 Workshop on Natural Language Processing in Biomedicine", title = "Boosting Precision and Recall of Dictionary-Based Protein Name Recognition", pages = "41--48", year = "2003", keywords = "NER", pdf = "http://www.aclweb.org/anthology/W03-1306.pdf", } @Article{Uramoto:2004:TMS, author = {N. Uramoto and H. Matsuzawa and T. Nagano and A. Murakami and H. Takeuchi and and K. Takeda}, title = {A text-mining system for knowledge discovery from biomedical documents}, journal = {{IBM} Systems Journal}, year = 2004, volume = 43, number = 3, pages = {516--533} } @InProceedings{Yakushiji:2001:EEB, author = "A. Yakushiji and Y. Tateisi Y. Miyao and J. Tsujii", booktitle = "Proceedings of the sixth Pacific Symposium on Biocomputing (PSB 2001)", title = "Event extraction from biomedical papers using a full parser", pages = "408--419", year = "2001", comments = "Limitations of pattern-matching approach. Problems of full-parser approach coped with preprocessing components. Examples of sentences with problematic structures. Corpus: 97 sentences. Evaluation: 23\% uniquely; 24\% with ambiguity.", keywords = "relations", pdf = "http://www-tsujii.is.s.u-tokyo.ac.jp/~genia/paper/YakushijiPSB2001.pdf", } @InProceedings{Yamamoto:2003:PNT, author = "Kaoru Yamamoto and Taku Kudo and Akihiko Konagaya and Yuji Matsumoto", editor = "Sophia Ananiadou and Jun'ichi Tsujii", booktitle = "Proceedings of the ACL 2003 Workshop on Natural Language Processing in Biomedicine", title = "Protein Name Tagging for Biomedical Annotation in Text", pages = "65--72", year = "2003", keywords = "NER", pdf = "http://www.aclweb.org/anthology/W03-1309.pdf", } @InProceedings{Yu:1999:RGK, author = "H. Yu and C. Friedman and A. Rhzetsky abd P. Kra", booktitle = "Proc AMIA Symp.", title = "Representing genomic knowledge in the {UMLS} semantic network", pages = "181--185", year = "1999", keywords = "ont-corp", }