SlideShare a Scribd company logo
1 of 17
Download to read offline
© 2014 IBM Corporation
Medical Relation Extraction with
Manifold Models
Chang Wang, IBM T. J. Watson Research Center
© 2014 IBM Corporation
Adapt IBM Watson to Different Domains
Contact Center
Healthcare Financial Services
Government
Diagnostic/treatment assistance,
evidenced-based insights,
collaborative medicine
Investment and retirement
planning, institutional trading
and decision support
Call center and tech support
services, enterprise knowledge
management, consumer insight
Public safety, improved
information sharing, security,
fraud and abuse prevention
© 2014 IBM Corporation
Main Topic of This Talk
This talk is about how we built a semantic relation extraction system for
medical domain.
A semantic relation example:
Healthcare
Diagnostic/treatment assistance,
evidenced-based insights,
collaborative medicine
What is the most common manifestation of MEN-1 (Multiple Endocrine Neoplasia type 1).
Symptom_of relation
© 2014 IBM Corporation
Motivation: How Relation Extraction is Used in Question Answering
– 1, Candidate Answer Generation:
• a, Detect relations in the question;
• b, Use the relation for knowledge base lookup (with UMLS KB, DBpedia, FreeBase, etc);
– 2, Passage Scoring:
Hyperparathyroidism is the most common sign of MEN-1.
What is the most common manifestation of MEN-1 (Multiple Endocrine Neoplasia type 1).
Question Focus
Symptom_of relation
Candidate Answer
Symptom_of relation
© 2014 IBM Corporation
Motivation: How Relation Extraction is Used in Question Answering
– 3, Knowledge Base (KB) Construction:
• a, Most existing KBs are manually built or extracted from semi structured sources, and thus have a
low coverage;
• b, Medical knowledge is growing and changing extremely quickly;
Our medical corpus contains 80M sentences
(11G pure text) coming from Wikipedia,
books, PubMed, etc.
© 2014 IBM Corporation
Identify the Key Medical Relations
From an analysis of 5,000 doctor dilemma questions from the American College of
Physicians and reading the literature (Demner-Fushman and Lin, 2007), we decided
to focus on 7 key relations.
These relations cover >50% of those 5,000 clinical questions.
© 2014 IBM Corporation
Collect Training Data- Distant Supervision + Human Labeling
This resulted in ~800 positive and ~13,000 negative labeled examples for each
relation, plus a huge amount of unlabeled examples.
© 2014 IBM Corporation
Technical Challenges & Design Goals:
1, Real data challenge:
– In typical relation extraction task, entities are manually labeled.
• For example, in i2b2 relation extraction task, entities are given and each has 1 of 3
concepts: “treatment”, “problem”, and “test”.
– In real applications, entities have to be automatically detected.
• In our application, entities are associated with multiple concepts from a list of 2.7M
concepts (can be further grouped into ~130 types).
2, Relation detectors need to be fast:
– Need to consider all the term pairs for each sentence in our corpus (80M sentences).
– Use linear classifiers.
3, Relation detectors need to be accurate:
– # training examples is not sufficient.
– labels from “crowd sourcing” and “distant supervision” are not 100% reliable.
– Utilize unlabeled data.
– Take label confidence into consideration.
© 2014 IBM Corporation
Method (1): Parsing
Most popular tool to parse medical text: MetaMap (Aronson, 2001)
We used Medical ESG
– An adaptation of ESG [English Slot Grammar] (McCord, Murdock, and Boguraev, 2012) to
medical domain;
– Similar results as Metamap;
– 10 times faster;
© 2014 IBM Corporation
Method (2): Feature Extraction
© 2014 IBM Corporation
Method (3): Cost Function to Minimize
Construct a linear mapping f that minimizes C(f):
αi: Label weight, xi: the ith example, µ: weight scalar,
f: mapping function, yi: label of xi, Wi,j: similarity of xi and xj,
)( ii xfx →
Positive
Positive
Negative
Negative
unlabeled
unlabeled
Negative
Illustration:
© 2014 IBM Corporation
Method (4): Algorithm:
Algorithm: Notation:
© 2014 IBM Corporation
Method (5): Advantages
A closed-form solution;
As fast as a linear regression classifier at the apply time;
Associate labels with weights;
– Useful for “crowd sourcing” and “distant supervision”
Make use of unlabeled data;
© 2014 IBM Corporation
Experiment (1): 5-Fold Cross Validation
On average, each relation has 800 positive examples and 13,000 negative examples;
For manifold models, 2,500-5,000 extra unlabeled examples are used.
Average F1 scores of all 5 folds;
Compare against SVM+ tree kernel (Collins and Duffy, 2001), SVM+ linear kernel (Schölkopf and Smola,
2002), Linear regression, SemRep (Rindflesch and Fiszman, 2003);
© 2014 IBM Corporation
Experiment (2): Knowledge Base Construction
Applied the relation detectors to our medical corpus with 80M sentences (11G text);
Resulted in 3.4M entries in the format of (relation_name, arg_1, arg_2, confidence);
The whole process cost 16 * 4 Core Machines 8 hours;
Evaluation
– A Candidate Answer Generation Experiment comparing the new KB and UMLS relation
KB (the most popular medical KB).
– 742 doctor dilemma questions from American College of Physicians;
– Detect relations in the question;
– Generate candidate answers using the relation based KB lookup;
– For each question, generate up to k answers: k=20, 50, 3000;
© 2014 IBM Corporation
Conclusions:
From the perspective of relation extraction applications,
– Identified 7 key relations that can facilitate clinical decision making
– Built a system that can directly extract relations from medical text
From the perspective of relation extraction methodologies,
– A manifold model based relation extraction system
• Closed-form solution
• Fast
• Utilizes unlabeled data
• Takes label weight into consideration
• Also works for the other domains
More detail: see “Relation Extraction with Manifold Models”, ACL-2014.
© 2014 IBM Corporation
References:
[1] A. Aronson. 2001. Effective mapping of biomedical text to the UMLS metathesaurus: the MetaMap
program.
[2] Michael Collins and Nigel Duffy. 2001. Convolution kernels for natural language.
[3] D. Demner-Fushman and J. Lin. 2007. Answering clinical questions with knowledge-based and
statistical techniques.
[4] D. Lindberg, B. Humphreys, and A. McCray. 1993. The Unified Medical Language System.
[5] M. McCord, J. W. Murdock, and B. K. Boguraev. 2012. Deep parsing in Watson.
[6] özlem Uzuner, B. R. South, S. Shen, and S. L. DuVall. 2011. 2010 i2b2/VA challenge on concepts,
assertions, and relations in clinical text.
[7] B. Schölkopf and A. J. Smola. 2002. Learning with Kernels: Support Vector Machines, Regularization,
Optimization, and Beyond.

More Related Content

What's hot

A Hybrid Approach for Personalized Recommender System Using Weighted TFIDF on...
A Hybrid Approach for Personalized Recommender System Using Weighted TFIDF on...A Hybrid Approach for Personalized Recommender System Using Weighted TFIDF on...
A Hybrid Approach for Personalized Recommender System Using Weighted TFIDF on...Editor IJCATR
 
Empirical analysis of ensemble methods for the classification of robocalls in...
Empirical analysis of ensemble methods for the classification of robocalls in...Empirical analysis of ensemble methods for the classification of robocalls in...
Empirical analysis of ensemble methods for the classification of robocalls in...IJECEIAES
 
Review of Multimodal Biometrics: Applications, Challenges and Research Areas
Review of Multimodal Biometrics: Applications, Challenges and Research AreasReview of Multimodal Biometrics: Applications, Challenges and Research Areas
Review of Multimodal Biometrics: Applications, Challenges and Research AreasCSCJournals
 
IRJET- Analysis of Rating Difference and User Interest
IRJET- Analysis of Rating Difference and User InterestIRJET- Analysis of Rating Difference and User Interest
IRJET- Analysis of Rating Difference and User InterestIRJET Journal
 
Trust Enhanced Role Based Access Control Using Genetic Algorithm
Trust Enhanced Role Based Access Control Using Genetic Algorithm Trust Enhanced Role Based Access Control Using Genetic Algorithm
Trust Enhanced Role Based Access Control Using Genetic Algorithm IJECEIAES
 
Information extraction from EHR
Information extraction from EHRInformation extraction from EHR
Information extraction from EHRAshis Chanda
 
an efficient approach for co extracting opinion targets based in online revie...
an efficient approach for co extracting opinion targets based in online revie...an efficient approach for co extracting opinion targets based in online revie...
an efficient approach for co extracting opinion targets based in online revie...INFOGAIN PUBLICATION
 
Search Interface Feature Evaluation in Biosciences
Search Interface Feature Evaluation in BiosciencesSearch Interface Feature Evaluation in Biosciences
Search Interface Feature Evaluation in BiosciencesZanda Mark
 
A Formal Machine Learning or Multi Objective Decision Making System for Deter...
A Formal Machine Learning or Multi Objective Decision Making System for Deter...A Formal Machine Learning or Multi Objective Decision Making System for Deter...
A Formal Machine Learning or Multi Objective Decision Making System for Deter...Editor IJCATR
 
IRJET- GPS based Medicine Informator
IRJET-  	  GPS based Medicine InformatorIRJET-  	  GPS based Medicine Informator
IRJET- GPS based Medicine InformatorIRJET Journal
 
Selecting Best Tractor Ranking Wise by Software using MADM(Multiple –Attribut...
Selecting Best Tractor Ranking Wise by Software using MADM(Multiple –Attribut...Selecting Best Tractor Ranking Wise by Software using MADM(Multiple –Attribut...
Selecting Best Tractor Ranking Wise by Software using MADM(Multiple –Attribut...IRJET Journal
 
On the benefit of logic-based machine learning to learn pairwise comparisons
On the benefit of logic-based machine learning to learn pairwise comparisonsOn the benefit of logic-based machine learning to learn pairwise comparisons
On the benefit of logic-based machine learning to learn pairwise comparisonsjournalBEEI
 
Predicting an Applicant Status Using Principal Component, Discriminant and Lo...
Predicting an Applicant Status Using Principal Component, Discriminant and Lo...Predicting an Applicant Status Using Principal Component, Discriminant and Lo...
Predicting an Applicant Status Using Principal Component, Discriminant and Lo...inventionjournals
 

What's hot (20)

Ijetcas14 368
Ijetcas14 368Ijetcas14 368
Ijetcas14 368
 
A Hybrid Approach for Personalized Recommender System Using Weighted TFIDF on...
A Hybrid Approach for Personalized Recommender System Using Weighted TFIDF on...A Hybrid Approach for Personalized Recommender System Using Weighted TFIDF on...
A Hybrid Approach for Personalized Recommender System Using Weighted TFIDF on...
 
C0441216
C0441216C0441216
C0441216
 
Empirical analysis of ensemble methods for the classification of robocalls in...
Empirical analysis of ensemble methods for the classification of robocalls in...Empirical analysis of ensemble methods for the classification of robocalls in...
Empirical analysis of ensemble methods for the classification of robocalls in...
 
Review of Multimodal Biometrics: Applications, Challenges and Research Areas
Review of Multimodal Biometrics: Applications, Challenges and Research AreasReview of Multimodal Biometrics: Applications, Challenges and Research Areas
Review of Multimodal Biometrics: Applications, Challenges and Research Areas
 
Ijcet 06 07_004
Ijcet 06 07_004Ijcet 06 07_004
Ijcet 06 07_004
 
IRJET- Analysis of Rating Difference and User Interest
IRJET- Analysis of Rating Difference and User InterestIRJET- Analysis of Rating Difference and User Interest
IRJET- Analysis of Rating Difference and User Interest
 
Trust Enhanced Role Based Access Control Using Genetic Algorithm
Trust Enhanced Role Based Access Control Using Genetic Algorithm Trust Enhanced Role Based Access Control Using Genetic Algorithm
Trust Enhanced Role Based Access Control Using Genetic Algorithm
 
Information extraction from EHR
Information extraction from EHRInformation extraction from EHR
Information extraction from EHR
 
an efficient approach for co extracting opinion targets based in online revie...
an efficient approach for co extracting opinion targets based in online revie...an efficient approach for co extracting opinion targets based in online revie...
an efficient approach for co extracting opinion targets based in online revie...
 
Phenoflow 2021
Phenoflow 2021Phenoflow 2021
Phenoflow 2021
 
Search Interface Feature Evaluation in Biosciences
Search Interface Feature Evaluation in BiosciencesSearch Interface Feature Evaluation in Biosciences
Search Interface Feature Evaluation in Biosciences
 
Search Interface Feature Evaluation
Search Interface Feature EvaluationSearch Interface Feature Evaluation
Search Interface Feature Evaluation
 
06522405
0652240506522405
06522405
 
C017510717
C017510717C017510717
C017510717
 
A Formal Machine Learning or Multi Objective Decision Making System for Deter...
A Formal Machine Learning or Multi Objective Decision Making System for Deter...A Formal Machine Learning or Multi Objective Decision Making System for Deter...
A Formal Machine Learning or Multi Objective Decision Making System for Deter...
 
IRJET- GPS based Medicine Informator
IRJET-  	  GPS based Medicine InformatorIRJET-  	  GPS based Medicine Informator
IRJET- GPS based Medicine Informator
 
Selecting Best Tractor Ranking Wise by Software using MADM(Multiple –Attribut...
Selecting Best Tractor Ranking Wise by Software using MADM(Multiple –Attribut...Selecting Best Tractor Ranking Wise by Software using MADM(Multiple –Attribut...
Selecting Best Tractor Ranking Wise by Software using MADM(Multiple –Attribut...
 
On the benefit of logic-based machine learning to learn pairwise comparisons
On the benefit of logic-based machine learning to learn pairwise comparisonsOn the benefit of logic-based machine learning to learn pairwise comparisons
On the benefit of logic-based machine learning to learn pairwise comparisons
 
Predicting an Applicant Status Using Principal Component, Discriminant and Lo...
Predicting an Applicant Status Using Principal Component, Discriminant and Lo...Predicting an Applicant Status Using Principal Component, Discriminant and Lo...
Predicting an Applicant Status Using Principal Component, Discriminant and Lo...
 

Similar to MLconf NYC Chang Wang

IBM Watson in Healthcare
IBM Watson in HealthcareIBM Watson in Healthcare
IBM Watson in HealthcareAnders Quitzau
 
AeHIN 28 August, 2014 - Innovation in Healthcare IT Standards: The Path to Bi...
AeHIN 28 August, 2014 - Innovation in Healthcare IT Standards: The Path to Bi...AeHIN 28 August, 2014 - Innovation in Healthcare IT Standards: The Path to Bi...
AeHIN 28 August, 2014 - Innovation in Healthcare IT Standards: The Path to Bi...Timothy Cook
 
Elsevier Industry Talk - WSDM 2020
Elsevier Industry Talk - WSDM 2020Elsevier Industry Talk - WSDM 2020
Elsevier Industry Talk - WSDM 2020Daniel Kershaw
 
shortstory258 slides.pptx
shortstory258 slides.pptxshortstory258 slides.pptx
shortstory258 slides.pptxAbdulVahedShaik
 
Machine learning - session 4
Machine learning - session 4Machine learning - session 4
Machine learning - session 4Luis Borbon
 
International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)ijceronline
 
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...ijceronline
 
Pin By David Rugger On Scoring And Notation Tea
Pin By David Rugger On Scoring And Notation  TeaPin By David Rugger On Scoring And Notation  Tea
Pin By David Rugger On Scoring And Notation TeaHeather Edwards
 
Evidence Based Healthcare Design
Evidence Based Healthcare DesignEvidence Based Healthcare Design
Evidence Based Healthcare DesignCarmen Martin
 
Mrta watson himss
Mrta watson himssMrta watson himss
Mrta watson himssLeon Henry
 
Using NLP Approach for Analyzing Customer Reviews
Using NLP Approach for Analyzing Customer Reviews Using NLP Approach for Analyzing Customer Reviews
Using NLP Approach for Analyzing Customer Reviews cscpconf
 
Chapter 7 PreviewReview IDIC Framework InteractCommunicat
Chapter 7 PreviewReview IDIC Framework InteractCommunicatChapter 7 PreviewReview IDIC Framework InteractCommunicat
Chapter 7 PreviewReview IDIC Framework InteractCommunicatsimisterchristen
 
emerson2021.pdf
emerson2021.pdfemerson2021.pdf
emerson2021.pdfh7r7cspjzp
 
T OP K-O PINION D ECISIONS R ETRIEVAL IN H EALTHCARE S YSTEM
T OP  K-O PINION  D ECISIONS  R ETRIEVAL IN  H EALTHCARE  S YSTEM T OP  K-O PINION  D ECISIONS  R ETRIEVAL IN  H EALTHCARE  S YSTEM
T OP K-O PINION D ECISIONS R ETRIEVAL IN H EALTHCARE S YSTEM csandit
 
Corporate data handling
Corporate data handlingCorporate data handling
Corporate data handlingJaipal Dhobale
 
cognitive computing for electronic medical record
cognitive computing for electronic medical record cognitive computing for electronic medical record
cognitive computing for electronic medical record selamu shirtawi
 
Big Data Means Big Potential Challenges for Nurse Execs Response.pdf
Big Data Means Big Potential Challenges for Nurse Execs Response.pdfBig Data Means Big Potential Challenges for Nurse Execs Response.pdf
Big Data Means Big Potential Challenges for Nurse Execs Response.pdfbkbk37
 
OpenEHR modeling case studies in China
OpenEHR modeling case studies in ChinaOpenEHR modeling case studies in China
OpenEHR modeling case studies in Chinaxudong_lu
 

Similar to MLconf NYC Chang Wang (20)

IBM Watson in Healthcare
IBM Watson in HealthcareIBM Watson in Healthcare
IBM Watson in Healthcare
 
AeHIN 28 August, 2014 - Innovation in Healthcare IT Standards: The Path to Bi...
AeHIN 28 August, 2014 - Innovation in Healthcare IT Standards: The Path to Bi...AeHIN 28 August, 2014 - Innovation in Healthcare IT Standards: The Path to Bi...
AeHIN 28 August, 2014 - Innovation in Healthcare IT Standards: The Path to Bi...
 
Elsevier Industry Talk - WSDM 2020
Elsevier Industry Talk - WSDM 2020Elsevier Industry Talk - WSDM 2020
Elsevier Industry Talk - WSDM 2020
 
shortstory258 slides.pptx
shortstory258 slides.pptxshortstory258 slides.pptx
shortstory258 slides.pptx
 
Machine learning - session 4
Machine learning - session 4Machine learning - session 4
Machine learning - session 4
 
International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)
 
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
 
Making Terminology Work
Making Terminology WorkMaking Terminology Work
Making Terminology Work
 
Pin By David Rugger On Scoring And Notation Tea
Pin By David Rugger On Scoring And Notation  TeaPin By David Rugger On Scoring And Notation  Tea
Pin By David Rugger On Scoring And Notation Tea
 
Evidence Based Healthcare Design
Evidence Based Healthcare DesignEvidence Based Healthcare Design
Evidence Based Healthcare Design
 
Mrta watson himss
Mrta watson himssMrta watson himss
Mrta watson himss
 
Using NLP Approach for Analyzing Customer Reviews
Using NLP Approach for Analyzing Customer Reviews Using NLP Approach for Analyzing Customer Reviews
Using NLP Approach for Analyzing Customer Reviews
 
Improving EMRs 2009
Improving EMRs 2009Improving EMRs 2009
Improving EMRs 2009
 
Chapter 7 PreviewReview IDIC Framework InteractCommunicat
Chapter 7 PreviewReview IDIC Framework InteractCommunicatChapter 7 PreviewReview IDIC Framework InteractCommunicat
Chapter 7 PreviewReview IDIC Framework InteractCommunicat
 
emerson2021.pdf
emerson2021.pdfemerson2021.pdf
emerson2021.pdf
 
T OP K-O PINION D ECISIONS R ETRIEVAL IN H EALTHCARE S YSTEM
T OP  K-O PINION  D ECISIONS  R ETRIEVAL IN  H EALTHCARE  S YSTEM T OP  K-O PINION  D ECISIONS  R ETRIEVAL IN  H EALTHCARE  S YSTEM
T OP K-O PINION D ECISIONS R ETRIEVAL IN H EALTHCARE S YSTEM
 
Corporate data handling
Corporate data handlingCorporate data handling
Corporate data handling
 
cognitive computing for electronic medical record
cognitive computing for electronic medical record cognitive computing for electronic medical record
cognitive computing for electronic medical record
 
Big Data Means Big Potential Challenges for Nurse Execs Response.pdf
Big Data Means Big Potential Challenges for Nurse Execs Response.pdfBig Data Means Big Potential Challenges for Nurse Execs Response.pdf
Big Data Means Big Potential Challenges for Nurse Execs Response.pdf
 
OpenEHR modeling case studies in China
OpenEHR modeling case studies in ChinaOpenEHR modeling case studies in China
OpenEHR modeling case studies in China
 

More from MLconf

Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...
Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...
Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...MLconf
 
Ted Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language UnderstandingTed Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language UnderstandingMLconf
 
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...MLconf
 
Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold Rush
Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold RushIgor Markov - Quantum Computing: a Treasure Hunt, not a Gold Rush
Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold RushMLconf
 
Josh Wills - Data Labeling as Religious Experience
Josh Wills - Data Labeling as Religious ExperienceJosh Wills - Data Labeling as Religious Experience
Josh Wills - Data Labeling as Religious ExperienceMLconf
 
Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...
Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...
Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...MLconf
 
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...MLconf
 
Meghana Ravikumar - Optimized Image Classification on the Cheap
Meghana Ravikumar - Optimized Image Classification on the CheapMeghana Ravikumar - Optimized Image Classification on the Cheap
Meghana Ravikumar - Optimized Image Classification on the CheapMLconf
 
Noam Finkelstein - The Importance of Modeling Data Collection
Noam Finkelstein - The Importance of Modeling Data CollectionNoam Finkelstein - The Importance of Modeling Data Collection
Noam Finkelstein - The Importance of Modeling Data CollectionMLconf
 
June Andrews - The Uncanny Valley of ML
June Andrews - The Uncanny Valley of MLJune Andrews - The Uncanny Valley of ML
June Andrews - The Uncanny Valley of MLMLconf
 
Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection Tasks
Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection TasksSneha Rajana - Deep Learning Architectures for Semantic Relation Detection Tasks
Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection TasksMLconf
 
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...MLconf
 
Vito Ostuni - The Voice: New Challenges in a Zero UI World
Vito Ostuni - The Voice: New Challenges in a Zero UI WorldVito Ostuni - The Voice: New Challenges in a Zero UI World
Vito Ostuni - The Voice: New Challenges in a Zero UI WorldMLconf
 
Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...
Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...
Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...MLconf
 
Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...
Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...
Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...MLconf
 
Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...
Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...
Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...MLconf
 
Neel Sundaresan - Teaching a machine to code
Neel Sundaresan - Teaching a machine to codeNeel Sundaresan - Teaching a machine to code
Neel Sundaresan - Teaching a machine to codeMLconf
 
Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...
Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...
Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...MLconf
 
Soumith Chintala - Increasing the Impact of AI Through Better Software
Soumith Chintala - Increasing the Impact of AI Through Better SoftwareSoumith Chintala - Increasing the Impact of AI Through Better Software
Soumith Chintala - Increasing the Impact of AI Through Better SoftwareMLconf
 
Roy Lowrance - Predicting Bond Prices: Regime Changes
Roy Lowrance - Predicting Bond Prices: Regime ChangesRoy Lowrance - Predicting Bond Prices: Regime Changes
Roy Lowrance - Predicting Bond Prices: Regime ChangesMLconf
 

More from MLconf (20)

Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...
Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...
Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...
 
Ted Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language UnderstandingTed Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language Understanding
 
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
 
Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold Rush
Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold RushIgor Markov - Quantum Computing: a Treasure Hunt, not a Gold Rush
Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold Rush
 
Josh Wills - Data Labeling as Religious Experience
Josh Wills - Data Labeling as Religious ExperienceJosh Wills - Data Labeling as Religious Experience
Josh Wills - Data Labeling as Religious Experience
 
Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...
Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...
Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...
 
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
 
Meghana Ravikumar - Optimized Image Classification on the Cheap
Meghana Ravikumar - Optimized Image Classification on the CheapMeghana Ravikumar - Optimized Image Classification on the Cheap
Meghana Ravikumar - Optimized Image Classification on the Cheap
 
Noam Finkelstein - The Importance of Modeling Data Collection
Noam Finkelstein - The Importance of Modeling Data CollectionNoam Finkelstein - The Importance of Modeling Data Collection
Noam Finkelstein - The Importance of Modeling Data Collection
 
June Andrews - The Uncanny Valley of ML
June Andrews - The Uncanny Valley of MLJune Andrews - The Uncanny Valley of ML
June Andrews - The Uncanny Valley of ML
 
Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection Tasks
Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection TasksSneha Rajana - Deep Learning Architectures for Semantic Relation Detection Tasks
Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection Tasks
 
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
 
Vito Ostuni - The Voice: New Challenges in a Zero UI World
Vito Ostuni - The Voice: New Challenges in a Zero UI WorldVito Ostuni - The Voice: New Challenges in a Zero UI World
Vito Ostuni - The Voice: New Challenges in a Zero UI World
 
Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...
Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...
Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...
 
Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...
Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...
Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...
 
Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...
Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...
Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...
 
Neel Sundaresan - Teaching a machine to code
Neel Sundaresan - Teaching a machine to codeNeel Sundaresan - Teaching a machine to code
Neel Sundaresan - Teaching a machine to code
 
Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...
Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...
Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...
 
Soumith Chintala - Increasing the Impact of AI Through Better Software
Soumith Chintala - Increasing the Impact of AI Through Better SoftwareSoumith Chintala - Increasing the Impact of AI Through Better Software
Soumith Chintala - Increasing the Impact of AI Through Better Software
 
Roy Lowrance - Predicting Bond Prices: Regime Changes
Roy Lowrance - Predicting Bond Prices: Regime ChangesRoy Lowrance - Predicting Bond Prices: Regime Changes
Roy Lowrance - Predicting Bond Prices: Regime Changes
 

MLconf NYC Chang Wang

  • 1. © 2014 IBM Corporation Medical Relation Extraction with Manifold Models Chang Wang, IBM T. J. Watson Research Center
  • 2. © 2014 IBM Corporation Adapt IBM Watson to Different Domains Contact Center Healthcare Financial Services Government Diagnostic/treatment assistance, evidenced-based insights, collaborative medicine Investment and retirement planning, institutional trading and decision support Call center and tech support services, enterprise knowledge management, consumer insight Public safety, improved information sharing, security, fraud and abuse prevention
  • 3. © 2014 IBM Corporation Main Topic of This Talk This talk is about how we built a semantic relation extraction system for medical domain. A semantic relation example: Healthcare Diagnostic/treatment assistance, evidenced-based insights, collaborative medicine What is the most common manifestation of MEN-1 (Multiple Endocrine Neoplasia type 1). Symptom_of relation
  • 4. © 2014 IBM Corporation Motivation: How Relation Extraction is Used in Question Answering – 1, Candidate Answer Generation: • a, Detect relations in the question; • b, Use the relation for knowledge base lookup (with UMLS KB, DBpedia, FreeBase, etc); – 2, Passage Scoring: Hyperparathyroidism is the most common sign of MEN-1. What is the most common manifestation of MEN-1 (Multiple Endocrine Neoplasia type 1). Question Focus Symptom_of relation Candidate Answer Symptom_of relation
  • 5. © 2014 IBM Corporation Motivation: How Relation Extraction is Used in Question Answering – 3, Knowledge Base (KB) Construction: • a, Most existing KBs are manually built or extracted from semi structured sources, and thus have a low coverage; • b, Medical knowledge is growing and changing extremely quickly; Our medical corpus contains 80M sentences (11G pure text) coming from Wikipedia, books, PubMed, etc.
  • 6. © 2014 IBM Corporation Identify the Key Medical Relations From an analysis of 5,000 doctor dilemma questions from the American College of Physicians and reading the literature (Demner-Fushman and Lin, 2007), we decided to focus on 7 key relations. These relations cover >50% of those 5,000 clinical questions.
  • 7. © 2014 IBM Corporation Collect Training Data- Distant Supervision + Human Labeling This resulted in ~800 positive and ~13,000 negative labeled examples for each relation, plus a huge amount of unlabeled examples.
  • 8. © 2014 IBM Corporation Technical Challenges & Design Goals: 1, Real data challenge: – In typical relation extraction task, entities are manually labeled. • For example, in i2b2 relation extraction task, entities are given and each has 1 of 3 concepts: “treatment”, “problem”, and “test”. – In real applications, entities have to be automatically detected. • In our application, entities are associated with multiple concepts from a list of 2.7M concepts (can be further grouped into ~130 types). 2, Relation detectors need to be fast: – Need to consider all the term pairs for each sentence in our corpus (80M sentences). – Use linear classifiers. 3, Relation detectors need to be accurate: – # training examples is not sufficient. – labels from “crowd sourcing” and “distant supervision” are not 100% reliable. – Utilize unlabeled data. – Take label confidence into consideration.
  • 9. © 2014 IBM Corporation Method (1): Parsing Most popular tool to parse medical text: MetaMap (Aronson, 2001) We used Medical ESG – An adaptation of ESG [English Slot Grammar] (McCord, Murdock, and Boguraev, 2012) to medical domain; – Similar results as Metamap; – 10 times faster;
  • 10. © 2014 IBM Corporation Method (2): Feature Extraction
  • 11. © 2014 IBM Corporation Method (3): Cost Function to Minimize Construct a linear mapping f that minimizes C(f): αi: Label weight, xi: the ith example, µ: weight scalar, f: mapping function, yi: label of xi, Wi,j: similarity of xi and xj, )( ii xfx → Positive Positive Negative Negative unlabeled unlabeled Negative Illustration:
  • 12. © 2014 IBM Corporation Method (4): Algorithm: Algorithm: Notation:
  • 13. © 2014 IBM Corporation Method (5): Advantages A closed-form solution; As fast as a linear regression classifier at the apply time; Associate labels with weights; – Useful for “crowd sourcing” and “distant supervision” Make use of unlabeled data;
  • 14. © 2014 IBM Corporation Experiment (1): 5-Fold Cross Validation On average, each relation has 800 positive examples and 13,000 negative examples; For manifold models, 2,500-5,000 extra unlabeled examples are used. Average F1 scores of all 5 folds; Compare against SVM+ tree kernel (Collins and Duffy, 2001), SVM+ linear kernel (Schölkopf and Smola, 2002), Linear regression, SemRep (Rindflesch and Fiszman, 2003);
  • 15. © 2014 IBM Corporation Experiment (2): Knowledge Base Construction Applied the relation detectors to our medical corpus with 80M sentences (11G text); Resulted in 3.4M entries in the format of (relation_name, arg_1, arg_2, confidence); The whole process cost 16 * 4 Core Machines 8 hours; Evaluation – A Candidate Answer Generation Experiment comparing the new KB and UMLS relation KB (the most popular medical KB). – 742 doctor dilemma questions from American College of Physicians; – Detect relations in the question; – Generate candidate answers using the relation based KB lookup; – For each question, generate up to k answers: k=20, 50, 3000;
  • 16. © 2014 IBM Corporation Conclusions: From the perspective of relation extraction applications, – Identified 7 key relations that can facilitate clinical decision making – Built a system that can directly extract relations from medical text From the perspective of relation extraction methodologies, – A manifold model based relation extraction system • Closed-form solution • Fast • Utilizes unlabeled data • Takes label weight into consideration • Also works for the other domains More detail: see “Relation Extraction with Manifold Models”, ACL-2014.
  • 17. © 2014 IBM Corporation References: [1] A. Aronson. 2001. Effective mapping of biomedical text to the UMLS metathesaurus: the MetaMap program. [2] Michael Collins and Nigel Duffy. 2001. Convolution kernels for natural language. [3] D. Demner-Fushman and J. Lin. 2007. Answering clinical questions with knowledge-based and statistical techniques. [4] D. Lindberg, B. Humphreys, and A. McCray. 1993. The Unified Medical Language System. [5] M. McCord, J. W. Murdock, and B. K. Boguraev. 2012. Deep parsing in Watson. [6] özlem Uzuner, B. R. South, S. Shen, and S. L. DuVall. 2011. 2010 i2b2/VA challenge on concepts, assertions, and relations in clinical text. [7] B. Schölkopf and A. J. Smola. 2002. Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond.