assisted curation does text mining really help
play

Assisted Curation: Does Text Mining Really Help? (Alex et al. 2008) - PowerPoint PPT Presentation

Oct 15, 2023 •243 likes •900 views

Assisted Curation: Does Text Mining Really Help? (Alex et al. 2008) by Benedict Fehringer Seminar: Unlocking the Secrets of the Past: Text Mining for Historical Documents Supervisor: Dr. Caroline Sporleder (and Martin Schreiber)

  1. Assisted Curation: Does Text Mining Really Help? (Alex et al. 2008) by Benedict Fehringer Seminar: „Unlocking the Secrets of the Past: Text Mining for Historical Documents“ Supervisor: Dr. Caroline Sporleder (and Martin Schreiber) 23.02.2012 Donnerstag, 23. Februar 2012

  2. Outline ! Introduction ! Related Work ! Assisted Curation ! Text Mining Pipeline ! Curation Experiments ! Discussion and Conclusion ! References Donnerstag, 23. Februar 2012

  3. Outline ! Introduction ! Related Work ! Assisted Curation ! Text Mining Pipeline ! Curation Experiments ! Discussion and Conclusion ! References Donnerstag, 23. Februar 2012

  4. Basic study elements - Content - ! Curation of biomedical literature ! For example, protein-protein interaction recognition: 1. Which protein are there? 2. If two proteins are named, are they in interaction? Donnerstag, 23. Februar 2012

  5. Example for protein-protein interaction recognition [...] An example is YHR105W, which interacts with one protein involved in 1. Which proteins are there? vesicular transport, Akr2, and with YGL161C, an uncharacterized protein 2. If two proteins are named, are that interacts with two transport they in interaction? proteins, Yip1 and Pep12. YHR105W also interacts with YPL246C, another uncharacterized protein that interacts with Ypt1 and Vam7, proteins implicated in vesicular transport and membrane fusion, respectively. [...] Source: Schwikowski, Uetz, & Fields (pp. 1259, 2000) Donnerstag, 23. Februar 2012

  6. Basic study elements - Research Question - ! Curation of biomedical literature ! For example, protein-protein interaction recognition: 1. Which protein are there? 2. If two proteins are named, are they in interaction? ! Task should be supported by text mining Donnerstag, 23. Februar 2012

  7. Related Work ! Increasing development of information extraction systems (spurred on by BioCreAtIvE II competition; Krallinger, Leitner, & Valencia, 2007) ! studies suggest reduction of curation time ! But: lack of user studies for extrinsically evaluation ! no validation by curator feedback about affecting their work and usefulness Donnerstag, 23. Februar 2012

  8. Basic study elements - Evaluation - ! Curation of biomedical literature ! For example, protein-protein interaction recognition: 1. Which protein are there? 2. If two proteins are named, are they in interaction? ! Task should be supported by text mining ! Evaluation by: ! objective performance metrics (e.g. speed improvement, number of records) ! focusing on user feedback, too Donnerstag, 23. Februar 2012

  9. Outline ! Introduction ! Related Work ! Assisted Curation ! Text Mining Pipeline ! Curation Experiments ! Discussion and Conclusion ! References Donnerstag, 23. Februar 2012

  10. Curation Scenario - General - ! Goal: Curators should identify protein-protein interactions (PPIs) ! Initial step: Providing set of matching papers ! Middle step: Filtering papers into candidates Donnerstag, 23. Februar 2012

  11. Curation Scenario - General - ! Goal: Curators should identify protein-protein interactions (PPIs) ! Initial step: Providing set of matching papers How can NLP help the curator ! Middle step: Filtering papers into candidates work? Donnerstag, 23. Februar 2012

  12. Curation Scenario - General - ! Goal: Curators should identify protein-protein interactions (PPIs) ! Initial step: Providing set of matching papers ! Middle step: Filtering papers into candidates ! Basic Assumption: Information Extraction (IE) techniques are likely effective in identifying entities and relations " More specific: NLP can propose candidate PPIs Donnerstag, 23. Februar 2012

  13. Curation Scenario - General - ! Goal: Curators should identify protein-protein interactions (PPIs) ! Initial step: Providing set of matching papers ! Middle step: Filtering papers into candidates ! Basic Assumption: Information Extraction (IE) techniques are likely effective in identifying entities and relations " More specific: NLP can propose candidate PPIs Donnerstag, 23. Februar 2012

  14. Curation Scenario - Concrete - Information Flow in the Curation Process Source: Alex et al. (p. 558, 2008) Donnerstag, 23. Februar 2012

  15. Curation Scenario - Concrete - Information Flow in the Curation Process Source: Alex et al. (p. 558, 2008) Donnerstag, 23. Februar 2012

  16. Curation Scenario - Concrete - Information Flow in the Curation Process Source: Alex et al. (p. 558, 2008) Donnerstag, 23. Februar 2012

  17. Curation Scenario - Concrete - Information Flow in the Curation Process Source: Alex et al. (p. 558, 2008) Donnerstag, 23. Februar 2012

  18. Curation Scenario - Concrete - Information Flow in the Curation Process Source: Alex et al. (p. 558, 2008) Donnerstag, 23. Februar 2012

  19. Curation Scenario - Concrete - Information Flow in the Curation Process Source: Alex et al. (p. 558, 2008) Donnerstag, 23. Februar 2012

  20. NLP Engine - Main Components - Concrete Subtasks NLP-Components 1. Exists protein‘s name in 1. Named Entity sentence? Recognition 2. Which protein do they name? 2. Term Identification 3. If two proteins are named, are 3. Relation Extraction they in interaction? Donnerstag, 23. Februar 2012

  21. NLP Engine - Creation details - ! How should the interface design look like? Donnerstag, 23. Februar 2012

  22. NLP Engine - Creation details - For example: To decide which species is associated with which protein should be quite simple for an ! How should the interface design look like? expert but not necessarily for the software. ! How should the labour be divided between human and the software? Donnerstag, 23. Februar 2012

  23. NLP Engine - Creation details - For example: Should recall or precision ! How should the interface design look like? be improved? ! How should the labour be divided between human and the software? ! Which functional characteristics of the NLP engine would be optimal? Donnerstag, 23. Februar 2012

  24. NLP Engine - Creation details - ! How should the interface design look like? ! How should the labour be divided between human and the software? ! Which functional characteristics of the NLP engine would be optimal? The focus will be on the third question. Donnerstag, 23. Februar 2012

  25. Outline ! Introduction ! Related Work ! Assisted Curation ! Text Mining Pipeline ! Curation Experiments ! Discussion and Conclusion ! References Donnerstag, 23. Februar 2012

  26. Pipeline-Components Pre- Named Entity Corpus processing Recognition Component Relation Term Performance Extraction Identification Donnerstag, 23. Februar 2012

  27. Pipeline-Components inter-annotator 217 Papers agreement Pre- Named Entity Corpus 84.9 64.8 processing Recognition PPI FRAG* 9 Entities relations relations were enriched with Component Relation Term Performance 88.4 Extraction Identification 87.1 59.6 Properties Normalized Attributes *linked fragments and mutants to their parents Donnerstag, 23. Februar 2012

  28. Pipeline-Components inter-annotator 217 Papers agreement Pre- Named Entity Corpus 84.9 64.8 processing Recognition PPI FRAG* 9 Entities relations relations Corpus consists of 2 million tokens: were enriched with Component Relation Term Performance 88.4 Extraction Identification - TRAIN (66%) 87.1 59.6 - DEVTEST (17%) Properties Normalized Attributes - TEST (17%) *linked fragments and mutants to their parents Donnerstag, 23. Februar 2012

  29. Pipeline-Components Pre- Named Entity Corpus processing Recognition Component Relation Term Performance Extraction Identification Donnerstag, 23. Februar 2012

  30. Pipeline-Components Pre- Named Entity Corpus processing Recognition Sentence Adding useful Attaches NCBI* boundary Tokenization linguistic taxonomy Component Relation Term detection markup identifiers Performance Extraction Identification *National Center for Biotechnology Information Donnerstag, 23. Februar 2012

  31. Pipeline-Components Pre- Named Entity Corpus processing Recognition Component Relation Term Performance Extraction Identification Donnerstag, 23. Februar 2012

  32. Pipeline-Components no entity Pre- Named Entity Corpus processing Recognition Component Relation Term Performance Extraction Identification entity Donnerstag, 23. Februar 2012

  33. Pipeline-Components entity no entity Sum no entity pred pred entity Pre- Named Entity 9 3 12 Corpus real processing Recognition no entity 1 11 12 real Sum 10 14 24 Component Relation Term Performance Extraction Identification entity Donnerstag, 23. Februar 2012

  34. Pipeline-Components entity no entity Sum no entity pred pred entity Pre- Named Entity 9 3 12 Corpus real processing Recognition no entity 1 11 12 real Sum 10 14 24 Component Relation Term Performance Extraction Identification Recall: 9/12 = 0.75 entity Donnerstag, 23. Februar 2012

  35. Pipeline-Components entity no entity Sum no entity pred pred entity Pre- Named Entity 9 3 12 Corpus real processing Recognition no entity 1 11 12 real Sum 10 14 24 Component Relation Term Performance Extraction Identification Recall: 9/12 = 0.75 Precision: 9/10 = 0.9 entity Donnerstag, 23. Februar 2012

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Evaluation of text data mining for Evaluation of text data mining for database curation: lessons

Evaluation of text data mining for Evaluation of text data mining for database curation: lessons

Evaluation of text data mining for Evaluation of text data mining for database curation: lessons learned database curation: lessons learned from the KDD Challenge Cup from the KDD Challenge Cup Alexander S. Yeh, Lynette Hirschman, and

235 views • 11 slides
Text Mining Text Mining Web pages Emails Technical documents Corporate documents

Text Mining Text Mining Web pages Emails Technical documents Corporate documents

Motivation for Text Mining Motivation for Text Mining Approximately 90% of the Worlds data is held in unstructured formats Text Mining Text Mining Web pages Emails Technical documents Corporate documents Books

456 views • 9 slides
Contents Text Mining Concept Tasks Twitter Data Analysis with R Twitter Extracting Tweets

Contents Text Mining Concept Tasks Twitter Data Analysis with R Twitter Extracting Tweets

Text Mining with R Yanchang Zhao http://www.RDataMining.com R and Data Mining Course Beijing University of Posts and Telecommunications, Beijing, China July 2019 Chapter 10: Text Mining, in R and Data Mining: Examples and Case Studies

904 views • 64 slides
Contents Text Mining Concept Tasks Twitter Data Analysis with R Twitter Extracting Tweets

Contents Text Mining Concept Tasks Twitter Data Analysis with R Twitter Extracting Tweets

Text Mining with R Yanchang Zhao http://www.RDataMining.com Tutorial on Machine Learning with R The Melbourne Data Science Week 2017 1 June 2017 Chapter 10: Text Mining, in R and Data Mining: Examples and Case Studies .

733 views • 57 slides
Text Mining with R Ben Williams 2018 Resources Text Mining with R: Julia Silge (StackOverflow)

Text Mining with R Ben Williams 2018 Resources Text Mining with R: Julia Silge (StackOverflow)

Text Mining with R Ben Williams 2018 Resources Text Mining with R: Julia Silge (StackOverflow) & David Robinson (DataCamp) https://www.tidytextmining.com/ R for Data Science: Garrett Grolemund & Hadley Wickham http://r4ds.had.co.nz/

866 views • 15 slides
Scholarly Text Curation & Robust Anchoring Requirements Timothy W. Cole

Scholarly Text Curation & Robust Anchoring Requirements Timothy W. Cole

W3C Workshop on Annotations San Francisco, California USA 2 April 2014 Scholarly Text Curation & Robust Anchoring Requirements Timothy W. Cole (t-cole3@illinois.edu) Thomas G. Habing (thabing@illinois.edu) Anchoring Methods to Support

329 views • 20 slides
Data Mining in Bioinformatics Day 4: Text Mining Karsten Borgwardt February 21 to March 4, 2011

Data Mining in Bioinformatics Day 4: Text Mining Karsten Borgwardt February 21 to March 4, 2011

Data Mining in Bioinformatics Day 4: Text Mining Karsten Borgwardt February 21 to March 4, 2011 Machine Learning & Computational Biology Research Group MPIs Tbingen .: Data Mining in Bioinformatics, Page 1 What is text mining?

813 views • 31 slides
2. Text Mining D-BSSE Karsten Borgwardt Data Mining II Course, Basel Spring Semester 2016 118

2. Text Mining D-BSSE Karsten Borgwardt Data Mining II Course, Basel Spring Semester 2016 118

2. Text Mining D-BSSE Karsten Borgwardt Data Mining II Course, Basel Spring Semester 2016 118 / 179 Text Mining Goals To learn key problems and techniques in the mining one of the most common types of data To learn how to represent text

738 views • 59 slides
Mining Minds Interpreter Service Curation Layer MMV-2.5 Overview 2 / Personalization is a

Mining Minds Interpreter Service Curation Layer MMV-2.5 Overview 2 / Personalization is a

Recommendation Mining Minds Interpreter Service Curation Layer MMV-2.5 Overview 2 / Personalization is a key element in Recommender Systems Personalization consists of tailoring a service or a product to accommodate specific needs of

600 views • 25 slides
Text Mining in Search Engines By: DJ Ambler With special thanks to the Internet Overview

Text Mining in Search Engines By: DJ Ambler With special thanks to the Internet Overview

Text Mining in Search Engines By: DJ Ambler With special thanks to the Internet Overview What is text mining? How is it used in search engines? Text Mining Definition A way to extract meaning from text Structuring, deriving

314 views • 10 slides
Data Mining in Bioinformatics Day 4: Text Mining Karsten Borgwardt February 25 to March 10

Data Mining in Bioinformatics Day 4: Text Mining Karsten Borgwardt February 25 to March 10

Data Mining in Bioinformatics Day 4: Text Mining Karsten Borgwardt February 25 to March 10 Bioinformatics Group MPIs Tbingen Karsten Borgwardt: Data Mining in Bioinformatics, Page 1 What is text mining? Definition Text mining is the use

603 views • 31 slides
INTEROPen FHIR Curation Work Dr. Munish Jokhani FHIR Curation Clinical Engagement Lead, NHS

INTEROPen FHIR Curation Work Dr. Munish Jokhani FHIR Curation Clinical Engagement Lead, NHS

INTEROPen FHIR Curation Work Dr. Munish Jokhani FHIR Curation Clinical Engagement Lead, NHS Digital 3 Agenda Use cases(Transfer of Care & GP Connect) What is FHIR curation/Why do we need curation? How: Overall curation

945 views • 63 slides
Combining data mining and text mining for detec1on of early

Combining data mining and text mining for detec1on of early

Combining data mining and text mining for detec1on of early stage demen1a: the SAMS framework Christopher Bull, Dommy Asfiandy, Ann Gledson, Joseph

284 views • 14 slides
Digital history and big data: Text mining historical documents on trade in the British Empire

Digital history and big data: Text mining historical documents on trade in the British Empire

Digital history and big data: Text mining historical documents on trade in the British Empire Beatrice Alex balex@inf.ed.ac.uk Digital scholarship: day of ideas 2, Edinburgh, 02/05/2013 OVERVIEW What is text mining? Text Mining in digital

484 views • 27 slides
Web Mining and Recommender Systems T ext Mining Learning Goals Introduce the topic of text

Web Mining and Recommender Systems T ext Mining Learning Goals Introduce the topic of text

Web Mining and Recommender Systems T ext Mining Learning Goals Introduce the topic of text mining Describe some of the difficulties of dealing with textual data Administrivia Midterm will be handed out after class next Monday Nov 9

891 views • 87 slides
Text Mining and Historical Research Beatrice Alex balex@inf.ed.ac.uk MSc Historical Research,

Text Mining and Historical Research Beatrice Alex balex@inf.ed.ac.uk MSc Historical Research,

Text Mining and Historical Research Beatrice Alex balex@inf.ed.ac.uk MSc Historical Research, University of Edinburgh, March 21st 2014 Friday, 21 March 2014 OVERVIEW What is text mining? Types of text analyses. Trading Consequences: text

698 views • 36 slides
MemeSequencer : Sparse Matching for Embedding Image Macros Abhimanyu (Abhi) Dubey, Esteban Moro,

MemeSequencer : Sparse Matching for Embedding Image Macros Abhimanyu (Abhi) Dubey, Esteban Moro,

MemeSequencer : Sparse Matching for Embedding Image Macros Abhimanyu (Abhi) Dubey, Esteban Moro, Manuel Cebrian and Iyad Rahwan Massachusetts Institute of Technology {dubeya*,emoro,cebrian,irahwan}@mit.edu Image Virality - Thousands of images

581 views • 24 slides
ID 111x Background Topics The Game Development Process Course Materials Motivation

ID 111x Background Topics The Game Development Process Course Materials Motivation

Topics ID 111x Background Topics The Game Development Process Course Materials Motivation Mark Claypool Professor Background (Who am I?) Who Are You? Dr. Mark Claypool (professor, Mark) Year (freshman, sophomore,

352 views • 3 slides
AllJoyn Node AllJoyn Thin Client Other Proximal or Cloud Devices 72 Device System Bridge

AllJoyn Node AllJoyn Thin Client Other Proximal or Cloud Devices 72 Device System Bridge

Any questions please contact winhectpe@microsoft.com AllJoyn Node AllJoyn Thin Client Other Proximal or Cloud Devices 72 Device System Bridge AllJoyn Common Interface Others OSS Z-Wave example Bridge Adapter

1.02k views • 33 slides
Community Meeting Celebrating 10 years of housing the homeless! 2 Strengthening the CoC System

Community Meeting Celebrating 10 years of housing the homeless! 2 Strengthening the CoC System

1 2018 Community Meeting Celebrating 10 years of housing the homeless! 2 Strengthening the CoC System Arlington Landlord Partnership Mary Marshall Assisted Living Residence Domestic Violence & Sexual Assault Hotline 3 100 Homes and

263 views • 10 slides
Aural Melissa Chan (chanm3) & Josh Nazarian (jknaz) The problem: Personalized content

Aural Melissa Chan (chanm3) & Josh Nazarian (jknaz) The problem: Personalized content

Aural Melissa Chan (chanm3) & Josh Nazarian (jknaz) The problem: Personalized content discovery and current CDPs are insufficient for expanding to new genres of music. When a person discovers a new track or artist, there is no

416 views • 3 slides
Native Content Distribution through Off-Path Content Discovery A Proposal for a Downstream

Native Content Distribution through Off-Path Content Discovery A Proposal for a Downstream

Native Content Distribution through Off-Path Content Discovery A Proposal for a Downstream FIB Opportunistic Off-Path Content Discovery in Information-Centric Networks O. Ascigil, V. Sourlas, I. Psaras, G. Pavlou IEEE LANMAN 2016

431 views • 39 slides
TECHNICAL DISCOVERY Ravindra Singh - @ravindrasingh01 Shashank Merothiya - @shashtra

TECHNICAL DISCOVERY Ravindra Singh - @ravindrasingh01 Shashank Merothiya - @shashtra

TECHNICAL DISCOVERY Ravindra Singh - @ravindrasingh01 Shashank Merothiya - @shashtra www.srijan.net | business@srijan.net Proprietary & Confidential WHY WE NEED A TECHNICAL DISCOVERY? Quality Budget Which leads to... Better Delivery

770 views • 22 slides
Integrating multi-dimensional information spaces Kostas Saidis, Alex Delis {saiko,ad}@di.uoa.gr

Integrating multi-dimensional information spaces Kostas Saidis, Alex Delis {saiko,ad}@di.uoa.gr

Integrating multi-dimensional information spaces Kostas Saidis, Alex Delis {saiko,ad}@di.uoa.gr University of Athens 2 Oct. 2009, Corfu, Greece 2 nd Workshop on Very Large Digital Libraries (VLDL 2009) In conjunction with ECDL 2009 Size does

460 views • 19 slides

More recommend