w Semantic tagging: a robust sequential tagger that consists of (1) an initial tagging step that combines lookup and regular expression tagging methods, (2) a disambiguation step that transforms the initial ambiguous tags into the final tags based on a set of pre-defined context-based rules.
\nw Parsing: The parsing component of MedEx uses a context-free grammar to parse textual sentences into structured forms, via a Chart Parser
", "tags": [], "relations": {}, "dateAdded": "2012-10-23T16:42:44Z", "dateModified": "2012-10-23T16:42:44Z" } }, { "key": "M9C4AF2W", "version": 1, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/M9C4AF2W", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/M9C4AF2W", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Xu et al.", "parsedDate": "2010-01", "numChildren": 1 }, "data": { "key": "M9C4AF2W", "version": 1, "itemType": "journalArticle", "title": "MedEx: a medication information extraction system for clinical narratives", "creators": [ { "creatorType": "author", "firstName": "Hua", "lastName": "Xu" }, { "creatorType": "author", "firstName": "Shane P.", "lastName": "Stenner" }, { "creatorType": "author", "firstName": "Son", "lastName": "Doan" }, { "creatorType": "author", "firstName": "Kevin B.", "lastName": "Johnson" }, { "creatorType": "author", "firstName": "Lemuel R.", "lastName": "Waitman" }, { "creatorType": "author", "firstName": "Joshua C.", "lastName": "Denny" } ], "abstractNote": "Medication information is one of the most important types of clinical data in electronic medical records. It is critical for healthcare safety and quality, as well as for clinical research that uses electronic medical record data. However, medication data are often recorded in clinical notes as free-text. As such, they are not accessible to other computerized applications that rely on coded data. We describe a new natural language processing system (MedEx), which extracts medication information from clinical notes. MedEx was initially developed using discharge summaries. An evaluation using a data set of 50 discharge summaries showed it performed well on identifying not only drug names (F-measure 93.2%), but also signature information, such as strength, route, and frequency, with F-measures of 94.5%, 93.9%, and 96.0% respectively. We then applied MedEx unchanged to outpatient clinic visit notes. It performed similarly with F-measures over 90% on a set of 25 clinic visit notes.", "publicationTitle": "Journal of the American Medical Informatics Association", "publisher": "", "place": "", "date": "January 2010", "volume": "17", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "19–24", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1197/jamia.M3378", "citationKey": "", "url": "http://dx.doi.org/10.1197/jamia.M3378", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "1527-974X", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Clinical" }, { "tag": "clinic-visit-notes" }, { "tag": "discharge-summaries" }, { "tag": "information-extraction" }, { "tag": "medex" } ], "collections": [], "relations": {}, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-23T16:42:44Z" } }, { "key": "GGE8SR2Q", "version": 1, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/GGE8SR2Q", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/GGE8SR2Q", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Doan et al.", "parsedDate": "2010-09", "numChildren": 1 }, "data": { "key": "GGE8SR2Q", "version": 1, "itemType": "journalArticle", "title": "Integrating existing natural language processing tools for medication extraction from discharge summaries", "creators": [ { "creatorType": "author", "firstName": "Son", "lastName": "Doan" }, { "creatorType": "author", "firstName": "Lisa", "lastName": "Bastarache" }, { "creatorType": "author", "firstName": "Sergio", "lastName": "Klimkowski" }, { "creatorType": "author", "firstName": "Joshua C.", "lastName": "Denny" }, { "creatorType": "author", "firstName": "Hua", "lastName": "Xu" } ], "abstractNote": "Objective To develop an automated system to extract medications and related information from discharge summaries as part of the 2009 i2b2 natural language processing (NLP) challenge. This task required accurate recognition of medication name, dosage, mode, frequency, duration, and reason for drug administration.Design We developed an integrated system using several existing NLP components developed at Vanderbilt University Medical Center, which included MedEx (to extract medication information), SecTag (a section identification system for clinical notes), a sentence splitter, and a spell checker for drug names. Our goal was to achieve good performance with minimal to no specific training for this document corpus; thus, evaluating the portability of those NLP tools beyond their home institution. The integrated system was developed using 17 notes that were annotated by the organizers and evaluated using 251 notes that were annotated by participating teams.Measurements The i2b2 challenge used standard measures, including precision, recall, and F-measure, to evaluate the performance of participating systems. There were two ways to determine whether an extracted textual finding is correct or not: exact matching or inexact matching. The overall performance for all six types of medication-related findings across 251 annotated notes was considered as the primary metric in the challenge.Results Our system achieved an overall F-measure of 0.821 for exact matching (0.839 precision; 0.803 recall) and 0.822 for inexact matching (0.866 precision; 0.782 recall). The system ranked second out of 20 participating teams on overall performance at extracting medications and related information.Conclusions The results show that the existing MedEx system, together with other NLP components, can extract medication information in clinical text from institutions other than the site of algorithm development with reasonable performance.", "publicationTitle": "Journal of the American Medical Informatics Association", "publisher": "", "place": "", "date": "September 2010", "volume": "17", "issue": "5", "section": "", "partNumber": "", "partTitle": "", "pages": "528–531", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1136/jamia.2010.003855", "citationKey": "", "url": "http://dx.doi.org/10.1136/jamia.2010.003855", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "1527-974X", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "NLP" }, { "tag": "drugs" }, { "tag": "information-extraction" }, { "tag": "medex" }, { "tag": "medication" } ], "collections": [], "relations": {}, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-23T16:40:32Z" } }, { "key": "CM9KI9NH", "version": 1, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/CM9KI9NH", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/CM9KI9NH", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/73103/items/GGE8SR2Q", "type": "application/json" } }, "meta": { "createdByUser": { "id": 1172564, "username": "yanj", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/yanj", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "CM9KI9NH", "version": 1, "parentItem": "GGE8SR2Q", "itemType": "note", "note": "Integrated SecTag, Extended MedEx, Spell checker
", "tags": [], "relations": {}, "dateAdded": "2012-10-23T16:40:31Z", "dateModified": "2012-10-23T16:40:31Z" } }, { "key": "6XFDAGXK", "version": 1, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/6XFDAGXK", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/6XFDAGXK", "type": "text/html" } }, "meta": { "createdByUser": { "id": 1172564, "username": "yanj", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/yanj", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "6XFDAGXK", "version": 1, "itemType": "note", "note": "Integrated SecTag, Extended MedEx, Spell checker
", "tags": [], "collections": [], "relations": {}, "dateAdded": "2012-10-23T16:39:30Z", "dateModified": "2012-10-23T16:39:30Z" } }, { "key": "64VAVQEV", "version": 1, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/64VAVQEV", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/64VAVQEV", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/73103/items/X56IUCXR", "type": "application/json" } }, "meta": { "createdByUser": { "id": 1172564, "username": "yanj", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/yanj", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "64VAVQEV", "version": 1, "parentItem": "X56IUCXR", "itemType": "note", "note": "w used a rule-based approach: NER, semantic tags.
\nw Detection of new medication names through the exploitation of semantic patterns
", "tags": [], "relations": {}, "dateAdded": "2012-10-23T16:36:29Z", "dateModified": "2012-10-23T16:36:29Z" } }, { "key": "X56IUCXR", "version": 1, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/X56IUCXR", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/X56IUCXR", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Hamon and Grabar", "parsedDate": "2010-09", "numChildren": 2 }, "data": { "key": "X56IUCXR", "version": 1, "itemType": "journalArticle", "title": "Linguistic approach for identification of medication names and related information in clinical narratives", "creators": [ { "creatorType": "author", "firstName": "Thierry", "lastName": "Hamon" }, { "creatorType": "author", "firstName": "Natalia", "lastName": "Grabar" } ], "abstractNote": "Background Pharmacotherapy is an integral part of any medical care process and plays an important role in the medical history of most patients. Information on medication is crucial for several tasks such as pharmacovigilance, medical decision or biomedical research.Objectives Within a narrative text, medication-related information can be buried within other non-relevant data. Specific methods, such as those provided by text mining, must be designed for accessing them, and this is the objective of this study.Methods The authors designed a system for analyzing narrative clinical documents to extract from them medication occurrences and medication-related information. The system also attempts to deduce medications not covered by the dictionaries used.Results Results provided by the system were evaluated within the framework of the I2B2 NLP challenge held in 2009. The system achieved an F-measure of 0.78 and ranked 7th out of 20 participating teams (the highest F-measure was 0.86). The system provided good results for the annotation and extraction of medication names, their frequency, dosage and mode of administration (F-measure over 0.81), while information on duration and reasons is poorly annotated and extracted (F-measure 0.36 and 0.29, respectively). The performance of the system was stable between the training and test sets.", "publicationTitle": "Journal of the American Medical Informatics Association", "publisher": "", "place": "", "date": "September 2010", "volume": "17", "issue": "5", "section": "", "partNumber": "", "partTitle": "", "pages": "549–554", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1136/jamia.2010.004036", "citationKey": "", "url": "http://dx.doi.org/10.1136/jamia.2010.004036", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "1527-974X", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "NLP" }, { "tag": "drugs" }, { "tag": "information-extraction" }, { "tag": "medication" } ], "collections": [], "relations": {}, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-23T16:36:29Z" } }, { "key": "EDG4PEZ6", "version": 11, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/EDG4PEZ6", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/EDG4PEZ6", "type": "text/html" } }, "meta": { "createdByUser": { "id": 981062, "username": "dhillert", "name": "Dieter Hillert", "links": { "alternate": { "href": "https://www.zotero.org/dhillert", "type": "text/html" } } }, "creatorSummary": "Hillert, Dieter", "parsedDate": "1998", "numChildren": 0 }, "data": { "key": "EDG4PEZ6", "version": 11, "itemType": "book", "title": "Sentence Processing: A Crosslinguistic Perspective.", "creators": [ { "creatorType": "editor", "firstName": "", "lastName": "Hillert, Dieter" } ], "abstractNote": "", "series": "Syntax and Semantics", "seriesNumber": "", "volume": "31", "numberOfVolumes": "", "edition": "", "date": "1998", "publisher": "Academic Press", "place": "San Diego, CA", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "numPages": "437", "ISBN": "", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "parsing" }, { "tag": "psycholinguistics" }, { "tag": "semantic" }, { "tag": "sentence processing" }, { "tag": "syntax" } ], "collections": [], "relations": {}, "dateAdded": "2012-10-18T21:01:33Z", "dateModified": "2012-10-18T21:11:49Z" } }, { "key": "GNGGCTRV", "version": 18, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/GNGGCTRV", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/GNGGCTRV", "type": "text/html" } }, "meta": { "createdByUser": { "id": 981062, "username": "dhillert", "name": "Dieter Hillert", "links": { "alternate": { "href": "https://www.zotero.org/dhillert", "type": "text/html" } } }, "creatorSummary": "Hillert and Buracas", "parsedDate": "2009", "numChildren": 0 }, "data": { "key": "GNGGCTRV", "version": 18, "itemType": "journalArticle", "title": "The Neural Substrates of Spoken Idiom Comprehension", "creators": [ { "creatorType": "author", "firstName": "Dieter G.", "lastName": "Hillert" }, { "creatorType": "author", "firstName": "Giedrius T.", "lastName": "Buracas" } ], "abstractNote": "To examine the neural correlates of spoken idiom comprehension, we conducted an event-related functional MRI study with a ‘rapid sentence decision’ task. The spoken sentences were equally familiar but varied in degrees\nof ‘idiom figurativeness’. Our results show that ‘figurativeness’ co-varied with neural activity in the left ventral dorsolateral prefrontal cortex, which involved two different clusters: one cluster engaged Broca’s area (Brodmann area, BA: 44 & 45) and adjacent regions (BA 11 & 47); the other cluster involved the superior and medial frontal gryrus (BA 8 & 9). Moreover, the comparison between unambiguous, explicit idiomatic and literal sentences revealed leftsided cluster activity in Broca’s area and BA 46 & 47. The contrast between ambiguous idiomatic and literal sentences engaged the superior and medial of the frontal midline (BA 9 & 10), but with left-sided prevalence. Finally, we report a very consistent deactivation in the superior parietal cortex by explicit\nidiomatic sentences as compared to literal sentences. Our findings are discussed in context of a neurological model of spoken language processing.", "publicationTitle": "Language and Cognitive Processes", "publisher": "", "place": "", "date": "2009", "volume": "24", "issue": "9", "section": "", "partNumber": "", "partTitle": "", "pages": "1370-1391", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "LCP", "DOI": "10.1080/01690960903057006", "citationKey": "", "url": "http://dx.doi.org/10.1080/01690960903057006", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "English", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Broca's area" }, { "tag": "idioms" }, { "tag": "neuroimaging" }, { "tag": "parsing" } ], "collections": [], "relations": {}, "dateAdded": "2012-10-18T16:30:33Z", "dateModified": "2012-10-18T21:09:22Z" } }, { "key": "FSTPZ847", "version": 4, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/FSTPZ847", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/FSTPZ847", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Christensen et al.", "parsedDate": "2009", "numChildren": 2 }, "data": { "key": "FSTPZ847", "version": 4, "itemType": "conferencePaper", "title": "ONYX: A system for the semantic analysis of clinical text", "creators": [ { "creatorType": "author", "firstName": "L.M.", "lastName": "Christensen" }, { "creatorType": "author", "firstName": "H.", "lastName": "Harkema" }, { "creatorType": "author", "firstName": "P.J.", "lastName": "Haug" }, { "creatorType": "author", "firstName": "J.Y.", "lastName": "Irwin" }, { "creatorType": "author", "firstName": "W.W.", "lastName": "Chapman" } ], "abstractNote": "", "proceedingsTitle": "Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing", "conferenceName": "", "publisher": "", "place": "", "date": "2009", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "19–27", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "ONYX", "language": "", "libraryCatalog": "Google Scholar", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "NLP" }, { "tag": "Semantics" }, { "tag": "dental" }, { "tag": "internal_papers" }, { "tag": "onyx" }, { "tag": "parsing" }, { "tag": "syntax" } ], "collections": [], "relations": { "owl:sameAs": [ "http://zotero.org/groups/69365/items/Z7MCN5EZ", "http://zotero.org/users/921078/items/FIX6GNEH" ], "dc:replaces": "http://zotero.org/groups/73103/items/Q2G2ZD3R" }, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-18T21:09:22Z" } }, { "key": "G9H5MRH9", "version": 4, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/G9H5MRH9", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/G9H5MRH9", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Poon and Domingos", "parsedDate": "2009-08", "numChildren": 0 }, "data": { "key": "G9H5MRH9", "version": 4, "itemType": "conferencePaper", "title": "Unsupervised Semantic Parsing", "creators": [ { "creatorType": "author", "firstName": "Hoifung", "lastName": "Poon" }, { "creatorType": "author", "firstName": "Pedro", "lastName": "Domingos" } ], "abstractNote": "", "proceedingsTitle": "Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing", "conferenceName": "", "publisher": "Association for Computational Linguistics", "place": "Singapore", "date": "August 2009", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1–10", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://www.aclweb.org/anthology-new/D/D09/D09-1001.bib", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Semantics" }, { "tag": "biomedical" }, { "tag": "dependency-trees" }, { "tag": "parsing" }, { "tag": "unsupervised" } ], "collections": [], "relations": {}, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-18T21:09:22Z" } }, { "key": "T5I5M9HN", "version": 3, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/T5I5M9HN", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/T5I5M9HN", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Schuler et al.", "parsedDate": "2010-03", "numChildren": 0 }, "data": { "key": "T5I5M9HN", "version": 3, "itemType": "journalArticle", "title": "Broad-Coverage Parsing Using Human-Like Memory Constraints", "creators": [ { "creatorType": "author", "firstName": "William", "lastName": "Schuler" }, { "creatorType": "author", "firstName": "Samir", "lastName": "AbdelRahman" }, { "creatorType": "author", "firstName": "Tim", "lastName": "Miller" }, { "creatorType": "author", "firstName": "Lane", "lastName": "Schwartz" } ], "abstractNote": "doi: 10.1162/coli.2010.36.1.36100 Human syntactic processing shows many signs of taking place within a general-purpose short-term memory. But this kind of memory is known to have a severely constrained storage capacity—possibly constrained to as few as three or four distinct elements. This article describes a model of syntactic processing that operates successfully within these severe constraints, by recognizing constituents in a right-corner transformed representation (a variant of left-corner parsing) and mapping this representation to random variables in a Hierarchic Hidden Markov Model, a factored time-series model which probabilistically models the contents of a bounded memory store over time. Evaluations of the coverage of this model on a large syntactically annotated corpus of English sentences, and the accuracy of a a bounded-memory parsing strategy based on this model, suggest this model may be cognitively plausible.", "publicationTitle": "Computational Linguistics", "publisher": "", "place": "", "date": "March 2010", "volume": "36", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "1–30", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1162/coli.2010.36.1.36100", "citationKey": "", "url": "http://dx.doi.org/10.1162/coli.2010.36.1.36100", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "hierarchic-hidden-markov-model" }, { "tag": "parsing" }, { "tag": "psycholinguistics" } ], "collections": [], "relations": {}, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-18T21:09:22Z" } }, { "key": "S4JZH82P", "version": 3, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/S4JZH82P", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/S4JZH82P", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Masseroli et al.", "parsedDate": "2006-06", "numChildren": 0 }, "data": { "key": "S4JZH82P", "version": 3, "itemType": "journalArticle", "title": "Argument-predicate distance as a filter for enhancing precision in extracting predications on the genetic etiology of disease.", "creators": [ { "creatorType": "author", "firstName": "M.", "lastName": "Masseroli" }, { "creatorType": "author", "firstName": "H.", "lastName": "Kilicoglu" }, { "creatorType": "author", "firstName": "F. M.", "lastName": "Lang" }, { "creatorType": "author", "firstName": "T. C.", "lastName": "Rindflesch" } ], "abstractNote": "BACKGROUND: Genomic functional information is valuable for biomedical research. However, such information frequently needs to be extracted from the scientific literature and structured in order to be exploited by automatic systems. Natural language processing is increasingly used for this purpose although it inherently involves errors. A postprocessing strategy that selects relations most likely to be correct is proposed and evaluated on the output of SemGen, a system that extracts semantic predications on the etiology of genetic diseases. Based on the number of intervening phrases between an argument and its predicate, we defined a heuristic strategy to filter the extracted semantic relations according to their likelihood of being correct. We also applied this strategy to relations identified with co-occurrence processing. Finally, we exploited postprocessed SemGen predications to investigate the genetic basis of Parkinson's disease. RESULTS: The filtering procedure for increased precision is based on the intuition that arguments which occur close to their predicate are easier to identify than those at a distance. For example, if gene-gene relations are filtered for arguments at a distance of 1 phrase from the predicate, precision increases from 41.95% (baseline) to 70.75%. Since this proximity filtering is based on syntactic structure, applying it to the results of co-occurrence processing is useful, but not as effective as when applied to the output of natural language processing.In an effort to exploit SemGen predications on the etiology of disease after increasing precision with postprocessing, a gene list was derived from extracted information enhanced with postprocessing filtering and was automatically annotated with GFINDer, a Web application that dynamically retrieves functional and phenotypic information from structured biomolecular resources. Two of the genes in this list are likely relevant to Parkinson's disease but are not associated with this disease in several important databases on genetic disorders. CONCLUSION: Information based on the proximity postprocessing method we suggest is of sufficient quality to be profitably used for subsequent applications aimed at uncovering new biomedical knowledge. Although proximity filtering is only marginally effective for enhancing the precision of relations extracted with co-occurrence processing, it is likely to benefit methods based, even partially, on syntactic structure, regardless of the relation.", "publicationTitle": "BMC bioinformatics", "publisher": "", "place": "", "date": "June 2006", "volume": "7", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "291+", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1186/1471-2105-7-291", "citationKey": "", "url": "http://dx.doi.org/10.1186/1471-2105-7-291", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "1471-2105", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "biomedical" }, { "tag": "co-occurrence" }, { "tag": "parsing" }, { "tag": "relation-extraction" }, { "tag": "syntax" } ], "collections": [], "relations": {}, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-18T21:09:22Z" } }, { "key": "QJ4KF6TW", "version": 3, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/QJ4KF6TW", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/QJ4KF6TW", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Bashyam and Taira", "parsedDate": "2009-06", "numChildren": 0 }, "data": { "key": "QJ4KF6TW", "version": 3, "itemType": "conferencePaper", "title": "Incorporating Syntactic Dependency Information towards Improved Coding of Lengthy Medical Concepts in Clinical Reports", "creators": [ { "creatorType": "author", "firstName": "Vijayaraghavan", "lastName": "Bashyam" }, { "creatorType": "author", "firstName": "Ricky K.", "lastName": "Taira" } ], "abstractNote": "", "proceedingsTitle": "Proceedings of the BioNLP 2009 Workshop", "conferenceName": "", "publisher": "Association for Computational Linguistics", "place": "Boulder, Colorado", "date": "June 2009", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "125–132", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://www.aclweb.org/anthology-new/W/W09/W09-1316.bib", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "clinical-text" }, { "tag": "dependency-parsing" }, { "tag": "dependency-relations" }, { "tag": "parsing" }, { "tag": "syntax" } ], "collections": [], "relations": {}, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-18T21:09:22Z" } }, { "key": "ACRDHSMC", "version": 2, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/ACRDHSMC", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/ACRDHSMC", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Yang et al.", "parsedDate": "2009-10", "numChildren": 0 }, "data": { "key": "ACRDHSMC", "version": 2, "itemType": "journalArticle", "title": "Assigning roles to protein mentions: The case of transcription factors", "creators": [ { "creatorType": "author", "firstName": "Hui", "lastName": "Yang" }, { "creatorType": "author", "firstName": "John", "lastName": "Keane" }, { "creatorType": "author", "firstName": "Casey M.", "lastName": "Bergman" }, { "creatorType": "author", "firstName": "Goran", "lastName": "Nenadic" } ], "abstractNote": "Transcription factors (TFs) play a crucial role in gene regulation, and providing structured and curated information about them is important for genome biology. Manual curation of TF related data is time-consuming and always lags behind the actual knowledge available in the biomedical literature. Here we present a machine-learning text mining approach for identification and tagging of protein mentions that play a TF role in a given context to support the curation process. More precisely, the method explicitly identifies those protein mentions in text that refer to their potential TF functions. The prediction features are engineered from the results of shallow parsing and domain-specific processing (recognition of relevant appearing in phrases) and a phrase-based Conditional Random Fields (CRF) model is used to capture the content and context information of candidate entities. The proposed approach for the identification of TF mentions has been tested on a set of evidence sentences from the TRANSFAC and FlyTF databases. It achieved an F-measure of around 51.5% with a precision of 62.5% using 5-fold cross-validation evaluation. The experimental results suggest that the phrase-based CRF model benefits from the flexibility to use correlated domain-specific features that describe the dependencies between TFs and other entities. To the best of our knowledge, this work is one of the first attempts to apply text-mining techniques to the task of assigning semantic roles to protein mentions.", "publicationTitle": "Journal of Biomedical Informatics", "publisher": "", "place": "", "date": "October 2009", "volume": "42", "issue": "5", "section": "", "partNumber": "", "partTitle": "", "pages": "887–894", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1016/j.jbi.2009.04.001", "citationKey": "", "url": "http://dx.doi.org/10.1016/j.jbi.2009.04.001", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "15320464", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "biomedical" }, { "tag": "information-extraction" }, { "tag": "keywords" }, { "tag": "machine-learning" }, { "tag": "named-entities" }, { "tag": "parsing" } ], "collections": [], "relations": {}, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-18T21:09:22Z" } }, { "key": "WKFFCE48", "version": 2, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/WKFFCE48", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/WKFFCE48", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Yakushiji et al.", "parsedDate": "2001", "numChildren": 0 }, "data": { "key": "WKFFCE48", "version": 2, "itemType": "journalArticle", "title": "Event extraction from biomedical papers using a full parser.", "creators": [ { "creatorType": "author", "firstName": "A.", "lastName": "Yakushiji" }, { "creatorType": "author", "firstName": "Y.", "lastName": "Tateisi" }, { "creatorType": "author", "firstName": "Y.", "lastName": "Miyao" }, { "creatorType": "author", "firstName": "J.", "lastName": "Tsujii" } ], "abstractNote": "We have designed and implemented an information extraction system using a full parser to investigate the plausibility of full analysis of text using general-purpose parser and grammar applied to biomedical domain. We partially solved the problems of full parsing of inefficiency, ambiguity, and low coverage by introducing the preprocessors, and proposed the use of modules that handles partial results of parsing for further improvement. Our approach makes it possible to modularize the system, so that the IE system as a whole becomes easy to be tuned to specific domains, and easy to be maintained and improved by incorporating various techniques of disambiguation, speed up, etc. In preliminary experiment, from 133 argument structures that should be extracted from 97 sentences, we obtained 23% uniquely and 24% with ambiguity. And 20% are extractable from not complete but partial results of full parsing.", "publicationTitle": "Pac Symp Biocomput", "publisher": "", "place": "", "date": "2001", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "408–419", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://view.ncbi.nlm.nih.gov/pubmed/11262959", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "biomedical" }, { "tag": "information-extraction" }, { "tag": "parsing" } ], "collections": [], "relations": {}, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-18T21:09:22Z" } }, { "key": "TFFM2RCC", "version": 2, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/TFFM2RCC", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/TFFM2RCC", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Smith and Smith", "parsedDate": "2007-06", "numChildren": 0 }, "data": { "key": "TFFM2RCC", "version": 2, "itemType": "conferencePaper", "title": "Probabilistic Models of Nonprojective Dependency Trees", "creators": [ { "creatorType": "author", "firstName": "David A.", "lastName": "Smith" }, { "creatorType": "author", "firstName": "Noah A.", "lastName": "Smith" } ], "abstractNote": "", "proceedingsTitle": "Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)", "conferenceName": "", "publisher": "Association for Computational Linguistics", "place": "Prague, Czech Republic", "date": "June 2007", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "132–140", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://www.aclweb.org/anthology-new/D/D07/D07-1014.bib", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "dependency-parsing" }, { "tag": "parsing" }, { "tag": "statistical" } ], "collections": [], "relations": {}, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-18T21:09:22Z" } }, { "key": "H49KFDJW", "version": 2, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/H49KFDJW", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/H49KFDJW", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Sasaki et al.", "parsedDate": "2009-04", "numChildren": 0 }, "data": { "key": "H49KFDJW", "version": 2, "itemType": "conferencePaper", "title": "Three BioNLP Tools Powered by a Biological Lexicon", "creators": [ { "creatorType": "author", "firstName": "Yutaka", "lastName": "Sasaki" }, { "creatorType": "author", "firstName": "Paul", "lastName": "Thompson" }, { "creatorType": "author", "firstName": "John", "lastName": "Mcnaught" }, { "creatorType": "author", "firstName": "Sophia", "lastName": "Ananiadou" } ], "abstractNote": "", "proceedingsTitle": "Proceedings of the Demonstrations Session at EACL 2009", "conferenceName": "", "publisher": "Association for Computational Linguistics", "place": "Athens, Greece", "date": "April 2009", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "61–64", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://www.aclweb.org/anthology-new/E/E09/E09-2016.bib", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "biomedical" }, { "tag": "information-retrieval" }, { "tag": "lexicon" }, { "tag": "parsing" }, { "tag": "pos-tagging" }, { "tag": "question-answering" }, { "tag": "tools" } ], "collections": [], "relations": {}, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-18T21:09:22Z" } }, { "key": "NEP2H3QA", "version": 2, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/NEP2H3QA", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/NEP2H3QA", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Sagae et al.", "numChildren": 0 }, "data": { "key": "NEP2H3QA", "version": 2, "itemType": "conferencePaper", "title": "Evaluating the Effects of Treebank Size in a Practical Application for Parsing", "creators": [ { "creatorType": "author", "firstName": "Kenji", "lastName": "Sagae" }, { "creatorType": "author", "firstName": "Yusuke", "lastName": "Miyao" }, { "creatorType": "author", "firstName": "Rune", "lastName": "Saetre" }, { "creatorType": "author", "firstName": "Jun'ichi", "lastName": "Tsujii" } ], "abstractNote": "", "proceedingsTitle": "ACL workshop on software engineering, testing, and quality assurance 2008", "conferenceName": "", "publisher": "", "place": "", "date": "", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "biomedical" }, { "tag": "parsing" } ], "collections": [], "relations": {}, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-18T21:09:22Z" } }, { "key": "SDPT9CP9", "version": 2, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/SDPT9CP9", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/SDPT9CP9", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Roark et al.", "parsedDate": "2007-06", "numChildren": 0 }, "data": { "key": "SDPT9CP9", "version": 2, "itemType": "conferencePaper", "title": "Syntactic complexity measures for detecting Mild Cognitive Impairment", "creators": [ { "creatorType": "author", "firstName": "Brian", "lastName": "Roark" }, { "creatorType": "author", "firstName": "Margaret", "lastName": "Mitchell" }, { "creatorType": "author", "firstName": "Kristy", "lastName": "Hollingshead" } ], "abstractNote": "", "proceedingsTitle": "Biological, translational, and clinical language processing", "conferenceName": "", "publisher": "Association for Computational Linguistics", "place": "Prague, Czech Republic", "date": "June 2007", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1–8", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://www.aclweb.org/anthology-new/W/W07/W07-1001.bib", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "cognition" }, { "tag": "parsing" } ], "collections": [], "relations": {}, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-18T21:09:22Z" } }, { "key": "R5UH2ITS", "version": 2, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/R5UH2ITS", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/R5UH2ITS", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Pustejovsky et al.", "parsedDate": "2002", "numChildren": 0 }, "data": { "key": "R5UH2ITS", "version": 2, "itemType": "journalArticle", "title": "Robust relational parsing over biomedical literature: extracting inhibit relations.", "creators": [ { "creatorType": "author", "firstName": "J.", "lastName": "Pustejovsky" }, { "creatorType": "author", "firstName": "J.", "lastName": "Castaño" }, { "creatorType": "author", "firstName": "J.", "lastName": "Zhang" }, { "creatorType": "author", "firstName": "M.", "lastName": "Kotecki" }, { "creatorType": "author", "firstName": "B.", "lastName": "Cochran" } ], "abstractNote": "We describe the design of a robust parser for identifying and extracting biomolecular relations from the biomedical literature. Separate automata over distinct syntactic domains were developed for extraction of nominal-based relational information versus verbal-based relations. This allowed us to optimize the grammars separately for each module, regardless of any specific relation resulting in significantly better performance. A unique feature of this system is the use of text-based anaphora resolution to enhance the results of argument binding in relational extraction. We demonstrate the performance of our system on inhibition-relations, and present our initial results measured against an annotated text used as a gold standard for evaluation purposes. The results represent a significant improvement over previously published results on extracting such relations from Medline: Precision was 90%, Recall 57%, and Partial Recall 22%. These results demonstrate the effectiveness of a corpus-based linguistic approach to information extraction over Medline.", "publicationTitle": "Pac Symp Biocomput", "publisher": "", "place": "", "date": "2002", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "362–373", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://view.ncbi.nlm.nih.gov/pubmed/11928490", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "anaphora-resolution" }, { "tag": "medline" }, { "tag": "parsing" }, { "tag": "relation-extraction" }, { "tag": "relational-parsing" } ], "collections": [], "relations": {}, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-18T21:09:22Z" } }, { "key": "U8SWD4VT", "version": 2, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/U8SWD4VT", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/U8SWD4VT", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Miyao et al.", "parsedDate": "2009-02", "numChildren": 0 }, "data": { "key": "U8SWD4VT", "version": 2, "itemType": "journalArticle", "title": "Evaluating contributions of natural language parsers to protein–protein interaction extraction", "creators": [ { "creatorType": "author", "firstName": "Yusuke", "lastName": "Miyao" }, { "creatorType": "author", "firstName": "Kenji", "lastName": "Sagae" }, { "creatorType": "author", "firstName": "Rune", "lastName": "S\\aetre" }, { "creatorType": "author", "firstName": "Takuya", "lastName": "Matsuzaki" }, { "creatorType": "author", "firstName": "Jun'ichi", "lastName": "Tsujii" } ], "abstractNote": "Motivation: While text mining technologies for biomedical research have gained popularity as a way to take advantage of the explosive growth of information in text form in biomedical papers, selecting appropriate natural language processing (NLP) tools is still difficult for researchers who are not familiar with recent advances in NLP. This article provides a comparative evaluation of several state-of-the-art natural language parsers, focusing on the task of extracting protein–protein interaction (PPI) from biomedical papers. We measure how each parser, and its output representation, contributes to accuracy improvement when the parser is used as a component in a PPI system.Results: All the parsers attained improvements in accuracy of PPI extraction. The levels of accuracy obtained with these different parsers vary slightly, while differences in parsing speed are larger. The best accuracy in this work was obtained when we combined Miyao and Tsujii's Enju parser and Charniak and Johnson's reranking parser, and the accuracy is better than the state-of-the-art results on the same data.Availability: The PPI extraction system used in this work (AkanePPI) is available online at http://www-tsujii.is.s.u-tokyo.ac.jp/downloads/downloads.cgi. The evaluated parsers are also available online from each developer's site.Contact: yusuke@is.s.u-tokyo.ac.jp", "publicationTitle": "Bioinformatics", "publisher": "", "place": "", "date": "February 2009", "volume": "25", "issue": "3", "section": "", "partNumber": "", "partTitle": "", "pages": "394–400", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1093/bioinformatics/btn631", "citationKey": "", "url": "http://dx.doi.org/10.1093/bioinformatics/btn631", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "1460-2059", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "biomedical" }, { "tag": "ie" }, { "tag": "parsing" } ], "collections": [], "relations": {}, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-18T21:09:22Z" } }, { "key": "RF4BP65A", "version": 2, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/RF4BP65A", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/RF4BP65A", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Mcclosky et al.", "parsedDate": "2006", "numChildren": 0 }, "data": { "key": "RF4BP65A", "version": 2, "itemType": "conferencePaper", "title": "Reranking and self-training for parser adaptation", "creators": [ { "creatorType": "author", "firstName": "David", "lastName": "Mcclosky" }, { "creatorType": "author", "firstName": "Eugene", "lastName": "Charniak" }, { "creatorType": "author", "firstName": "Mark", "lastName": "Johnson" } ], "abstractNote": "Statistical parsers trained and tested on the Penn Wall Street Journal (WSJ) treebank have shown vast improvements over the last 10 years. Much of this improvement, however, is based upon an ever-increasing number of features to be trained on (typically) the WSJ treebank data. This has led to concern that such parsers may be too finely tuned to this corpus at the expense of portability to other genres. Such worries have merit. The standard †Charniak parser †checks in at a labeled precisionrecall f-measure of 89.7 % on the Penn WSJ test set, but only 82.9 % on the test set from the Brown treebank corpus. This paper should allay these fears. In particular, we show that the reranking parser described in Charniak and Johnson (2005) improves performance of the parser on Brown to 85.2%. Furthermore, use of the self-training techniques described in (Mc-Closky et al., 2006) raise this to 87.8% (an error reduction of 28%) again without any use of labeled Brown data. This is remarkable since training the parser and reranker on labeled Brown data achieves only 88.4%. 1", "proceedingsTitle": "In ACL", "conferenceName": "", "publisher": "", "place": "", "date": "2006", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "337–344", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.68.33", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "adaptation" }, { "tag": "parsing" } ], "collections": [], "relations": {}, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-18T21:09:22Z" } }, { "key": "S3W58HZR", "version": 2, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/S3W58HZR", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/S3W58HZR", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Johan and Wirén", "parsedDate": "2008", "numChildren": 0 }, "data": { "key": "S3W58HZR", "version": 2, "itemType": "journalArticle", "title": "Robust parsing and spoken negotiative dialogue with databases", "creators": [ { "creatorType": "author", "firstName": "B. O. Y. E.", "lastName": "Johan" }, { "creatorType": "author", "firstName": "M. A. T. S.", "lastName": "Wirén" } ], "abstractNote": "This paper presents a robust parsing algorithm and semantic formalism for the interpretation of utterances in spoken negotiative dialogue with databases. The algorithm works in two passes: a domain-specific pattern-matching phase and a domain-independent semantic analysis phase. Robustness is achieved by limiting the set of representable utterance types to an empirically motivated subclass which is more expressive than propositional slot–value lists, but much less expressive than first-order logic. Our evaluation shows that in actual practice the vast majority of utterances that occur can be handled, and that the parsing algorithm is highly efficient and accurate.", "publicationTitle": "Natural Language Engineering", "publisher": "", "place": "", "date": "2008", "volume": "14", "issue": "03", "section": "", "partNumber": "", "partTitle": "", "pages": "289–312", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1017/S1351324906004402", "citationKey": "", "url": "http://dx.doi.org/10.1017/S1351324906004402", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "parsing" }, { "tag": "speech" } ], "collections": [], "relations": {}, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-18T21:09:22Z" } }, { "key": "RJ2IZ6TI", "version": 2, "library": { "type": "group", "id": 73103, "name": "U of U DBMI NLP", "links": { "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/73103/items/RJ2IZ6TI", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/u_of_u_dbmi_nlp/items/RJ2IZ6TI", "type": "text/html" } }, "meta": { "createdByUser": { "id": 921078, "username": "mtharp813", "name": "Melissa Tharp", "links": { "alternate": { "href": "https://www.zotero.org/mtharp813", "type": "text/html" } } }, "creatorSummary": "Huang et al.", "parsedDate": "2005-05", "numChildren": 0 }, "data": { "key": "RJ2IZ6TI", "version": 2, "itemType": "journalArticle", "title": "Improved identification of noun phrases in clinical radiology reports using a high-performance statistical natural language parser augmented with the UMLS specialist lexicon.", "creators": [ { "creatorType": "author", "firstName": "Yang", "lastName": "Huang" }, { "creatorType": "author", "firstName": "Henry J.", "lastName": "Lowe" }, { "creatorType": "author", "firstName": "Dan", "lastName": "Klein" }, { "creatorType": "author", "firstName": "Russell J.", "lastName": "Cucina" } ], "abstractNote": "OBJECTIVE: The aim of this study was to develop and evaluate a method of extracting noun phrases with full phrase structures from a set of clinical radiology reports using natural language processing (NLP) and to investigate the effects of using the UMLS(R) Specialist Lexicon to improve noun phrase identification within clinical radiology documents. DESIGN: The noun phrase identification (NPI) module is composed of a sentence boundary detector, a statistical natural language parser trained on a nonmedical domain, and a noun phrase (NP) tagger. The NPI module processed a set of 100 XML-represented clinical radiology reports in Health Level 7 (HL7)(R) Clinical Document Architecture (CDA)-compatible format. Computed output was compared with manual markups made by four physicians and one author for maximal (longest) NP and those made by one author for base (simple) NP, respectively. An extended lexicon of biomedical terms was created from the UMLS Specialist Lexicon and used to improve NPI performance. RESULTS: The test set was 50 randomly selected reports. The sentence boundary detector achieved 99.0% precision and 98.6% recall. The overall maximal NPI precision and recall were 78.9% and 81.5% before using the UMLS Specialist Lexicon and 82.1% and 84.6% after. The overall base NPI precision and recall were 88.2% and 86.8% before using the UMLS Specialist Lexicon and 93.1% and 92.6% after, reducing false-positives by 31.1% and false-negatives by 34.3%. CONCLUSION: The sentence boundary detector performs excellently. After the adaptation using the UMLS Specialist Lexicon, the statistical parser's NPI performance on radiology reports increased to levels comparable to the parser's native performance in its newswire training domain and to that reported by other researchers in the general nonmedical domain.", "publicationTitle": "Journal of the American Medical Informatics Association : JAMIA", "publisher": "", "place": "", "date": "May 2005", "volume": "12", "issue": "3", "section": "", "partNumber": "", "partTitle": "", "pages": "275–285", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1197/jamia.M1695", "citationKey": "", "url": "http://dx.doi.org/10.1197/jamia.M1695", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "1067-5027", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "chunking" }, { "tag": "parsing" }, { "tag": "umls" } ], "collections": [], "relations": {}, "dateAdded": "2012-03-19T21:26:27Z", "dateModified": "2012-10-18T21:09:22Z" } } ]