@article{albright:13a,
	abstract = {Objective
To create annotated clinical narratives with layers of syntactic and semantic labels to facilitate advances in clinical natural language processing (NLP).
To develop NLP algorithms and open source components.

Methods
Manual annotation of a clinical narrative corpus of 127 606 tokens following the Treebank schema for syntactic information, PropBank schema for predicate-argument structures, and the Unified Medical Language System (UMLS) schema for semantic information. NLP components were developed.

Results
The final corpus consists of 13 091 sentences containing 1772 distinct predicate lemmas. Of the 766 newly created PropBank frames, 74 are verbs. There are 28 539 named entity (NE) annotations spread over 15 UMLS semantic groups, one UMLS semantic type, and the Person semantic category. The most frequent annotations belong to the UMLS semantic groups of Procedures (15.71%), Disorders (14.74%), Concepts and Ideas (15.10%), Anatomy (12.80%), Chemicals and Drugs (7.49%), and the UMLS semantic type of Sign or Symptom (12.46%). Inter-annotator agreement results: Treebank (0.926), PropBank (0.891--0.931), NE (0.697--0.750). The part-of-speech tagger, constituency parser, dependency parser, and semantic role labeler are built from the corpus and released open source. A significant limitation uncovered by this project is the need for the NLP community to develop a widely agreed-upon schema for the annotation of clinical concepts and their relations.

Conclusions
This project takes a foundational step towards bringing the field of clinical NLP up to par with NLP in the general domain. The corpus creation and NLP components provide a resource for research and application development that would have been previously impossible.},
	author = {Albright, Daniel and Lanfranchi, Arrick and Fredriksen, Anwen and Styler, William F. and Warner, Colin and Hwang, Jena D. and Choi, Jinho D. and Dligach, Dmitriy and Nielsen, Rodney D. and Martin, James and Ward, Wayne and Palmer, Martha and Savova, Guergana K.},
	date-added = {2017-08-31 03:01:32 +0000},
	date-modified = {2018-08-21 18:36:23 +0000},
	journal = {Journal of the American Medical Informatics Association},
	keywords = {selected,medical},
	number = {5},
	pages = {922--930},
	title = {{Towards comprehensive syntactic and semantic annotations of the clinical narrative}},
	url_paper = {http://jamia.oxfordjournals.org/content/jaminfo/20/5/922.full.pdf},
	url_slides = {https://www.slideshare.net/jchoi7s/towards-comprehensive-syntactic-and-semantic-annotations-of-the-clinical-narrative},
	volume = {20},
	year = {2013},
	Bdsk-Url-1 = {http://dx.doi.org/10.1136/amiajnl-2012-001317}}

{"_id":"dunqDzXojQyNhyaQh","bibbaseid":"albright-lanfranchi-fredriksen-styler-warner-hwang-choi-dligach-etal-towardscomprehensivesyntacticandsemanticannotationsoftheclinicalnarrative-2013","author_short":["Albright, D.","Lanfranchi, A.","Fredriksen, A.","Styler, W. F.","Warner, C.","Hwang, J. D.","Choi, J. D.","Dligach, D.","Nielsen, R. D.","Martin, J.","Ward, W.","Palmer, M.","Savova, G. K."],"bibdata":{"bibtype":"article","type":"article","abstract":"Objective To create annotated clinical narratives with layers of syntactic and semantic labels to facilitate advances in clinical natural language processing (NLP). To develop NLP algorithms and open source components. Methods Manual annotation of a clinical narrative corpus of 127 606 tokens following the Treebank schema for syntactic information, PropBank schema for predicate-argument structures, and the Unified Medical Language System (UMLS) schema for semantic information. NLP components were developed. Results The final corpus consists of 13 091 sentences containing 1772 distinct predicate lemmas. Of the 766 newly created PropBank frames, 74 are verbs. There are 28 539 named entity (NE) annotations spread over 15 UMLS semantic groups, one UMLS semantic type, and the Person semantic category. The most frequent annotations belong to the UMLS semantic groups of Procedures (15.71%), Disorders (14.74%), Concepts and Ideas (15.10%), Anatomy (12.80%), Chemicals and Drugs (7.49%), and the UMLS semantic type of Sign or Symptom (12.46%). Inter-annotator agreement results: Treebank (0.926), PropBank (0.891–0.931), NE (0.697–0.750). The part-of-speech tagger, constituency parser, dependency parser, and semantic role labeler are built from the corpus and released open source. A significant limitation uncovered by this project is the need for the NLP community to develop a widely agreed-upon schema for the annotation of clinical concepts and their relations. Conclusions This project takes a foundational step towards bringing the field of clinical NLP up to par with NLP in the general domain. The corpus creation and NLP components provide a resource for research and application development that would have been previously impossible.","author":[{"propositions":[],"lastnames":["Albright"],"firstnames":["Daniel"],"suffixes":[]},{"propositions":[],"lastnames":["Lanfranchi"],"firstnames":["Arrick"],"suffixes":[]},{"propositions":[],"lastnames":["Fredriksen"],"firstnames":["Anwen"],"suffixes":[]},{"propositions":[],"lastnames":["Styler"],"firstnames":["William","F."],"suffixes":[]},{"propositions":[],"lastnames":["Warner"],"firstnames":["Colin"],"suffixes":[]},{"propositions":[],"lastnames":["Hwang"],"firstnames":["Jena","D."],"suffixes":[]},{"propositions":[],"lastnames":["Choi"],"firstnames":["Jinho","D."],"suffixes":[]},{"propositions":[],"lastnames":["Dligach"],"firstnames":["Dmitriy"],"suffixes":[]},{"propositions":[],"lastnames":["Nielsen"],"firstnames":["Rodney","D."],"suffixes":[]},{"propositions":[],"lastnames":["Martin"],"firstnames":["James"],"suffixes":[]},{"propositions":[],"lastnames":["Ward"],"firstnames":["Wayne"],"suffixes":[]},{"propositions":[],"lastnames":["Palmer"],"firstnames":["Martha"],"suffixes":[]},{"propositions":[],"lastnames":["Savova"],"firstnames":["Guergana","K."],"suffixes":[]}],"date-added":"2017-08-31 03:01:32 +0000","date-modified":"2018-08-21 18:36:23 +0000","journal":"Journal of the American Medical Informatics Association","keywords":"selected,medical","number":"5","pages":"922–930","title":"Towards comprehensive syntactic and semantic annotations of the clinical narrative","url_paper":"http://jamia.oxfordjournals.org/content/jaminfo/20/5/922.full.pdf","url_slides":"https://www.slideshare.net/jchoi7s/towards-comprehensive-syntactic-and-semantic-annotations-of-the-clinical-narrative","volume":"20","year":"2013","bdsk-url-1":"http://dx.doi.org/10.1136/amiajnl-2012-001317","bibtex":"@article{albright:13a,\n\tabstract = {Objective\nTo create annotated clinical narratives with layers of syntactic and semantic labels to facilitate advances in clinical natural language processing (NLP).\nTo develop NLP algorithms and open source components.\n\nMethods\nManual annotation of a clinical narrative corpus of 127 606 tokens following the Treebank schema for syntactic information, PropBank schema for predicate-argument structures, and the Unified Medical Language System (UMLS) schema for semantic information. NLP components were developed.\n\nResults\nThe final corpus consists of 13 091 sentences containing 1772 distinct predicate lemmas. Of the 766 newly created PropBank frames, 74 are verbs. There are 28 539 named entity (NE) annotations spread over 15 UMLS semantic groups, one UMLS semantic type, and the Person semantic category. The most frequent annotations belong to the UMLS semantic groups of Procedures (15.71%), Disorders (14.74%), Concepts and Ideas (15.10%), Anatomy (12.80%), Chemicals and Drugs (7.49%), and the UMLS semantic type of Sign or Symptom (12.46%). Inter-annotator agreement results: Treebank (0.926), PropBank (0.891--0.931), NE (0.697--0.750). The part-of-speech tagger, constituency parser, dependency parser, and semantic role labeler are built from the corpus and released open source. A significant limitation uncovered by this project is the need for the NLP community to develop a widely agreed-upon schema for the annotation of clinical concepts and their relations.\n\nConclusions\nThis project takes a foundational step towards bringing the field of clinical NLP up to par with NLP in the general domain. The corpus creation and NLP components provide a resource for research and application development that would have been previously impossible.},\n\tauthor = {Albright, Daniel and Lanfranchi, Arrick and Fredriksen, Anwen and Styler, William F. and Warner, Colin and Hwang, Jena D. and Choi, Jinho D. and Dligach, Dmitriy and Nielsen, Rodney D. and Martin, James and Ward, Wayne and Palmer, Martha and Savova, Guergana K.},\n\tdate-added = {2017-08-31 03:01:32 +0000},\n\tdate-modified = {2018-08-21 18:36:23 +0000},\n\tjournal = {Journal of the American Medical Informatics Association},\n\tkeywords = {selected,medical},\n\tnumber = {5},\n\tpages = {922--930},\n\ttitle = {{Towards comprehensive syntactic and semantic annotations of the clinical narrative}},\n\turl_paper = {http://jamia.oxfordjournals.org/content/jaminfo/20/5/922.full.pdf},\n\turl_slides = {https://www.slideshare.net/jchoi7s/towards-comprehensive-syntactic-and-semantic-annotations-of-the-clinical-narrative},\n\tvolume = {20},\n\tyear = {2013},\n\tBdsk-Url-1 = {http://dx.doi.org/10.1136/amiajnl-2012-001317}}\n\n","author_short":["Albright, D.","Lanfranchi, A.","Fredriksen, A.","Styler, W. F.","Warner, C.","Hwang, J. D.","Choi, J. D.","Dligach, D.","Nielsen, R. D.","Martin, J.","Ward, W.","Palmer, M.","Savova, G. K."],"key":"albright:13a","id":"albright:13a","bibbaseid":"albright-lanfranchi-fredriksen-styler-warner-hwang-choi-dligach-etal-towardscomprehensivesyntacticandsemanticannotationsoftheclinicalnarrative-2013","role":"author","urls":{" paper":"http://jamia.oxfordjournals.org/content/jaminfo/20/5/922.full.pdf"," slides":"https://www.slideshare.net/jchoi7s/towards-comprehensive-syntactic-and-semantic-annotations-of-the-clinical-narrative"},"keyword":["selected","medical"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"http://www.mathcs.emory.edu/~choi/cv/jinho_choi-20210601.bib","dataSources":["KCe4LtCfLaE5R9apZ","WRbWtphN7JFZaJSwS"],"keywords":["selected","medical"],"search_terms":["towards","comprehensive","syntactic","semantic","annotations","clinical","narrative","albright","lanfranchi","fredriksen","styler","warner","hwang","choi","dligach","nielsen","martin","ward","palmer","savova"],"title":"Towards comprehensive syntactic and semantic annotations of the clinical narrative","year":2013}