Download presentation
Presentation is loading. Please wait.
Published byMalcolm French Modified over 9 years ago
1
1 Dr Alexiei Dingli Introduction to Web Science Harvesting the SW
2
2 Acquire Model Reuse Retrieve Publish Maintain Six challenges of the Knowledge Life Cycle
3
3 Information Extraction vs. Retrieval IRIE
4
4 A couple of approaches … Active learning to reduce annotation burden –Supervised learning –Adaptive IE –The Melita methodology Automatic annotation of large repositories –Largely unsupervised –Armadillo
5
5 Created by Carnegie Mellon School of Computer Science How to retrieve –Speaker –Location –Start Time –End Time From seminar announcements received by email The Seminar Announcements Task
6
6 Dr. Steals presents in Dean Hall at one am. becomes Dr. Steals presents in Dean Hall at one am. Seminar Announcements Example
7
7 How many documents out of the retrieved documents are relevant? How many retrieved documents are relevant out of all the relevant documents? Weighted harmonic mean of precision and recall Information Extraction Measures
8
8 If I ask the librarian to search for books on cars, there are 10 relevant books in the library and out of the 8 he found, only 4 seem to be relevant books. What is his precision, recall and f-measure? IE Measures Examples
9
9 If I ask the librarian to search for books on cars, there are 10 relevant books in the library and out of the 8 he found, only 4 seem to be relevant books. What is his precision, recall and f-measure? Precision = 4/8 = 50% Recall = 4/10 = 40% F=(2*50*40)/(50+40) = 44.4% IE Measures Answers
10
10 What is IE? –Automated ways of extracting unstructured or partially structured information from machine readable files What is AIE? –Performs tasks of traditional IE –Exploits the power of Machine Learning in order to adapt to complex domains having large amounts of domain dependent data different sub-language features different text genres –Considers important the Usability and Accessibility of the system Adaptive IE
11
11 Amilcare Tool for adaptive IE from Web-related texts –Specifically designed for document annotation –Based on (LP) 2 algorithm *Linguistic Patterns by Learning Patterns Covering algorithm based on Lazy NLP Trains with a limited amount of examples Effective on different text types –free texts –semi-structured texts –structured texts –Uses Gate and Annie for preprocessing
12
12 CMU: detailed results 1.Best overall accuracy 2.Best result on speaker field 3.No results below 75%
13
13 Gate General Architecture for Text Engineering –provides a software infrastructure for researchers and developers working in NLP Contains –Tokeniser –Gazetteers –Sentence Splitter –POS Tagger –Semantic Tagger (ANNIE) –Co-reference Resolution –Multi lingual support –Protégé –WEKA –many more exist and can be added http://www.gate.ac.uk
14
14 Current practice of annotation for knowledge identification and extraction Annotation is time consuming needs annotation by experts is complex Reduce burden of text annotation for Knowledge Management
15
15 Different Annotation Systems SGML T E X Xanadu CoNote ComMentor JotBot Third Voice Annotate.net The Annotation Engine Alembic The Gate Annotation Tool iMarkup, Yawas MnM, S-CREAM
16
16 Tool for assisted automatic annotation Uses an Adaptive IE engine to learn how to annotate (no use of rule writing for adapting the system) Users: annotates document samples IE System: –Trains while users annotate –Generalizes over seen cases –Provides preliminary annotation for new documents Performs smart ordering of documents Advantages –Annotates trivial or previously seen cases –Focuses slow/expensive user activity on unseen cases –User mainly validates extracted information Simpler & less error prone / Speeds up corpus annotation –The system learns how to improve its capabilities Melita
17
17 Methodology: Melita Bootstrap Phase Bare Text Amilcare Learns in background User Annotates
18
18 Methodology: Melita Checking Phase Bare Text Learning in background from missing tags, mistakes User Annotates Amilcare Annotates
19
19 Methodology: Melita Support Phase Bare Text Corrections used to retrain Amilcare Annotates User Corrects
20
20 Smart ordering of Documents Bare Text Tries to annotate all the documents and selects the document with partial annotations Learns annotations User Annotates
21
21 An evolving system is difficult to control Goal: –Avoiding unwelcome/unreliable suggestions –Adapting proactivity to user’s needs Method: –Allow users to tune proactivity –Monitor user reactions to suggestions Intrusivity
22
22 Methodology: Melita Ontology defining concepts Control Panel Document Panel
23
23 Results TagAmount of Texts needed for training PrecRec stime208463 etime209672 location308261 speaker1007570 30 60
24
24 Research better ways of annotating concepts in documents Optimise document ordering to maximise the discovery of new tags Allow users to edit the rules Learn to discover relationships !! Not only suggest but also corrects user annotations !! Future Work
25
25 Semantic Web requires document annotation –Current approaches Manual (e.g. Ontomat) or semi-automatic (MnM, S-Cream, Melita) BUT: –Manual/Semi-automatic annotation of Large diverse repositories Containing different and sparse information is unfeasible E.g. a Web site (So: 1,600 pages) Annotation for the Semantic Web
26
26 Information on the Web (or large repositories) is Redundant Information repeated in different superficial formats –Databases/ontologies –Structured pages (e.g. produced by databases) –Largely structured pages (bibliography pages) –Unstructured pages (free texts) Redundancy
27
27 Largely unsupervised annotation of documents –Based on Adaptive Information Extraction –Bootstrapped using redundancy of information Method –Use the structured information (easier to extract) to bootstrap learning on less structured sources ( more difficult to extract ) The Idea
28
28 –Mines web-sites to extract biblios from personal pages Tasks: Finding people’s names Finding home pages Finding personal biblio pages Extract biblio references –Sources NE Recognition (Gate’s Annie) Citeseer/Unitrier (largely incomplete biblios) Google Homepagesearch Example: Extracting Bibliographies
29
29 Mining Web sites (1) Mines the site looking for People’s names Uses Generic patterns (NER) Citeseer for likely bigrams Looks for structured lists of names Annotates known names Trains on annotations to discover the HTML structure of the page Recovers all names and hyperlinks
30
30 Experimental Results II - Sheffield People –discovering who works in the department –using Information Integration Total present in site 139 Using generic patterns + online repositories –35 correct, 5 wrong –Precision35 / 40 = 87.5 % –Recall35 / 139 = 25.2 % –F-measure 39.1 % Errors –A. Schriffin –Eugenio Moggi –Peter Gray
31
31 Experimental Results IE - Sheffield People –using Information Extraction Total present in site 139 –116 correct, 8 wrong –Precision116 / 124= 93.5 % –Recall116 / 139= 83.5 % –F-measure 88.2 % Errors –Speech and Hearing –European Network –Department Of Enhancements – Lists, Postprocessor –Position Paper –The Network –To System
32
32 Experimental Results - Edinburgh People –using Information Integration Total present in site 216 Using generic patterns + online repositories –11 correct, 2 wrong –Precision11 / 13 = 84.6 % –Recall11 / 216 = 5.1 % –F-measure 9.6 % –using Information Extraction –153 correct, 10 wrong –Precision153 / 163= 93.9 % –Recall153 / 216= 70.8 % –F-measure80.7 %
33
33 Experimental Results - Aberdeen People –using Information Integration Total present in site 70 Using generic patterns + online repositories –21 correct, 1 wrong –Precision21 / 22 = 95.5 % –Recall21 / 70 = 30.0 % –F-measure 45.7 % –using Information Extraction –63 correct, 2 wrong –Precision63 / 65= 96.9 % –Recall63 / 70 = 90.0 % –F-measure93.3 %
34
34 Mining Web sites (2) Annotates known papers Trains on annotations to discover the HTML structure Recovers co-authoring information
35
35 Experimental Results (1) Papers –discovering publications in the department –using Information Integration Total present in site 320 Using generic patterns + online repositories –151 correct, 1 wrong –Precision151 / 152 = 99 % –Recall151 / 320 = 47 % –F-measure64 % Errors - Garbage in database!! @misc{ computer-mining, author = "Department Of Computer", title = "Mining Web Sites Using Adaptive Information Extraction Alexiei Dingli and Fabio Ciravegna and David Guthrie and Yorick Wilks", url = "citeseer.nj.nec.com/582939.html" }
36
36 Experimental Results (2) Papers –using Information Extraction Total present in site 320 –214 correct, 3 wrong –Precision214 / 217 = 99 % –Recall214 / 320 = 67 % –F-measure 80 % Errors –Wrong boundaries in detection of paper names! –Names of workshops mistaken as paper names!
37
37 Task –Given the name of an artist, find all the paintings of that artist. –Created for the ArtEquAKT project Artists domain
38
38 Artists domain Evaluation ArtistMethodPrecisionRecallF-Measure CaravaggioII100.0%61%75.8% IE100.0%98.8%99.4% CezanneII100.0%27.1%42.7% IE91.0%42.6%58.0% ManetII100.0%29.7%45.8% IE100.0%40.6%57.8% MonetII100.0%14.6%25.5% IE86.3%48.5%62.1% RaphaelII100.0%59.9%74.9% IE96.5%86.4%91.2% RenoirII94.7%40.0%56.2% IE96.4%60.0%74.0%
39
39 –Providing … A URL List of services –Already wrapped (e.g. Google is in default library) –Train wrappers using examples Examples of fillers (e.g. project names) –In case … Correcting intermediate results Reactivating Armadillo when paused User Role
40
40 –Library of known services (e.g. Google, Citeseer) –Tools for training learners for other structured sources –Tools for bootstrapping learning From un/structured sources No user annotation Multi-strategy acquisition of information using redundancy –User-driven revision of results With re-learning after user correction Armadillo
41
41 Armadillo learns how to extract information –From large repositories By integrating information –from diverse and distributed resources Use: –Ontology population –Information highlighting –Document enrichment –Enhancing user experience Rationale
42
42 Data Navigation (1)
43
43 Data Navigation (2)
44
44 Data Navigation (3)
45
45 Automatic annotation services –For a specific ontology –Constantly re-indexing/re-annotating documents –Semantic search engine Effects: –No annotation in the document As today’s indexes are not stored in the documents –No legacy with the past Annotation with the latest version of the ontology Multiple annotations for a single document –Simplifies maintenance Page changed but not re-annotated IE for SW: The Vision
46
46 Questions?
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.