Bio-medical entity extraction using Support Vector Machines
Published 1 January 2003Open access
Koichi Takeuchi, Nigel Collier
Citations32
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
A relationship between feature window size and the amount of training data is indicated and that a combination of surface words, orthographic features and head noun features achieve the best performance among the feature sets tested.
Abstract
Support Vector Machines have achieved state of the art performance in several classification tasks. In this article we apply them to the identification and semantic annotation of scientific and technical terminology in the domain of molecular biology. This illustrates the extensibility of the traditional named entity task to special domains with extensive terminologies such as those in medicine and related disciplines. We illustrate SVM's capabilities using a sample of 100 journal abstracts texts taken from the {human, blood cell, transcription factor} domain of MEDLINE. Approximately 3400 terms are annotated and the model performs at about 74% F-score on cross-validation tests. A detailed analysis based on empirical evidence shows the contribution of various feature sets to performance.
Keywords
Computer ScienceBiochemistry, Genetics and Molecular Biology
The Nature of Statistical Learning Theory
39,279 Citations1995Vladimir Vapnik
Data Mining and Knowledge DiscoveryA Tutorial on Support Vector Machines for Pattern Recognition
16,433 Citations1998Christopher J. C. Burges
There are several arguments which support the observed high accuracy of SVMs, which are reviewed and numerous examples and proofs of most of the key theorems are given.
Cambridge University Press eBooksAn Introduction to Support Vector Machines and Other Kernel-based Learning Methods
13,883 Citations2000Nello Cristianini, John Shawe‐Taylor
Knowledge AcquisitionA translation approach to portable ontology specifications
12,428 Citations1993Thomas Gruber
This paper describes a mechanism for defining ontologies that are portable over representation systems, basing Ontolingua itself on an ontology of domain-independent, representational idioms.
Technical reportsMaking Large-Scale SVM Learning Practical
4,317 Citations2006Thorsten Joachims
This chapter presents algorithmic and computational results developed for SVM light V 2.0, which make large-scale SVM training more practical and give guidelines for the application of SVMs to large domains.
Machine LearningChoosing Multiple Parameters for Support Vector Machines
2,182 Citations2002Olivier Chapelle, Vladimir Vapnik +2 more
The problem of automatically tuning multiple parameters for pattern recognition Support Vector Machines (SVMs) is considered by minimizing some estimates of the generalization error of SVMs using a gradient descent algorithm over the set of parameters.
A simple rule-based part of speech tagger
1,418 Citations1992Eric Brill
This work presents a simple rule-based part of speech tagger which automatically acquires its rules and tags with accuracy comparable to stochastic taggers, demonstrating that the stochastics method is not the only viable method for part ofspeech tagging.
Methods of Information in MedicineThe Unified Medical Language System
1,187 Citations1993Betsy L. Humphreys, Alexa T. McCray +1 more
The UMLS project and current developments in high-speed, high-capacity international networks are converging in ways that have great potential for enhancing access to biomedical information.
Natural Language EngineeringTechnical terminology: some linguistic properties and an algorithm for identification in text
817 Citations1995John S. Justeson, Slava M. Katz
The paper presents a terminology indentification algorithm that recovers a high proportion of the technical terms in a text, and a high proportaion of the recovered strings are vaild technical terms.
PubMedConstructing biological knowledge bases by extracting information from text sources.
597 Citations1999Mark Craven, Johan Kumlien
A research effort aimed at automatically mapping information from text sources into structured representations, such as knowledge bases, is begun, to use machine-learning methods to induce routines for extracting facts from text.
Yearbook of Medical InformaticsThe Unified Medical Language System
508 Citations1993Betsy L. Humphreys, Alexa T. McCray +1 more
Nucleic Acids ResearchThe SWISS-PROT protein sequence data bank and its new supplement TREMBL
479 Citations1996Amos Bairoch
This supplement consists of entries in SWISS-PROT-like format derived from the translation of all coding sequences (CDS) in the EMBL nucleotide sequence database, except CDS already included in SWiss- PROT.
A non-projective dependency parser
370 Citations1997Pasi Tapanainen, Timo Järvinen
This work describes a practical parser for unrestricted dependencies that creates links between words and names the links according to their syntactic functions.
Automatic Extraction of Protein Interactions from Scientific Abstracts
247 Citations1999James Thomas, David Milward +3 more
This paper motivates the use of Information Extraction for gathering data on protein interactions, describes the customization of an existing IE system, SRI's Highlight, for this task and presents the results of an experiment on unseen Medline abstracts which show that customization to a new domain can be fast, reliable and cost-effective.
Information Extraction with HMMs and Shrinkage
235 Citations1999Dayne Freitag, Andrew Kachites McCallum
A statistical technique called shrinkage is used that significantly improves parameter estimation of the HMM emission probabilities in the face of sparse training data and the resulting HMM outperforms a state-of-the-art rule-learning system.
Exploiting diverse knowledge sources via maximum entropy in named entity recognition
210 Citations1998Andrew Borthwick, John Sterling +2 more
This paper describes a novel statistical namedentity recognition system built around a maximum entity framework using the framework of maximum entropy theory and utilizing a flexible object-based architecture to make use of an extraordinarily diverse range of knowledge sources in making its tagging decisions.
Semantic Heterogeneity in Global Information Systems: The Role of Metadata, Context and Ontologies
196 Citations1997Vipul Kashyap, Amit Sheth
This chapter explores approaches to tackle semantic heterogeneity problem in the context of Global Information Systems GIS which are systems geared to handle information requests on the Global Information Infrastructure GII and proposes an approach using terminological relationships to achieve semantic interoperability.
Use of support vector machines in <i>extended</i> named entity recognition
133 Citations2002Koichi Takeuchi, Nigel Collier
The apparatus will maintain the club head in the same plane of the swing arm throughout the swing and maintain theClub face perpendicular to the line of travel while swinging the club in the normal back swing and forward swing.
A decision tree method for finding and classifying names in Japanese texts
124 Citations1998Satoshi Sekine, Ralph Grishman +1 more
A supervised learning system which uses a decision tree to find and classify names in Japanese texts, which does not work fully automatically and also needs special dictionaries, but performs well and does not have parameters to be adjusted by hand.
Terminology International Journal of Theoretical and Applied Issues in Specialized CommunicationGlossary of terms used in terminology
85 Citations1997B. Besse, Blaise Nkwenti‐Azeh +1 more
PubMedWord segmentation processing: a way to exponentially extend medical dictionaries.
46 Citations1995Christian Lovis, Pierre-André Michel +2 more
The approach developed in this paper is a pragmatic way to rapidly increase the lexico-semantic part of medical dictionaries and developed a semi-automatic tool, able to translate almost any diagnosis expressed in French into its equivalent in the ICD-9CM coding scheme.
Support Vector methods in learning and feature extraction
32 Citations1998Bernhard Schölkopf, Müller K-R Smola Aj +4 more
The idea of Mercer kernels and associated feature spaces are explained, connections to the theory of reproducing kernels and to regularization theory are described, and a technique for Nonlinear Principal Component Analysis (Kernel PCA) based on the same types of kernels is developed.
Building an Annotated Corpus in the Molecular-Biology Domain
26 Citations2000Yuka Tateisi, Tomoko Ohta +3 more
A corpus of annotated abstracts taken from National Library of Medicine's MEDLINE database is built, its ontological basis, and the experience in designing the annotation scheme are reported on.
Use of Support Vector Machines in Extended Named Entity Recognition
24 Citations2002Kouichi Takeuchi
Comparison between tagged corpora for the named entity task
24 Citations2000Chikashi Nobata, Nigel Collier +1 more
Two measures for comparing corpora based on information theory statistics such as gain ratio as well as simple term-class frequency counts are presented and it is found that gain ratio was the more reliable predictor.
Lecture notes in computer scienceA Framework for Integrating Deep and Shallow Semantic Structures in Text Mining
12 Citations2003Nigel Collier, Koichi Takeuchi +3 more
A framework for combining the shallow levels of semantic description commonly used in MUC-style information extraction with the deeper semantic structures available in such ontologies is presented.
Europe PMC (PubMed Central)Extraction of Medical Information from Textual Sources: A Statistical Variant of the Boundary Word Method
5 Citations1997Terrell W. Herzig, Merida L. Johns