1. December 2005CSA3180: Information Extraction I1 CSA3180: Natural Language Processing Information Extraction 1 – Introduction Information Extraction Named Entities IE Systems MUC Finite State Machines Pattern Recognition

2. December 2005CSA3180: Information Extraction I2 Introduction Slides based on Lectures by Marti Hearst (2004) GATE Information Extraction http://www.gate.ac.uk/ie/ Sheffield Web Intelligence Technologies http://nlp.shef.ac.uk/wig/

3. December 2005CSA3180: Information Extraction I3 Classification at different granularities Text Categorization: –Classify an entire document Information Extraction (IE): –Identify and classify small units within documents Named Entity Extraction (NE): –A subset of IE –Identify and classify proper names People, locations, organizations

4. December 2005CSA3180: Information Extraction I4 Martin Baker, a person Genomics job Employers job posting form

5. December 2005CSA3180: Information Extraction I5 Aggregator Websites

6. December 2005CSA3180: Information Extraction I6 foodscience.com-Job2 JobTitle: Ice Cream Guru Employer: foodscience.com JobCategory: Travel/Hospitality JobFunction: Food Services JobLocation: Upper Midwest Contact Phone: 800-488-2611 DateExtracted: January 8, 2001 Source: www.foodscience.com/jobs_midwest.html OtherCompanyJobs: foodscience.com-Job1

7. December 2005CSA3180: Information Extraction I7 Aggregator Websites Read in many web pages from different sites Extract information into a database Screen Scraping Can then return data matching particular queries Data mining can extract meaningful insight that might not have been obvious

8. December 2005CSA3180: Information Extraction I8

9. December 2005CSA3180: Information Extraction I9 Data Mining

10. December 2005CSA3180: Information Extraction I10 IE from Research Papers

11. December 2005CSA3180: Information Extraction I11 IE from Commercial Websites

12. December 2005CSA3180: Information Extraction I12 What is Information Extraction? Filling slots in a database from sub-segments of text. As a task: October 14, 2002, 4:00 a.m. PT For years, Microsoft Corporation CEO Bill Gates railed against the economic philosophy of open-source software with Orwellian fervor, denouncing its communal licensing as a "cancer" that stifled technological innovation. Today, Microsoft claims to "love" the open-source concept, by which software code is made public to encourage improvement and development by outside programmers. Gates himself says Microsoft will gladly disclose its crown jewels--the coveted code behind the Windows operating system--to select customers. "We can be open source. We love the concept of shared source," said Bill Veghte, a Microsoft VP. "That's a super- important shift for us in terms of code access.“ Richard Stallman, founder of the Free Software Foundation, countered saying… NAME TITLE ORGANIZATION

13. December 2005CSA3180: Information Extraction I13 What is Information Extraction? Filling slots in a database from sub-segments of text. As a task: October 14, 2002, 4:00 a.m. PT For years, Microsoft Corporation CEO Bill Gates railed against the economic philosophy of open-source software with Orwellian fervor, denouncing its communal licensing as a "cancer" that stifled technological innovation. Today, Microsoft claims to "love" the open-source concept, by which software code is made public to encourage improvement and development by outside programmers. Gates himself says Microsoft will gladly disclose its crown jewels--the coveted code behind the Windows operating system--to select customers. "We can be open source. We love the concept of shared source," said Bill Veghte, a Microsoft VP. "That's a super-important shift for us in terms of code access.“ Richard Stallman, founder of the Free Software Foundation, countered saying… NAME TITLE ORGANIZATION Bill Gates CEO Microsoft Bill Veghte VP Microsoft Richard Stallman founder Free Soft.. IE

14. December 2005CSA3180: Information Extraction I14 What is Information Extraction? Information Extraction = segmentation + classification + association As a family of techniques: Microsoft Corporation CEO Bill Gates Microsoft Gates Microsoft Bill Veghte Microsoft VP Richard Stallman founder Free Software Foundation aka “named entity extraction” October 14, 2002, 4:00 a.m. PT For years, Microsoft Corporation CEO Bill Gates railed against the economic philosophy of open-source software with Orwellian fervor, denouncing its communal licensing as a "cancer" that stifled technological innovation. Today, Microsoft claims to "love" the open-source concept, by which software code is made public to encourage improvement and development by outside programmers. Gates himself says Microsoft will gladly disclose its crown jewels--the coveted code behind the Windows operating system--to select customers. "We can be open source. We love the concept of shared source," said Bill Veghte, a Microsoft VP. "That's a super-important shift for us in terms of code access.“ Richard Stallman, founder of the Free Software Foundation, countered saying…

15. December 2005CSA3180: Information Extraction I15 What is Information Extraction? Information Extraction = segmentation + classification + association A family of techniques: October 14, 2002, 4:00 a.m. PT For years, Microsoft Corporation CEO Bill Gates railed against the economic philosophy of open-source software with Orwellian fervor, denouncing its communal licensing as a "cancer" that stifled technological innovation. Today, Microsoft claims to "love" the open-source concept, by which software code is made public to encourage improvement and development by outside programmers. Gates himself says Microsoft will gladly disclose its crown jewels--the coveted code behind the Windows operating system--to select customers. "We can be open source. We love the concept of shared source," said Bill Veghte, a Microsoft VP. "That's a super- important shift for us in terms of code access.“ Richard Stallman, founder of the Free Software Foundation, countered saying… Microsoft Corporation CEO Bill Gates Microsoft Gates Microsoft Bill Veghte Microsoft VP Richard Stallman founder Free Software Foundation

16. December 2005CSA3180: Information Extraction I16 What is Information Extraction? Information Extraction = segmentation + classification + association A family of techniques: October 14, 2002, 4:00 a.m. PT For years, Microsoft Corporation CEO Bill Gates railed against the economic philosophy of open-source software with Orwellian fervor, denouncing its communal licensing as a "cancer" that stifled technological innovation. Today, Microsoft claims to "love" the open-source concept, by which software code is made public to encourage improvement and development by outside programmers. Gates himself says Microsoft will gladly disclose its crown jewels--the coveted code behind the Windows operating system--to select customers. "We can be open source. We love the concept of shared source," said Bill Veghte, a Microsoft VP. "That's a super-important shift for us in terms of code access.“ Richard Stallman, founder of the Free Software Foundation, countered saying… Microsoft Corporation CEO Bill Gates Microsoft Gates Microsoft Bill Veghte Microsoft VP Richard Stallman founder Free Software Foundation

17. December 2005CSA3180: Information Extraction I17 IE in Context Create ontology Segment Classify Associate Cluster Load DB Spider Query, Search Data mine IE Document collection Database Filter by relevance Label training data Train extraction models

18. December 2005CSA3180: Information Extraction I18 IE in Context: Formatting Grammatical sentences and some formatting & links Text paragraphs without formatting Astro Teller is the CEO and co-founder of BodyMedia. Astro holds a Ph.D. in Artificial Intelligence from Carnegie Mellon University, where he was inducted as a national Hertz fellow. His M.S. in symbolic and heuristic computation and B.S. in computer science are from Stanford University. His work in science, literature and business has appeared in international media from the New York Times to CNN to NPR.

19. December 2005CSA3180: Information Extraction I19 IE in Context: Formatting Non-grammatical snippets, rich formatting & links Tables

20. December 2005CSA3180: Information Extraction I20 IE in Context: Coverage Web site specific Amazon.com Book Pages Formatting Genre specific Resumes Layout

21. December 2005CSA3180: Information Extraction I21 IE in Context: Coverage Wide, non-specific University Names Language

22. December 2005CSA3180: Information Extraction I22 IE in Context: Complexity Closed set He was born in Alabama… The big Wyoming sky… U.S. states Regular set Phone: (413) 545-1323 The CALD main office can be reached at 412-268-1299 U.S. phone numbers Complex pattern University of Arkansas P.O. Box 140 Hope, AR 71802 U.S. postal addresses Headquarters: 1128 Main Street, 4th Floor Cincinnati, Ohio 45210 …was among the six houses sold by Hope Feldman that year. Ambiguous patterns, needing context and many sources of evidence Person names Pawel Opalinski, Software Engineer at WhizBang Labs.

23. December 2005CSA3180: Information Extraction I23 IE in Context: Single Field/Record Single entity Person: Jack Welch Binary relationship Relation: Person-Title Person: Jack Welch Title: CEO N-ary record “Named entity” extraction Jack Welch will retire as CEO of General Electric tomorrow. The top role at the Connecticut company will be filled by Jeffrey Immelt. Relation: Company-Location Company: General Electric Location: Connecticut Relation: Succession Company: General Electric Title: CEO Out: Jack Welsh In: Jeffrey Immelt Person: Jeffrey Immelt Location: Connecticut

24. December 2005CSA3180: Information Extraction I24 State of the Art Named entity recognition from newswire text –Person, Location, Organization, … –F1 in high 80’s or low- to mid-90’s Binary relation extraction –Contained-in (Location1, Location2) Member-of (Person1, Organization1) –F1 in 60’s or 70’s or 80’s Web site structure recognition –Extremely accurate performance obtainable –Human effort (~10min?) required on each site

25. December 2005CSA3180: Information Extraction I25 IE Generations Hand-Built Systems – Knowledge Engineering [1980s– ] –Rules written by hand –Require experts who understand both the systems and the domain –Iterative guess-test-tweak-repeat cycle Automatic, Trainable Rule-Extraction Systems [1990s– ] –Rules discovered automatically using predefined templates, using automated rule learners –Require huge, labeled corpora (effort is just moved!) Statistical Models [1997 – ] –Use machine learning to learn which features indicate boundaries and types of entities. –Learning usually supervised; may be partially unsupervised

26. December 2005CSA3180: Information Extraction I26 IE Techniques Lexicons Alabama Alaska … Wisconsin Wyoming Abraham Lincoln was born in Kentucky. member? Classify Pre-segmented Candidates Abraham Lincoln was born in Kentucky. Classifier which class? Sliding Window Abraham Lincoln was born in Kentucky. Classifier which class? Try alternate window sizes: Boundary Models Abraham Lincoln was born in Kentucky. Classifier which class? BEGINENDBEGINEND BEGIN Context Free Grammars Abraham Lincoln was born in Kentucky. NNPVPNPVNNP NP PP VP S Most likely parse? Finite State Machines Abraham Lincoln was born in Kentucky. Most likely state sequence?

27. December 2005CSA3180: Information Extraction I27 Trainable IE Systems Pros Annotating text is simpler & faster than writing rules. Domain independent Domain experts don’t need to be linguists or programers. Learning algorithms ensure full coverage of examples. Cons Hand-crafted systems perform better, especially at hard tasks. (but this is changing) Training data might be expensive to acquire May need huge amount of training data Hand-writing rules isn’t that hard!!

28. December 2005CSA3180: Information Extraction I28 MUC: Genesis of IE DARPA funded significant efforts in IE in the early to mid 1990’s. Message Understanding Conference (MUC) was an annual event/competition where results were presented. Focused on extracting information from news articles: –Terrorist events –Industrial joint ventures –Company management changes Information extraction of particular interest to the intelligence community (CIA, NSA). (Note: early ’90’s)

29. December 2005CSA3180: Information Extraction I29 MUC Named entity Person, Organization, Location Co-reference Clinton  President Bill Clinton Template element Perpetrator, Target Template relation Incident Multilingual

30. December 2005CSA3180: Information Extraction I30 MUC Typical Text Bridgestone Sports Co. said Friday it has set up a joint venture in Taiwan with a local concern and a Japanese trading house to produce golf clubs to be shipped to Japan. The joint venture, Bridgestone Sports Taiwan Co., capitalized at 20 million new Taiwan dollars, will start production of 20,000 iron and “metal wood” clubs a month

31. December 2005CSA3180: Information Extraction I31 MUC Typical Text Bridgestone Sports Co. said Friday it has set up a joint venture in Taiwan with a local concern and a Japanese trading house to produce golf clubs to be shipped to Japan. The joint venture, Bridgestone Sports Taiwan Co., capitalized at 20 million new Taiwan dollars, will start production of 20,000 iron and “metal wood” clubs a month

32. December 2005CSA3180: Information Extraction I32 MUC Templates Relationship tie-up Entities: Bridgestone Sports Co, a local concern, a Japanese trading house Joint venture company Bridgestone Sports Taiwan Co Activity ACTIVITY 1 Amount NT$2,000,000

33. December 2005CSA3180: Information Extraction I33 MUC Templates ATIVITY 1 –Activity Production –Company Bridgestone Sports Taiwan Co –Product Iron and “metal wood” clubs –Start Date January 1990

34. December 2005CSA3180: Information Extraction I34 Bridgestone Sports Co. said Friday it had set up a joint venture in Taiwan with a local concern and a Japanese trading house to produce golf clubs to be supplied to Japan. The joint venture, Bridgestone Sports Taiwan Co., capitalized at 20 million new Taiwan dollars, will start production in January 1990 with production of 20,000 iron and “metal wood” clubs a month. TIE-UP-1 Relationship: TIE-UP Entities: “Bridgestone Sport Co.” “a local concern” “a Japanese trading house” Joint Venture Company: “Bridgestone Sports Taiwan Co.” Activity: ACTIVITY-1 Amount: NT$200000000 Example from Fastus (1993)

35. December 2005CSA3180: Information Extraction I35 Bridgestone Sports Co. said Friday it had set up a joint venture in Taiwan with a local concern and a Japanese trading house to produce golf clubs to be supplied to Japan. The joint venture, Bridgestone Sports Taiwan Co., capitalized at 20 million new Taiwan dollars, will start production in January 1990 with production of 20,000 iron and “metal wood” clubs a month. TIE-UP-1 Relationship: TIE-UP Entities: “Bridgestone Sport Co.” “a local concern” “a Japanese trading house” Joint Venture Company: “Bridgestone Sports Taiwan Co.” Activity: ACTIVITY-1 Amount: NT$200000000 ACTIVITY-1 Activity: PRODUCTION Company: “Bridgestone Sports Taiwan Co.” Product: “iron and ‘metal wood’ clubs” Start Date: DURING: January 1990

36. December 2005CSA3180: Information Extraction I36 Bridgestone Sports Co. said Friday it had set up a joint venture in Taiwan with a local concern and a Japanese trading house to produce golf clubs to be supplied to Japan. The joint venture, Bridgestone Sports Taiwan Co., capitalized at 20 million new Taiwan dollars, will start production in January 1990 with production of 20,000 iron and “metal wood” clubs a month. TIE-UP-1 Relationship: TIE-UP Entities: “Bridgestone Sport Co.” “a local concern” “a Japanese trading house” Joint Venture Company: “Bridgestone Sports Taiwan Co.” Activity: ACTIVITY-1 Amount: NT$200000000 ACTIVITY-1 Activity: PRODUCTION Company: “Bridgestone Sports Taiwan Co.” Product: “iron and ‘metal wood’ clubs” Start Date: DURING: January 1990

37. December 2005CSA3180: Information Extraction I37 Evaluating IE Accuracy Always evaluate performance on independent, manually- annotated test data not used during system development. Measure for each test document: –Total number of correct extractions in the solution template: N –Total number of slot/value pairs extracted by the system: E –Number of extracted slot/value pairs that are correct (i.e. in the solution template): C Compute average value of metrics adapted from IR: –Recall = C/N –Precision = C/E –F-Measure = Harmonic mean of recall and precision

38. December 2005CSA3180: Information Extraction I38 Results for 1997 NE – named entity recognition CO – coreference resolution TE – template element construction TR – template relation construction ST – scenario template production

39. December 2005CSA3180: Information Extraction I39 Finite State Transducers for IE Basic method for extracting relevant information IE systems generally use a collection of specialized FSTs Company Name detection Person Name detection Relationship detection

40. December 2005CSA3180: Information Extraction I40 Equivalent Representations Finite automata Regular expressions Regular languages Each can describe the others Theorem: For every regular expression, there is a deterministic finite-state automaton that defines the same language, and vice versa.

41. December 2005CSA3180: Information Extraction I41 Finite State Automata Graphs The start state An accepting state A transition a A state

42. December 2005CSA3180: Information Extraction I42 Finite Automata A FA is similar to a compiler in that: –A compiler recognizes legal programs in some (source) language. –A finite-state machine recognizes legal strings in some language. Example: Programming Language Identifiers –sequences of one or more letters or digits, starting with a letter: letter letter | digit S A

43. December 2005CSA3180: Information Extraction I43 Finite Automata Transition s 1  a s 2 Is read In state s 1 on input “a” go to state s 2 If end of input –If in accepting state => accept –Otherwise => reject If no transition possible (got stuck) => reject FSA = Finite State Automata

44. December 2005CSA3180: Information Extraction I44 Finite State Automata Language The language defined by a FSA is the set of strings accepted by the FSA. –in the language of the FSM shown below: x, tmp2, XyZzy, position27. –not in the language of the FSM shown below: 123, a?, 13apples. letter letter | digit S A

45. December 2005CSA3180: Information Extraction I45 Example: Integer Literals FSA that accepts integer literals with an optional + or - sign: Note the two different edges from S to A (+|-)?[0-9]+ + digit S B A -

46. December 2005CSA3180: Information Extraction I46 Finite State Automata Example FSA that accepts three letter English words that begin with p and end with d or t. Here I use the convenient notation of making the state name match the input that has to be on the edge leading to that state. p t a o u d i

47. December 2005CSA3180: Information Extraction I47 Formal Definition A finite automaton is a 5-tuple ( , Q, , q, F) where: –An input alphabet  –A set of states Q –A start state q –A set of accepting states F  Q –  is the state transition function: Q x   Q (i.e., encodes transitions state  input state)

48. December 2005CSA3180: Information Extraction I48 FSA Implementation A table-driven approach: table: –one row for each state in the machine, and –one column for each possible character. Table[j][k] –which state to go to from state j on character k, –an empty entry corresponds to the machine getting stuck. Note: when you use the re package in python, it converts your regex’s into efficient FSMs

49. December 2005CSA3180: Information Extraction I49 Terminology FSA: Finite State Automaton FSM: Finite State Machine –FSA, FSM used interchangibly FST: Finite State Transducer –The same as FSA, except each transition produces output

50. December 2005CSA3180: Information Extraction I50 FSTs for IE FSTs are often compiled from regular expressions Probabilistic (weighted) FSTs FSTs mean different things to different IE approaches: –Based on lexical items (words) –Based on statistical language models –Based on deep syntactic/semantic analysis Several FSTs or a more complex FST can be used to find one type of information (e.g. company names)

51. December 2005CSA3180: Information Extraction I51 FSTs for IE Frodo Baggins works for Hobbit Factory, Inc. Text Analyzer: Frodo – Proper Name Baggins – Proper Name works – Verb for – Prep Hobbit – UnknownCap Factory – NounCap Inc– CompAbbr

52. December 2005CSA3180: Information Extraction I52 FSTs for IE Frodo Baggins works for Hobbit Factory, Inc. A regular expression for finding company names: “some capitalized words, maybe a comma, then a company abbreviation indicator” CompanyName = (ProperName | SomeCap)+ Comma? CompAbbr

53. December 2005CSA3180: Information Extraction I53 FSTs for IE Frodo Baggins works for Hobbit Factory, Inc. ProperName works for CompanyName.

54. December 2005CSA3180: Information Extraction I54 FSTs for IE Frodo Baggins works for Hobbit Factory, Inc. 123 4 word (CAP | PN) CAB comma CAB word CAP = SomeCap, CAB = CompAbbr, PN = ProperName,  = empty string Company Name Detection FSA

55. December 2005CSA3180: Information Extraction I55 FSTs for IE Frodo Baggins works for Hobbit Factory, Inc. 123 4 word  word (CAP | PN)   CAB  CN comma   CAB  CN word  word CAP = SomeCap, CAB = CompAbbr, PN = ProperName,  = empty string, CN = CompanyName Company Name Detection FST

56. December 2005CSA3180: Information Extraction I56 FSMs for Pattern Recognition Use regex’s at a higher level of description for pattern recognition Determining which person holds what office in what organization –[person], [office] of [org] Vuk Draskovic, leader of the Serbian Renewal Movement –[org] (named, appointed, etc.) [person] P [office] NATO appointed Wesley Clark as Commander in Chief Determining where an organization is located –[org] in [loc] NATO headquarters in Brussels –[org] [loc] (division, branch, headquarters, etc.) KFOR Kosovo headquarters

57. December 2005CSA3180: Information Extraction I57 FASTUS Successful early IE system (1993) Built on Finite State Automata (FSA) transductions

58. December 2005CSA3180: Information Extraction I58 1.Complex Words: Recognition of multi-words and proper names 2.Basic Phrases: Simple noun groups, verb groups and particles 3.Complex phrases: Complex noun groups and verb groups 4.Domain Events: Patterns for events of interest to the application Basic templates are to be built. 5. Merging Structures: Templates from different parts of the texts are merged if they provide information about the same entity or event. set up new Taiwan dollars a Japanese trading house had set up production of 20, 000 iron and metal wood clubs [company] [set up] [Joint-Venture] with [company]