Presentation is loading. Please wait.

Presentation is loading. Please wait.

University of Sheffield, NLP Introduction to Text Mining Module 4: Development Lifecycle (Part 1)

Similar presentations


Presentation on theme: "University of Sheffield, NLP Introduction to Text Mining Module 4: Development Lifecycle (Part 1)"— Presentation transcript:

1 University of Sheffield, NLP Introduction to Text Mining Module 4: Development Lifecycle (Part 1)

2 University of Sheffield, NLP Aims of this module ● Turning resources into applications: SLAM ● RichNews: multimedia application and demo ● Musing: Business Intelligence application ● KIM CORE Timelines application and demo ● GATE MIMIR: Semantic search and indexing in use ● The GATE Process

3 University of Sheffield, NLP Semantic Annotation for the Life Sciences

4 University of Sheffield, NLP Aim of the application ● Life science semantic annotation is much more than generic annotation of genes, proteins and diseases in text, in order to support search ● There are many highly use-case specific annotation requirements that demand a fresh look at how we drive annotation – our processes ● Processes to support annotation ● Many use cases are ad-hoc and specialised ● Clinical research – new requirements every day ● How can we support this? What tools do we need?

5 University of Sheffield, NLP Background ● The user ● SLAM: South London and Maudsley NHS Trust ● BRC: Biomedical Research Centre ● CRIS: Case Register Information System ● February and March 2010 ● Proof of concept around MMSE ● Requirements analysis, installation, adaptation ● Since 2010 ● In production ● Cloud based system ● Further use cases

6 University of Sheffield, NLP Clinical records ● Generic entities such as anatomical location, diagnosis and drug are sometimes of interest ● But many of the enquiries we have seen are more often interested in large numbers of very specific, and ad hoc entities or events ● This example is with a UK National Biomedical Research Centre ● An example – cognitive ability as shown by the MMSE score ● Illustrates a typical (but not the only) process

7 University of Sheffield, NLP Types of IE systems ● Deep or shallow analysis ● Knowledge Engineering or Machine Learning approaches ● Supervised ● Unsupervised ● Active learning ● GATE is agnostic

8 University of Sheffield, NLP Supervised learning architecture

9 University of Sheffield, NLP Unable to assess MMSE but last one on 1/1/8 was 21/30

10 University of Sheffield, NLP Today she scored 5/30 on the MMSE

11 University of Sheffield, NLP Today she scored 5/30 on the MMSE I reviewed Mrs. ZZZZZ on 6th March

12 University of Sheffield, NLP A shallow approach ● Pre-processing, including ● morphological analysis ● “Patient was seen on” vs “I saw this patient on” ● POS tagging ● “patient was [VERB] on [DATE]” ● Dictionary lookup ● “MMSE”, “Mini mental”, “Folstein”, “AMTS” ● Coreference ● “We did an MMSE. It was 23/30”

13 University of Sheffield, NLP Annotations His MMSE was 23/30 on 15 January 2008.

14 University of Sheffield, NLP Annotations His MMSE was 23/30 on 15 January 2008. 0....5....10...15...|....|....|....|....

15 University of Sheffield, NLP Annotations His MMSE was 23/30 on 15 January 2008. 0....5....10...15...|....|....|....|....

16 University of Sheffield, NLP Annotations His MMSE was 23/30 on 15 January 2008. 0....5....10...15...|....|....|....|.... IdType 1sentence

17 University of Sheffield, NLP Annotations His MMSE was 23/30 on 15 January 2008. 0....5....10...15...|....|....|....|.... IdType 1sentence

18 University of Sheffield, NLP Annotations His MMSE was 23/30 on 15 January 2008. 0....5....10...15...|....|....|....|.... IdType 1sentence 2token 3token 4token 5token 6token 7token

19 University of Sheffield, NLP Annotations His MMSE was 23/30 on 15 January 2008. 0....5....10...15...|....|....|....|.... IdTypeStartEnd 1sentence039 2token03 3token48 4token912 5token1315 6token1516 7token1618

20 University of Sheffield, NLP Annotations His MMSE was 23/30 on 15 January 2008. 0....5....10...15...|....|....|....|.... IdTypeStartEndFeatures 1sentence039 2token03pos=PP 3token48pos=NN 4token912pos=VB 5token1315pos=CD 6token1516pos=SM 7token1618pos=CD

21 University of Sheffield, NLP Annotations His MMSE was 23/30 on 15 January 2008. 0....5....10...15...|....|....|....|.... IdTypeStartEndFeatures 1sentence039 2token03pos=PP 3token48pos=NN 4token912pos=VBroot=be 5token1315pos=CDtype=num 6token1516pos=SMtype=slash 7token1618pos=CDtype=num

22 University of Sheffield, NLP Dictionary lookup His MMSE was 23/30 on 15 January 2008. 0....5....10...15...|....|....|....|.... Month

23 University of Sheffield, NLP Dictionary lookup His MMSE was 23/30 on 15 January 2008. 0....5....10...15...|....|....|....|.... MMS E Month

24 University of Sheffield, NLP Limitations of dictionary lookup ● Dictionary lookup is designed for finding simple, regular terms and features ● False positives ● “He may get better” ● “Mother is a smoker” ● “He often burns the toast, setting off the smoke alarm” ● Cannot deal with complex patterns ● For example, recognising e-mail addresses using just a dictionary would be impossible ● Cannot deal with ambiguity ● I for Iodine, or I for me?

25 University of Sheffield, NLP Pattern matching ● The early components in a GATE pipeline produce simple annotations (Token, Sentence, Dictionary lookups) ● These annotations have features (Token kind, part of speech, major type...) ● Patterns in these annotations and features can suggest more complex information ● We use JAPE, the pattern matching language in GATE, to find these patterns

26 University of Sheffield, NLP Patterns His MMSE was 23/30 on 15 January 2008. 0....5....10...15...|....|....|....|.... MMS E Month {number}{Month}{number}

27 University of Sheffield, NLP Patterns His MMSE was 23/30 on 15 January 2008. 0....5....10...15...|....|....|....|.... MMS E Month Date

28 University of Sheffield, NLP Patterns His MMSE was 23/30 on 15 January 2008. 0....5....10...15...|....|....|....|.... MMS E Month {number}{slash}{number}

29 University of Sheffield, NLP Patterns His MMSE was 23/30 on 15 January 2008. 0....5....10...15...|....|....|....|.... MMS E Month Score

30 University of Sheffield, NLP Patterns His MMSE was 23/30 on 15 January 2008. 0....5....10...15...|....|....|....|.... MMS E Month ScoreDate

31 University of Sheffield, NLP Patterns His MMSE was 23/30 on 15 January 2008. 0....5....10...15...|....|....|....|.... MMS E Month ScoreDate {MMSE}{BE}{Score}{?}{Date}

32 University of Sheffield, NLP Patterns His MMSE was 23/30 on 15 January 2008. 0....5....10...15...|....|....|....|.... MMS E Month ScoreDate MMSE with score and date

33 University of Sheffield, NLP Patterns are general ● MMSE was 23/30 on 15 January 2009 ● Mini mental was 25/30 on 12/08/07 ● MMS was 25/30 last week ● MMSE is 25/30 today ● With adaptation ● MMSE 25 out of 30 ● Long range dependencies on dates

34 University of Sheffield, NLP MMSE pipeline

35 University of Sheffield, NLP MMSE pipeline Import CSV into GATE

36 University of Sheffield, NLP MMSE pipeline Import CSV into GATE Tokenise

37 University of Sheffield, NLP MMSE pipeline Import CSV into GATE Tokenise Sentence split

38 University of Sheffield, NLP MMSE pipeline Import CSV into GATE Tokenise Sentence split POS tag

39 University of Sheffield, NLP MMSE pipeline Import CSV into GATE Tokenise Sentence split POS tag Dictionary Lookup

40 University of Sheffield, NLP MMSE pipeline Import CSV into GATE Tokenise Sentence split POS tag Date patterns Dictionary Lookup

41 University of Sheffield, NLP MMSE pipeline Import CSV into GATE Tokenise Sentence split POS tag Date patterns Score patterns Dictionary Lookup

42 University of Sheffield, NLP MMSE pipeline Import CSV into GATE Tokenise Sentence split POS tag Date patterns Score patterns MMSE patterns Dictionary Lookup

43 University of Sheffield, NLP MMSE pipeline Import CSV into GATE Tokenise Sentence split POS tag Date patterns Score patterns MMSE patterns Dictionary Lookup Export back to CSV

44 University of Sheffield, NLP Writing patterns ● Requires training ● Depending on time and skills, domain expert may take on some rule writing ● Requirements not always clear, and users do not always understand what the technology can do ● Needs a process to support ● Domain expert manually annotates examples ● Language engineer writes rules ● Measure accuracy of rules ● Repeat

45 University of Sheffield, NLP The process as agile development ● IE system development is often linear ● Guidelines → annotate → implement ● This is similar to the “waterfall” method of software development ● Gather requirements → design → implement ● This has long been known to be problematic ● In contrast, our approach is agile

46 University of Sheffield, NLP The process as agile development ● Recognise that requirements change ● Embrace that change ● Use it to drive development ● Developers and software engineers work alongside each other to understand requirements ● Early and iterative delivery ● Feedback to collect further requirements ● Reduces cost of annotation

47 University of Sheffield, NLP Annotation - a process Gather examples

48 University of Sheffield, NLP A process Write rules Gather examples

49 University of Sheffield, NLP A process Write rules Run over Unseen documents Gather examples

50 University of Sheffield, NLP A process Write rules Run over Unseen documents Human correction Gather examples

51 University of Sheffield, NLP A process Write rules Run over Unseen documents Measure performance Human correction Gather examples

52 University of Sheffield, NLP A process Write rules Run over Unseen documents Measure performance Human correction Good enou gh? Gather examples

53 University of Sheffield, NLP A process Write rules Run over Unseen documents Measure performance Human correction Examine errors Good enou gh? No Gather examples

54 University of Sheffield, NLP

55 Annotation Diff

56 University of Sheffield, NLP A process Write rules Run over Unseen documents Measure performance Human correction Examine errors Good enou gh? No Gather examples

57 University of Sheffield, NLP A process Improve rules Run over Unseen documents Measure performance Human correction Examine errors Good enou gh? No Gather examples

58 University of Sheffield, NLP A process Improve rules Run over Unseen documents Measure performance Human correction Examine errors Good enou gh? No Yes Gather examples

59 University of Sheffield, NLP Supporting the process ● We need to train and implement the process ● We need tools to support this process ● Quality Assurance Tools ● Workflow: GATE Teamware ● Annotation pattern search: Mimir ● Coupling search and annotation: Khresmoi ● Develop a pattern and run it over text ● Human correction ● Feedback

60 University of Sheffield, NLP GATE Teamware: defining workflows

61 University of Sheffield, NLP GATE Teamware: managing projects

62 University of Sheffield, NLP 62 GATE Teamware: monitoring projects

63 University of Sheffield, NLP When is it good enough? Performance Effort 100%

64 University of Sheffield, NLP When is it good enough? □Like disease ○A small number of very common ones ○Lots of rare ones □For a straightforward use case, ○3 or 4 iterations ○plateau at around 90%

65 University of Sheffield, NLP Implications ● Ad-hoc annotation and search is as important an approach as generic annotation ● We need tools and processes to support this style of annotation ● An agile annotation process involves users, helps us to elicit their requirements, and reduces the cost of annotation


Download ppt "University of Sheffield, NLP Introduction to Text Mining Module 4: Development Lifecycle (Part 1)"

Similar presentations


Ads by Google