{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T22:52:19Z","timestamp":1761519139127,"version":"3.41.0"},"reference-count":63,"publisher":"Oxford University Press (OUP)","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Objective Semantic role labeling (SRL), which extracts a shallow semantic relation representation from different surface textual forms of free text sentences, is important for understanding natural language. Few studies in SRL have been conducted in the medical domain, primarily due to lack of annotated clinical SRL corpora, which are time-consuming and costly to build. The goal of this study is to investigate domain adaptation techniques for clinical SRL leveraging resources built from newswire and biomedical literature to improve performance and save annotation costs.<\/jats:p><jats:p>Materials and Methods Multisource Integrated Platform for Answering Clinical Questions (MiPACQ), a manually annotated SRL clinical corpus, was used as the target domain dataset. PropBank and NomBank from newswire and BioProp from biomedical literature were used as source domain datasets. Three state-of-the-art domain adaptation algorithms were employed: instance pruning, transfer self-training, and feature augmentation. The SRL performance using different domain adaptation algorithms was evaluated by using 10-fold cross-validation on the MiPACQ corpus. Learning curves for the different methods were generated to assess the effect of sample size.<\/jats:p><jats:p>Results and Conclusion When all three source domain corpora were used, the feature augmentation algorithm achieved statistically significant higher F-measure (83.18%), compared to the baseline with MiPACQ dataset alone (F-measure, 81.53%), indicating that domain adaptation algorithms may improve SRL performance on clinical text. To achieve a comparable performance to the baseline method that used 90% of MiPACQ training samples, the feature augmentation algorithm required &amp;lt;50% of training samples in MiPACQ, demonstrating that annotation costs of clinical SRL can be reduced significantly by leveraging existing SRL resources from other domains.<\/jats:p>","DOI":"10.1093\/jamia\/ocu048","type":"journal-article","created":{"date-parts":[[2015,6,11]],"date-time":"2015-06-11T11:04:18Z","timestamp":1434020658000},"page":"967-979","source":"Crossref","is-referenced-by-count":14,"title":["Domain adaptation for semantic role labeling of clinical text"],"prefix":"10.1093","volume":"22","author":[{"given":"Yaoyun","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Texas School of Biomedical Informatics at Houston, Houston, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Buzhou","family":"Tang","sequence":"additional","affiliation":[{"name":"University of Texas School of Biomedical Informatics at Houston, Houston, TX, USA"},{"name":"Department of Computer Science, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Jiang","sequence":"additional","affiliation":[{"name":"University of Texas School of Biomedical Informatics at Houston, Houston, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingqi","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Texas School of Biomedical Informatics at Houston, Houston, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hua","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Texas School of Biomedical Informatics at Houston, Houston, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2015,6,10]]},"reference":[{"key":"2020110613033224100_ocu048-B1","first-page":"233","article-title":"Shallow semantic parsing using support vector machines","volume-title":"Proceedings of Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics","author":"Pradhan","year":"21-26, 2004"},{"key":"2020110613033224100_ocu048-B2","volume-title":"Natural Language Understanding","author":"Allen","year":"1995","edition":"2nd ed."},{"key":"2020110613033224100_ocu048-B3","first-page":"July 7-12, 2003","article-title":"Using predicate-argument structures for information extraction","volume-title":"Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics","author":"Surdeanu"},{"key":"2020110613033224100_ocu048-B4","first-page":"284","article-title":"Automatic construction of predicate-argument structure patterns for biomedical information extraction","volume-title":"Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing","author":"Akane","year":"22-23, 2006"},{"key":"2020110613033224100_ocu048-B5","first-page":"60","article-title":"Biomedical information extraction with predicate-argument structure patterns","volume-title":"Proceedings of the First International Symposium on Semantic Mining in Biomedicine","author":"Yakushiji","year":"10-13, 2005"},{"key":"2020110613033224100_ocu048-B6","article-title":"Open information extraction from biomedical literature using predicate-argument structure patterns","volume-title":"Proceedings of the 5th International Symposium on Languages in Biology and Medicine","author":"Nguyen","year":"12-13, 2013"},{"issue":"1","key":"2020110613033224100_ocu048-B7","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1186\/1471-2105-5-155","article-title":"PASBio: predicate-argument structures for event extraction in molecular biology","volume":"5","author":"Wattarujeekrit","year":"2004","journal-title":"BMC Bioinformatics"},{"key":"2020110613033224100_ocu048-B8","first-page":"410","article-title":"Towards semantic role labeling & IE in the medical literature","author":"Kogan","year":"22-26, 2005","journal-title":"AMIA Symposium"},{"issue":"7","key":"2020110613033224100_ocu048-B9","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1093\/bioinformatics\/btk044","article-title":"LSAT: learning about alternative transcripts in MEDLINE","volume":"22","author":"Shah","year":"2006","journal-title":"Bioinformatics"},{"key":"2020110613033224100_ocu048-B10","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1186\/1471-2105-9-277","article-title":"Semantic role labeling for protein transport predicates","volume":"9","author":"Bethard","year":"2008","journal-title":"BMC Bioinformatics"},{"issue":"7","key":"2020110613033224100_ocu048-B11","doi-asserted-by":"crossref","first-page":"e6393","DOI":"10.1371\/journal.pone.0006393","article-title":"Large scale application of neural network based semantic role labeling for automated relation extraction from biomedical texts","volume":"4","author":"Barnickel","year":"2009","journal-title":"PloS One"},{"key":"2020110613033224100_ocu048-B12","first-page":"604","article-title":"Shallow semantic parsing of randomized controlled trial reports","author":"Paek","year":"11-15, 2006","journal-title":"AMIA Symposium"},{"issue":"5","key":"2020110613033224100_ocu048-B13","doi-asserted-by":"crossref","first-page":"922","DOI":"10.1136\/amiajnl-2012-001317","article-title":"Towards comprehensive syntactic and semantic annotations of the clinical narrative","volume":"20","author":"Albright","year":"2013","journal-title":"J Am Med Inform Assoc."},{"key":"2020110613033224100_ocu048-B14","first-page":"783","article-title":"Predicate argument structure frames for modeling information in operative notes","volume":"192","author":"Wang","year":"2013","journal-title":"Stud Health Technol Inform."},{"key":"2020110613033224100_ocu048-B15","first-page":"803","article-title":"Annotating noun argument structure for NomBank","volume-title":"Proceedings of the Language Resources and Evaluation Conference","author":"Meyers","year":"26-28, 2004"},{"key":"2020110613033224100_ocu048-B16","first-page":"24","article-title":"The NomBank Project: an interim peport","volume-title":"Proceedings of the HLT-NAACL 2004 Workshop: Frontiers in Corpus Annotation","author":"Meyers","year":"6, 2004"},{"key":"2020110613033224100_ocu048-B17","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1186\/1471-2105-8-325","article-title":"BIOSMILE: a semantic role labeling system for biomedical verbs using a maximum-entropy model with automatically generated template features","volume":"8","author":"Tsai","year":"2007","journal-title":"BMC Bioinformatics"},{"issue":"1","key":"2020110613033224100_ocu048-B18","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1162\/0891201053630264","article-title":"The proposition bank: an annotated corpus of semantic roles","volume":"31","author":"Palmer","year":"2005","journal-title":"Comput Linguist."},{"issue":"6","key":"2020110613033224100_ocu048-B19","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1016\/j.jbi.2003.11.003","article-title":"The interaction of domain knowledge and linguistic structure in natural language processing: interpreting hypernymic propositions in biomedical text","volume":"36","author":"Rindflesch","year":"2003","journal-title":"J Biomed Inform."},{"issue":"23","key":"2020110613033224100_ocu048-B20","doi-asserted-by":"crossref","first-page":"3158","DOI":"10.1093\/bioinformatics\/bts591","article-title":"SemMedDB: a PubMed-scale repository of biomedical semantic predications","volume":"28","author":"Kilicoglu","year":"2012","journal-title":"Bioinformatics"},{"volume-title":"Natural Language Information Processing","author":"Sager","key":"2020110613033224100_ocu048-B21"},{"issue":"1","key":"2020110613033224100_ocu048-B22","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1197\/jamia.M2401","article-title":"Automated acquisition of disease\u2013drug knowledge from biomedical and clinical documents: an initial study","volume":"15","author":"Chen","year":"2008","journal-title":"J Am Med Inform Assoc."},{"key":"2020110613033224100_ocu048-B23","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1007\/978-1-4614-3223-4_14","article-title":"Biomedical text mining: a survey of recent progress","volume-title":"Mining Text Data","author":"Simpson","year":"2012"},{"key":"2020110613033224100_ocu048-B24","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198242246.001.0001","volume-title":"A Theory of Language and Information: a Mathematical Approach","author":"Harris","year":"1991"},{"issue":"4","key":"2020110613033224100_ocu048-B25","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1016\/S1532-0464(03)00012-1","article-title":"Two biomedical sublanguages: a description based on the theories of Zellig Harris","volume":"35","author":"Friedman","year":"2002","journal-title":"J Biomed Inform."},{"issue":"9","key":"2020110613033224100_ocu048-B26","doi-asserted-by":"crossref","first-page":"e3158","DOI":"10.1371\/journal.pone.0003158","article-title":"Nominalization and alternations in biomedical language","volume":"3","author":"Cohen","year":"2008","journal-title":"PLoS One"},{"issue":"1","key":"2020110613033224100_ocu048-B27","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1197\/jamia.M3378","article-title":"MedEx: a medication information extraction system for clinical narratives","volume":"17","author":"Xu","year":"2010","journal-title":"J Am Med Inform Assoc."},{"author":"Schuler","key":"2020110613033224100_ocu048-B28"},{"author":"Ruppenhofer","key":"2020110613033224100_ocu048-B29","article-title":"FrameNet II: extended theory and practice"},{"volume-title":"English Verb Classes and Alternations: a Preliminary Investigation","year":"1993","author":"Levin","key":"2020110613033224100_ocu048-B30"},{"issue":"3","key":"2020110613033224100_ocu048-B31","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1162\/089120102760275983","article-title":"Automatic labeling of semantic roles","volume":"28","author":"Gildea","year":"2002","journal-title":"Comput Linguist."},{"key":"2020110613033224100_ocu048-B32","first-page":"12","article-title":"Using semantic roles to improve question answering","volume-title":"Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)","author":"Shen","year":"28-30, 2007"},{"issue":"3.4","key":"2020110613033224100_ocu048-B33","doi-asserted-by":"crossref","first-page":"3:1","DOI":"10.1147\/JRD.2012.2185409","article-title":"Deep parsing in Watson","volume":"56","author":"McCord","year":"2012","journal-title":"IBM J Res Dev."},{"key":"2020110613033224100_ocu048-B34","first-page":"152","article-title":"Introduction to the CoNLL-2005 shared task: semantic role labeling","volume-title":"Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005)","author":"Carreras","year":"29-30, 2005"},{"key":"2020110613033224100_ocu048-B35","first-page":"159","article-title":"The CoNLL-2008 shared task on joint parsing of syntactic and semantic dependencies","volume-title":"Proceedings of the Twelfth Conference on Computational Natural Language Learning","author":"Surdeanu","year":"16-17, 2008"},{"key":"2020110613033224100_ocu048-B36","first-page":"88","article-title":"Calibrating features for semantic role labeling","volume-title":"Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing","author":"Xue","year":"25-26, 2004"},{"key":"2020110613033224100_ocu048-B37","first-page":"1","article-title":"Semantic parsing for high-precision semantic role labelling","volume-title":"Proceedings of the Twelfth Conference on Computational Natural Language Learning","author":"Merlo","year":"16-17, 2008"},{"key":"2020110613033224100_ocu048-B38","first-page":"155","article-title":"Jointly identifying predicates, arguments and senses using Markov logic","volume-title":"Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics","author":"Meza-Ruiz","year":"31- 5, 2009"},{"issue":"10","key":"2020110613033224100_ocu048-B39","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE T Knowl Data Eng."},{"key":"2020110613033224100_ocu048-B40","first-page":"1431","article-title":"A study of actions in operative notes","author":"Wang","year":"3-7, 2012","journal-title":"AMIA Symposium"},{"article-title":"Multi-task transfer learning for weakly-supervised relation extraction","author":"Jiang","key":"2020110613033224100_ocu048-B41","doi-asserted-by":"crossref","DOI":"10.3115\/1690219.1690288"},{"key":"2020110613033224100_ocu048-B42","first-page":"647","article-title":"Crosslingual induction of semantic roles","volume-title":"Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics","author":"Titov","year":"8-14, 2012"},{"volume-title":"Literature Survey: Domain Adaptation Algorithms for Natural Language Processing","year":"2012","author":"Li","key":"2020110613033224100_ocu048-B43"},{"issue":"3","key":"2020110613033224100_ocu048-B44","doi-asserted-by":"crossref","first-page":"257","DOI":"10.5626\/JCSE.2011.5.3.257","article-title":"A survey of transfer and multitask learning in bioinformatics","volume":"5","author":"Xu","year":"2011","journal-title":"J Comput Sci Eng."},{"issue":"8","key":"2020110613033224100_ocu048-B45","doi-asserted-by":"crossref","first-page":"1098","DOI":"10.1093\/bioinformatics\/btq075","article-title":"Domain adaptation for semantic role labeling in the biomedical domain","volume":"26","author":"Dahlmeier","year":"2010","journal-title":"Bioinformatics"},{"issue":"5","key":"2020110613033224100_ocu048-B46","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1136\/amiajnl-2012-001453","article-title":"Improving performance of natural language processing part-of-speech tagging on clinical narratives through domain adaptation","volume":"20","author":"Ferraro","year":"2013","journal-title":"J Am Med Inform Assoc."},{"issue":"3","key":"2020110613033224100_ocu048-B47","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.artmed.2014.02.002","article-title":"Statistical parsing of varieties of clinical Finnish","volume":"61","author":"Laippala","year":"2014","journal-title":"Artif Intell Med."},{"issue":"6","key":"2020110613033224100_ocu048-B48","doi-asserted-by":"crossref","first-page":"1088","DOI":"10.1016\/j.jbi.2008.02.003","article-title":"Word sense disambiguation across two domains: biomedical literature and clinical notes","volume":"41","author":"Savova","year":"2008","journal-title":"J Biomed Inform."},{"issue":"4","key":"2020110613033224100_ocu048-B49","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1016\/j.jbi.2010.02.005","article-title":"UMLS content views appropriate for NLP processing of the biomedical literature vs","volume":"43","author":"Demner-Fushman","year":"2010","journal-title":"clinical text. J Biomed Inform."},{"key":"2020110613033224100_ocu048-B50","first-page":"183","article-title":"Dependency-based syntactic-semantic analysis with PropBank and NomBank","volume-title":"Proceedings of the Twelfth Conference on Computational Natural Language Learning","author":"Johansson","year":"16-17, 2008"},{"key":"2020110613033224100_ocu048-B51","doi-asserted-by":"crossref","first-page":"i180","DOI":"10.1093\/bioinformatics\/btg1023","article-title":"GENIA corpus\u2013semantically annotated corpus for bio-textmining","volume":"19","author":"Kim","year":"2003","journal-title":"Bioinformatics"},{"key":"2020110613033224100_ocu048-B52","first-page":"264","article-title":"Instance weighting for domain adaptation in NLP","volume-title":"Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics","author":"Jiang","year":"25-27, 2007"},{"key":"2020110613033224100_ocu048-B53","first-page":"101","article-title":"Self-training for biomedical parsing","volume-title":"The 46th Annual Meeting of the Association of Computational Linguistics","author":"McClosky","year":"16-18, 2008"},{"key":"2020110613033224100_ocu048-B54","first-page":"182","article-title":"Instance level transfer learning for cross lingual opinion analysis","volume-title":"Proceedings of the Second Workshop on Computational Approaches to Subjectivity and Sentiment Analysis","author":"Xu","year":"24, 2011"},{"key":"2020110613033224100_ocu048-B55","first-page":"193","article-title":"Boosting for transfer learning","volume-title":"Proceedings of the 24th International Conference on Machine Learning","author":"Dai","year":"20-24, 2007"},{"key":"2020110613033224100_ocu048-B56","first-page":"256","article-title":"Frustratingly easy domain adaptation","volume-title":"Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics","author":"Daume","year":"25-27, 2007"},{"issue":"1\u20133","key":"2020110613033224100_ocu048-B57","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1007\/s10994-005-0912-2","article-title":"Support vector learning for semantic argument classification","volume":"60","author":"Pradhan","year":"2005","journal-title":"J Mach Learn."},{"key":"2020110613033224100_ocu048-B58","first-page":"1871","article-title":"LIBLINEAR: a library for large linear classification","volume":"9","author":"Fan","year":"2008","journal-title":"J Mach Learn Res."},{"key":"2020110613033224100_ocu048-B59","first-page":"137","article-title":"Text categorization with support vector machines: learning with many relevant features","volume-title":"Proceedings of the 10th European Conference on Machine Learning","author":"Joachims","year":"21-23, 1998"},{"key":"2020110613033224100_ocu048-B60","article-title":"Wilcoxon signed-rank test","volume-title":"Wiley Encyclopedia of Clinical Trials","author":"Woolson","year":"2007"},{"issue":"2","key":"2020110613033224100_ocu048-B61","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1162\/coli.2008.34.2.257","article-title":"The importance of syntactic parsing and inference in semantic role labeling","volume":"34","author":"Punyakanok","year":"2008","journal-title":"Comput Linguist."},{"key":"2020110613033224100_ocu048-B62","first-page":"283","article-title":"Knowledge transfer via multiple model local structure mapping","volume-title":"Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Gao","year":"24-27, 2008"},{"key":"2020110613033224100_ocu048-B63","article-title":"On handling negative transfer and imbalanced distributions in multiple source transfer learning","volume-title":"SIAM Conference on Data Mining","author":"Ge","year":"2-4, 2013"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/22\/5\/967\/34146440\/ocu048.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/22\/5\/967\/34146440\/ocu048.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T14:43:55Z","timestamp":1748443435000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/22\/5\/967\/928549"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6,10]]},"references-count":63,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2015,6,10]]},"published-print":{"date-parts":[[2015,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocu048","relation":{},"ISSN":["1527-974X","1067-5027"],"issn-type":[{"type":"electronic","value":"1527-974X"},{"type":"print","value":"1067-5027"}],"subject":[],"published-other":{"date-parts":[[2015,9]]},"published":{"date-parts":[[2015,6,10]]}}}