Improving performance of natural language processing part-of-speech tagging on clinical narratives through domain adaptation
Journal of the American Medical Informatics AssociationPublished 14 March 2013Open access
Jeffrey P. Ferraro, Hal Daumé, Scott L. DuVall, Wendy W. Chapman, Henk Harkema, Peter J. Haug
Citations44
SJR quartileQ1
SJR score2.04
SNIP1.95
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
ClinAdapt successfully boosts POS tagging performance through domain adaptation requiring a modest amount of annotated clinical data, to reduce pipeline error propagation leading to better overall results on complex processing tasks.
Abstract
ClinAdapt successfully boosts POS tagging performance through domain adaptation requiring a modest amount of annotated clinical data. Improving the performance of critical NLP subtasks is expected to reduce pipeline error propagation leading to better overall results on complex processing tasks.
Keywords
Computer Science
Building a Large Annotated Corpus of English: The Penn Treebank
7,528 Citations1993Mitchell P. Marcus
Feature-rich part-of-speech tagging with a cyclic dependency network
2,851 Citations2003Kristina Toutanova, Dan Klein +2 more
A new part-of-speech tagger is presented that demonstrates the following ideas: explicit use of both preceding and following tag contexts via a dependency network representation, broad use of lexical features, and effective use of priors in conditional loglinear models.
Journal of the American Medical Informatics AssociationMayo clinical Text Analysis and Knowledge Extraction System (cTAKES): architecture, component evaluation and applications
2,017 Citations2010Guergana Savova, James Masanz +5 more
The cTAKES annotations are the foundation for methods and modules for higher-level semantic processing of clinical free-text, and its components, specifically trained for the clinical domain, create rich linguistic and semantic annotations.
Domain adaptation with structural correspondence learning
1,562 Citations2006John Blitzer, Ryan McDonald +1 more
This work introduces structural correspondence learning to automatically induce correspondences among features from different domains in order to adapt existing models from a resource-rich source domain to aresource-poor target domain.
Transformation-based error-driven learning and natural language processing: a case study in part-of-speech tagging
1,531 Citations1995Eric Brill
This paper describes a simple rule-based approach to automated learning of linguistic knowledge that has been shown for a number of tasks to capture information in a clearer and more direct fashion without a compromise in performance.
Improved backing-off for M-gram language modeling
1,490 Citations2002Reinhard Kneser, Hermann Ney
This paper proposes to use distributions which are especially optimized for the task of back-off, which are quite different from the probability distributions that are usually used for backing-off.
ArXiv.orgFrustratingly Easy Domain Adaptation
1,395 Citations2009Hal Daumé
This work describes an approach to domain adaptation that is appropriate exactly in the case when one has enough “target” data to do slightly better than just using only “source’ data.
Machine LearningLearning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm
1,376 Citations1988Nick Littlestone
This work presents one such algorithm that learns disjunctive Boolean functions, along with variants for learning other classes of Boolean functions.
Maximum Entropy Model for Part-Of-Speech Tagging
1,276 Citations1996Adwait Ratnaparkhi
A statistical model which trains from a corpus annotated with Part Of Speech tags and assigns them to previously unseen text with state of the art accuracy and discusses the corpus consistency problems discovered during the implementation of these features.
BioinformaticsGENIA corpus—a semantically annotated corpus for bio-textmining
1,243 Citations2003JD Kim, Tomoko Ohta +2 more
Enriching the knowledge sources used in a maximum entropy part-of-speech tagger
948 Citations2000Kristina Toutanova, Christopher D. Manning
This paper presents results for a maximum-entropy-based part of speech tagger, which achieves superior performance principally by enriching the information sources used for tagging by incorporating these features: more extensive treatment of capitalization for unknown words, and features for the disambiguation of the tense forms of verbs.
Yearbook of Medical InformaticsExtracting Information from Textual Documents in the Electronic Health Record: A Review of Recent Research
896 Citations2008Guergana Savova, Karin Kipper-Schuler +2 more
Performance of information extraction systems with clinical text has improved since the last systematic review in 1995, but they are still rarely applied outside of the laboratory they have been developed in.
Machine LearningLearning quickly when irrelevant attributes abound: A new linear-threshold algorithm
501 Citations1988Nick Littlestone
This work presents one such algorithm that learns disjunctive Boolean functions, along with variants for learning other classes of Boolean functions.
ScholarlyCommons (University of Pennsylvania)Part-of-Speech Tagging Guidelines for the Penn Treebank Project (3rd Revision)
436 Citations1990Beatrice Santorini
This manual addresses the linguistic issues that arise in connection with annotating texts by part of speech ("tagging") and discusses parts of speech that are easily confused and gives guidelines on how to tag such cases.
Lecture notes in computer sciencePart-of-Speech Tagging from 97% to 100%: Is It Time for Some Linguistics?
408 Citations2011Christopher D. Manning
It is suggested and demonstrated that the largest opportunity for further progress comes from improving the taxonomic basis of the linguistic resources from which taggers are trained, that is, from improved descriptive linguistics.
Journal of the American Medical Informatics AssociationOvercoming barriers to NLP for clinical text: the role of shared tasks and the need for additional creative solutions
307 Citations2011Wendy W. Chapman, Prakash M. Nadkarni +4 more
This issue of JAMIA focuses on natural language processing (NLP) techniques for clinical-text information extraction and shared tasks like the i2b2/VA Challenge, a shared-task challenge co-sponsored by the Veteran's Administration for the last 2 years.
arXiv (Cornell University)Some Advances in Transformation-Based Part of Speech Tagging
279 Citations1994Eric Brill
BioinformaticsMedPost: a part-of-speech tagger for bioMedical text
225 Citations2004Larry Smith, Thomas C. Rindflesch +1 more
A part-of-speech tagger that achieves over 97% accuracy on MEDLINE citations and a corpus of 5700 manually tagged sentences are presented.
Journal of Biomedical InformaticsTwo biomedical sublanguages: a description based on the theories of Zellig Harris
219 Citations2002Carol Friedman, Pauline Kra +1 more
This paper summarizes Zellig Harris' language and sublanguage theories, and describes the sublanguage grammars developed for two different biomedical domains, and illustrates how Harris' theories provide a basis for the development of language processing systems in the biomedical domain.
Transformation-based learning in the fast lane
204 Citations2001Grace Ngai, Radu Florian
This paper presents a novel and realistic method for speeding up the training time of a transformation-based learner without sacrificing performance and shows that this system is able to achieve a significant improvement in training time while still achieving the same performance as a standard transformation- based learner.
A rule-based approach to prepositional phrase attachment disambiguation
195 Citations1994Eric Brill, Philip Resnik
A new corpus- based approach to prepositional phrase attachment disambiguation is described, and results comparing performance of this algorithm with other corpus-based approaches to this problem are presented.
Mistake bounds and logarithmic linear-threshold learning algorithms
184 Citations1990N. Littlestone
An analysis that shows that a straightforward transformation applied to mistake bounded algorithms, consisting of adding a hypothesis testing phase, produces algorithms that have asymptotically optimal PAC-learning bounds for certain target classes.
Guided Learning for Bidirectional Sequence Classification
158 Citations2007Libin Shen, Giorgio Satta +1 more
Computational LinguisticsSample Selection for Statistical Parsing
135 Citations2004Rebecca Hwa
It is found that sample selection can significantly reduce the size of annotated training corpora and that uncertainty is a robust predictive criterion that can be easily applied to different learning models.
Solving the problem of cascading errors
115 Citations2006Jenny Rose Finkel, Christopher D. Manning +1 more
A novel architecture is presented, which models these pipelines as Bayesian networks, with each low level task corresponding to a variable in the network, and then it is performed approximate inference to find the best labeling.
The MIT Press eBooksLearning as Search Optimization
114 Citations2007Hal Daumé, Daniel Marcu
This chapter contains sections titled: Introduction, Previous Work, Search Optimization, Experiments, Summary and Discussion.
DigitalCommons@UTEP (The University of Texas at El Paso)Understanding and Computing Cohen’s Kappa: A Tutorial.
103 Citations2007James M. Wood
This tutorial explains the underlying logic of Kappa and shows why it is superior to simple percentage of agreement as a measure of interrater reliability.
Part of speech tagging using a network of linear separators
103 Citations1998Dan Roth, Dmitry Zelenko
An architecture and an on-line learning algorithm are presented that utilizes this mistake-driven algorithm for multi-class prediction-selecting the part of speech of a word and it is shown that the algorithm performs comparably to the best known algorithms for POS.
Information Processing & ManagementThe medical archival system: An information retrieval system based on distributed parallel processing
100 Citations1991Russell J. Yount, John K. Vries
The software design of MARS is described and its implementation as a practical system for large-scale information management is described.
PubMedIdentification of findings suspicious for breast cancer based on natural language processing of mammogram reports.
98 Citations1997Nilesh Jain, C Friedman
While MedLEE was able to identify all the suspicious findings, it varied in the level of granularity, particularly about the location of the suspicious finding, particularly in the area of the mammography center.
PubMedIdentification of suspected tuberculosis patients based on natural language processing of chest radiograph reports.
96 Citations1996Nilesh Jain, Charles Knirsch +2 more
A retrospective study to determine if MedLEE can identify patients at risk for having tuberculosis (TB) based on their admission chest radiographs to determine patient eligibility for computerized clinical practice guidelines.
Learning Based Java for Rapid Development of NLP Systems
68 Citations2010Nick Rizzolo, Dan Roth
This paper demonstrates that there exists a theoretical model that describes most NLP approaches adeptly and introduces the concept of data driven compilation, a translation process in which the efficiency of the generated code benefits from the data given as input to the learning algorithms.
Meeting of the Association for Computational LinguisticsSimple Semi-Supervised Training of Part-Of-Speech Taggers
67 Citations2010Anders Søgaard
PubMedA natural language parsing system for encoding admitting diagnoses.
51 Citations1997Peter J. Haug, Lee M. Christensen +4 more
A natural language parser is developed that converts free-text admitting diagnoses into a coded form and has proven acceptably accurate in the experimental laboratory to warrant a test in the target clinical environment.
Journal of Biomedical InformaticsDomain-specific language models and lexicons for tagging
50 Citations2005Anni Coden, Serguei Pakhomov +3 more
It is shown that a large annotated general-English corpus is not sufficient for building a part-of-speech tagger model adequate for tagging documents from the medical domain, and a quite small domain-specific corpus to a large general- English one boosts performance to over 92% accuracy from 87% in studies.
Kluwer Academic Publishers eBooksSemantic Text Parsing for Patient Records
47 Citations2006Carol Friedman
This chapter focuses on semantic methods that map narrative patient information to a structured coded form that will be accessible to other automated applications.
International Journal of Medical InformaticsDeveloping a corpus of clinical notes manually annotated for part-of-speech
44 Citations2005Serguei Pakhomov, AR Coden +1 more
Preliminary experimental results indicate the necessity for adapting state-of-the-art POS taggers to the sublanguage domain of clinical text and find that discriminating between different types of discourse represented by different sections ofclinical text may be very beneficial to improve correctness of POS tagging.
PubMedComparing syntactic complexity in medical and non-medical corpora.
42 Citations2001David A. Campbell, Stephen B. Johnson
The results show that the syntax of medical language shows less variation than non-medical language and is likely simpler, which may reduce the difficulty of some free text machine learning problems by capitalizing on the simpler nature of narrative medical syntax.
Methods of Information in MedicineThe Distinction between Linguistic and Conceptual Semantics in Medical Terminology and its Implication for NLP-Based Knowledge Acquisition
37 Citations1998F. Buekens, Georges De Moor +2 more
It is argued that in a multilingual environment, linguistic ontologies should be designed as interfaces between domain conceptualizations and linguistic knowledge bases and described how the distinction between conceptual and linguistic semantics may assist in reaching this objective.
Detecting Structural Metadata with Decision Trees and Transformation-Based Learning
36 Citations2004Joungbum Kim, Sarah Schwarm +1 more
Combinations of decision trees and language models are used to predict sentence ends and interruption points and given these events transformation based learning is used to detect edit disfluencies and conversational fillers.
PubMedPart-of-speech tagging for clinical text: wall or bridge between institutions?
33 Citations2011Jung-Wei Fan, Rashmi Prasad +5 more
It is suggested that institutions can benefit more from sharing raw annotations but less from sharing pre-trained models for the POS tagging task, and cross-institution data sharing for other types of NLP tasks.
Journal of the American Medical Informatics AssociationHeuristic Sample Selection to Minimize Reference Standard Training Set for a Part-Of-Speech Tagger
30 Citations2007K. Liu, Wendy W. Chapman +2 more
Multidimensional transformation-based learning
26 Citations2001Radu Florian, Grace Ngai
A novel method that allows a machine learning algorithm following the transformation-based learning paradigm to be applied to multiple classification tasks by training jointly and simultaneously on all fields is presented.
Transformation-based learning for semantic parsing
18 Citations2009Filip Jurčíček, Milomir Gašić +5 more
This paper presents a semantic parser that transforms an initial semantic hypothesis into the correct semantics by applying an ordered list of transformation rules which enables the parser to be very efficient while retaining high accuracy.
Computational LinguisticsA Life of Language
16 Citations2005Martin Kay
This is a truly overwhelming experience, and I am honored and humbled and, of course, delighted to be among so many of the friends that have enriched my life in so many ways.
Amsterdam studies in the theory and history of linguistic science. Series 4, Current issues in linguistic theoryMultilingual dependency parsing: A pipeline approach
13 Citations2007Ming‐Wei Chang, Quang Do +1 more
This paper develops a general framework for machine learning based dependency parsing based on a pipeline approach, where a task is decomposed into several sequential stages, and proposes two natural principles for pipeline frameworks to make local decisions as reliable as possible and reduce the number of sequential decisions made.
Academic Emergency MedicineThe Research Guide: A Primer for Residents, Other Health Care Trainees, and Practitioners
11 Citations2012David L. Schriger, Marc A. Probst +1 more
A transformational-based learner for dependency grammars in discharge summaries
11 Citations2002David A. Campbell, Stephen B. Johnson
A dependency grammar parser that learns through a transformational-based algorithm, and a novel design for templates and transformations which capitalize on the dependency structure directly and produces human-readable rules.
Natural Language EngineeringRandomized rule selection in transformation-based learning: a comparative study
9 Citations2001Sandra Carberry, K. Vijay‐Shanker +2 more
A variant of TBL that overcomes the training time problems of standard TBL without sacrificing accuracy is presented, called Randomized TBL, which includes a set of experiments on part-of-speech tagging in which the size of the corpus and template set are varied.