Presentation is loading. Please wait.

Presentation is loading. Please wait.

Classifying Semantic Relations in Bioscience Texts Barbara Rosario Marti Hearst SIMS, UC Berkeley Supported by NSF DBI-0317510.

Similar presentations


Presentation on theme: "Classifying Semantic Relations in Bioscience Texts Barbara Rosario Marti Hearst SIMS, UC Berkeley Supported by NSF DBI-0317510."— Presentation transcript:

1 Classifying Semantic Relations in Bioscience Texts Barbara Rosario Marti Hearst SIMS, UC Berkeley http://biotext.berkeley.edu Supported by NSF DBI-0317510 and a gift from Genentech

2 Adapted from Dan Klein's slides (CS 294-5) Natural Language Processing Goal: Deep understand of broad language It’d be great if machines could: Translate for us Write up our research Find out information for us Summarize But they can’t Language is ambiguous, flexible, complex, subtle

3 NLP in practice Syntactic analysis: Part-of-Speech Tagging Parsing Shallow parsing Applications: Text Classification (sort of) Question Answering Spelling Correction (sort of) Machine Translation Information retrieval Information Extraction

4 Identification and classification of small units within documents

5 Extracting Job Openings from the Web 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

6 Adapted from slide by William Cohen6 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

7 Adapted from slide by William Cohen7 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

8 Adapted from slide by William Cohen8 Information Extraction = segmentation + classification + association As 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 aka “named entity extraction” What is Information Extraction

9 Adapted from slide by William Cohen9 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 What is Information Extraction

10 Adapted from slide by William Cohen10 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

11 Adapted from Dan Klein's CS 294-5 slides Semantic Roles Define roles to be extracted Application dependent JobTitle, Employer, JobCategory, JobLocation… But we would like them to be more “general” Linguistic theories, granularity of roles Proto-agent, proto-patient Fillmore’s case theory has 9 roles (agent patient, location, experimenter, etc) Extreme view: each verb has its own set of roles Buyer, bought_thing, seller, sold_thing Middle view: roles are particular to a semantic Frame (like transaction)

12 Roles in the Biomedical domain Treatment and Disease A two-dose combined hepatitis A and B vaccine would facilitate immunization programs Proteins A caveolin - 1 - dependent coupling of PrPc to the tyrosine kinase Fyn was observed

13 Relations Person-affiliation: Affiliation(Gates, Microsoft) = CEO Location: Location(Microsoft) = Redmond Protein1 inhibits (or activates, releases) protein2

14 Problem: Which relations hold between 2 entities? TreatmentDisease Cure? Prevent? Side Effect?

15 Hepatitis Examples Cure These results suggest that con A-induced hepatitis was ameliorated by pretreatment with TJ-135. Prevent A two-dose combined hepatitis A and B vaccine would facilitate immunization programs Vague Effect of interferon on hepatitis B

16 Two tasks Relationship Extraction: Identify the several semantic relations that can occur between the entities disease and treatment in bioscience text Entity extraction: Related problem: identify such entities Much of the important, late-breaking bioscience information is found only in textual form. We need both task to extract useful information from text and to make inference

17 The Approach Data: MEDLINE abstracts and titles Collection of 4,600 biomedical journals Graphical models and Neural Network Lexical, syntactic and semantic features

18 Data and Relations MEDLINE, abstracts and titles 3662 sentences labeled Relevant: 1724 Irrelevant: 1771 e.g., “Patients were followed up for 6 months” 2 types of Entities, many instances treatment and disease 7 Relationships between these entities The labeled data is available at http://biotext.berkeley.edu

19 Semantic Relationships 810: Cure Intravenous immune globulin for recurrent spontaneous abortion 616: Only Disease Social ties and susceptibility to the common cold 166: Only Treatment Flucticasone propionate is safe in recommended doses 63: Prevent Statins for prevention of stroke

20 Semantic Relationships 36: Vague Phenylbutazone and leukemia 29: Side Effect Malignant mesodermal mixed tumor of the uterus following irradiation 4: Does NOT cure Evidence for double resistance to permethrin and malathion in head lice

21 Features Word Part of speech Phrase constituent Orthographic features ‘is number’, ‘all letters are capitalized’, ‘first letter is capitalized’ … MeSH (semantic features) Replace words, or sequences of words, with generalizations via MeSH categories Peritoneum -> Abdomen

22 Features (cont.): MeSH MeSH Tree Structures 1. Anatomy [A] 2. Organisms [B] 3. Diseases [C] 4. Chemicals and Drugs [D] 5. Analytical, Diagnostic and Therapeutic Techniques and Equipment [E] 6. Psychiatry and Psychology [F] 7. Biological Sciences [G] 8. Physical Sciences [H] 9. Anthropology, Education, Sociology and Social Phenomena [I] 10. Technology and Food and Beverages [J] 11. Humanities [K] 12. Information Science [L] 13. Persons [M] 14. Health Care [N] 15. Geographic Locations [Z]

23 Features (cont.): MeSH 1. Anatomy [A] Body Regions [A01] + Musculoskeletal System [A02] Digestive System [A03] + Respiratory System [A04] + Urogenital System [A05] + Endocrine System [A06] + Cardiovascular System [A07] + Nervous System [A08] + Sense Organs [A09] + Tissues [A10] + Cells [A11] + Fluids and Secretions [A12] + Animal Structures [A13] + Stomatognathic System [A14] (…..) Body Regions [A01] Abdomen [A01.047] Groin [A01.047.365] Inguinal Canal [A01.047.412] Peritoneum [A01.047.596] + Umbilicus [A01.047.849] Axilla [A01.133] Back [A01.176] + Breast [A01.236] + Buttocks [A01.258] Extremities [A01.378] + Head [A01.456] + Neck [A01.598] (….)

24 Models Graphical Models (static and dynamic) Neural networks

25 Graphical Models Graph theory plus probability theory Nodes are variables Edges are conditional probabilities Absence of an edge between nodes implies conditional independence between the variables of the nodes A BC P(A) P(B|A) P(C|A)  P(C|A,B)

26 Graphical Models for Role and Relation Extraction StaticDynamic

27 Graphical Models Relation node: Semantic relation (cure, prevent, none..) expressed in the sentence

28 Graphical Models Role nodes: 3 choices: treatment, disease, or none

29 Graphical Models Feature nodes (observed): word, POS, MeSH…

30 Graphical Models Joint probability distribution over relation, roles and features nodes Parameters estimated with maximum likelihood and absolute discounting smoothing Task: Find P(Role | observable features) P(Relation | observable features )

31 Neural Networks Feed-forward network (MATLAB) Same features

32 Relation extraction Results in terms of classification accuracy (with and without irrelevant sentences) 2 cases: Roles hidden Roles given

33 Relation classification: Results SentencesInputDynamic GMNN Only relevant Only features72.679.8 Roles given83.092.5 Relevant + Irrelevant Only features74.979.6 Roles given91.696.6

34 Relation classification: Results SentencesInputDynamic GMNN Only relevant Only features72.679.8 Roles given83.092.5 Relevant + Irrelevant Only features74.979.6 Roles given91.696.6

35 Role extraction Results in terms of F-measure NN: Couldn’t run it (features vectors too large) Graphical models can do role extraction and relationship classification simultaneously

36 Role Extraction: Results F-measures SentencesDynamic GM Only relevant0.73 Relevant + irrelevant 0.71

37 Features impact: Role Extraction Most important features: 1)Word, 2)MeSH Models Dynamic All features 0.71 No word 0.61 -14.1% No MeSH 0.65 -8.4% (rel. + irrel.)

38 Most important features: Roles Accuracy: GM NN All feat. + roles 82.0 96.9 All feat. – roles 74.9 79.6 -8.7% -17.8% All feat. + roles – Word 79.8 96.4 -2.8% -0.5% All feat. + roles – MeSH 84.6 97.3 3.1% 0.4% Features impact: Relation classification (rel. + irrel.)

39 Features impact: Relation classification Most realistic case: Roles not known Most important features: 1) Mesh for NN and word for GM Accuracy: GM NN All feat. – roles 74.9 79.6 All feat. - roles – Word 66.1 76.2 -11.8% -4.3% All feat. - roles – MeSH 72.5 74.1 -3.2% -6.9% (rel. + irrel.)

40 Conclusions Classification of subtle semantic relations in bioscience text Discriminative model (neural network) achieves high classification accuracy Graphical models for the simultaneous extraction of entities and relationships Importance of lexical hierarchy Future work: A new collection of disease/treatment data Different entities/relations Unsupervised learning to discover relation types

41 Thank you! Barbara Rosario Marti Hearst SIMS, UC Berkeley http://biotext.berkeley.edu

42 Additional slides

43 Several DIFFERENT Relations between the Same Types of Entities Thus differs from the problem statement of other work on relations Many find one relation which holds between two entities (many based on ACE) Agichtein and Gravano (2000), lexical patterns for location of Zelenko et al. (2002) SVM for person affiliation and organization-location Hasegawa et al. (ACL 2004) Person- Organization -> President “relation” Craven (1999, 2001) HMM for subcellular- location and disorder-association Doesn’t identify the actual relation

44 Related work: Bioscience Many hand-built rules Feldman et al. (2002), Friedman et al. (2001) Pustejovsky et al. (2002) Saric et al.; this conference

45 Slide by Chris Manning, based on slides by several others45 MUC: the 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)

46 Adapted from slide by Lucian Vlad Lita46 Message Understanding Conference (MUC) Named entity Person, Organization, Location Co-reference Clinton  President Bill Clinton Template element Perpetrator, Target Template relation Incident Multilingual

47 Adapted from slide by Lucian Vlad Lita47 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

48 Adapted from slide by Lucian Vlad Lita48 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

49 Adapted from slide by Lucian Vlad Lita49 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

50 Adapted from slide by Lucian Vlad Lita50 MUC Templates ATIVITY 1 Activity Production Company Bridgestone Sports Taiwan Co Product Iron and “metal wood” clubs Start Date January 1990

51 Graphical Models Different dependencies between the features and the relation nodes D3 D1 S1 D2 S2

52 Relation classification: Confusion Matrix Computed for the model D2, “rel + irrel.”, “only features”

53 Smoothing: absolute discounting Lower the probability of seen events by subtracting a constant from their count (ML estimate: ) The remaining probability is evenly divided by the unseen events

54 F-measures for role extraction in function of smoothing factors

55 Relation accuracies in function of smoothing factors


Download ppt "Classifying Semantic Relations in Bioscience Texts Barbara Rosario Marti Hearst SIMS, UC Berkeley Supported by NSF DBI-0317510."

Similar presentations


Ads by Google