marianne lykke royal school of library and information science susan l. price and lois m. l....
DESCRIPTION
Using semantic components to represent and search domain-specific documents: An evaluation of indexing accuracy and consistency. Marianne Lykke Royal School of Library and Information Science Susan L. Price and Lois M. L. Delcambre Portland State University. ISKO 2010 Conference - PowerPoint PPT PresentationTRANSCRIPT
ISKO 2010 Marianne Lykke
Marianne LykkeRoyal School of Library and Information Science
Susan L. Price and Lois M. L. DelcambrePortland State University
ISKO 2010 ConferenceSapienza University of Rome, Faculty of Philosophy
February 23 - 26, 2010
Using semantic components to represent and search domain-specific documents: An evaluation of indexing accuracy and consistency
ISKO 2010 Marianne Lykke
Agenda
• Problem and motivation• Semantic component model• Research questions• Test design• Results• Conclusions
ISKO 2010 Marianne Lykke
Problem and motivationChallenges for information retrieval in domain-
specific digital libraries:• Domain-specific libraries often contain large sets
of similar documents about few topicso Important to be able to distinguish between
topical similar documents• Domain experts often have specific information
needs targeting a single “right answer”, specified by domain-specific facets. o Important to be able to limit search to domain-
specific dimensions(e.g. Leckie et al., 1996; Fagin et al., 2003; Freund et al., 2005; Hearst et al.,
2006)
ISKO 2010 Marianne Lykke
Problem and motivation
• Little time for information retrievalo Important that then relevant documents are highly
ranked and retrieved by first query• Distributed indexing, carried out by indexers with
varied degree of indexing competenceo Important to address classical indexing problems:
quality, exhaustivity, specificity, consistency (e.g. Leckie et al., 1996; Fagin et al., 2003; Freund et al., 2005; Hearst et al., 2006)
ISKO 2010 Marianne Lykke
Semantic component model • Semantic components model developed to facilitate
formulation of specific, structured queries covering the search topic exhaustively by domain-specific dimensions
• Two-level model dividing a given collection into a set of document classes, each class with an associated set of semantic components
• Based on assumptions thato Domain experts know document genres within a certain
domain: content and structure (Dillon, 1991; Orlikowski & Yates, 1994; Bishop, 1999; Vaughan & Dillon, 2005)
o Domain-specific document content and structure correspond to domain-specific information needs (Ely et al, 1999,2000; Price, Delcambre, Nielsen, 2006)
HIO 2009 Marianne Lykke
SC: General information
SC: Practical information
Document class: Clinical method
HIO 2009 Marianne Lykke
SC: General information
SC: Risk factors
After treatment
Document class: Clinical method
ISKO 2010 Marianne Lykke
Semantiske component modelDocument class Semantic component Document class Semantic component
Clinical problem General informationDiagnosisReferralTreatment
Clinical unit Function and specialtyPractical informationReferralStaff and organization
Clinical method General informationPractical informationReferralAftercareRisksExpected results
Drugs General informationPractical informationTarget groupEffectSide effects
Services General informationPractical informationReferral
Notice General informationPractical informationQualification
HIO 2009 Marianne Lykke
HIO 2009 Marianne Lykke
ISKO 2010 Marianne Lykke
Case study• sundhed.dk: Danish, national health portal• Active since 2001, 25.000 documents• Two main target groups: citizens and medical
professionals • Combination of full-text indexing and controlled,
assigned indexing: o ICPC, International Classification Primary Careo ICD-10, International Classification of Diseaseso Home-grown Citizens Thesaurus
• Large and varied group of indexers o 5 regionso Up to 250 indexers per region
• Specific target group: family doctors
ISKO 2010 Marianne Lykke
Test design• Comparative, experimental indexing study
o Baseline: keyword indexing (controlled and free terms)o Experimental: semantic component indexing
• Test persons: 16 sundhed.dk indexers (convenience sample)
• Indexing task: 12 sundhed.dk documentso 6 documents were indexed with semantic components
(SC)o 6 documents were indexed with keywords
• Random assignment of documents and indexing methods
• Training session• Evaluation measures:
o Accuracy o Consistencyo Indexing timeo Easiness
ISKO 2010 Marianne Lykke
Research questions
• Is semantic component indexing more accurate than keyword indexing compared to a reference standard?
• Is semantic component indexing more consistent than keyword indexing?
• Is semantic component indexing faster than keyword indexing?
• Is semantic component indexing easier than keyword indexing?
ISKO 2010 Marianne Lykke
AccuracyDocument Semantic component Keywords
Recall macroaverage
Precisionmacroaverage
Recallmacroaverage
Precision macroaverage
1 0.74 ± 0.37 0.89 ± 0.26 0.14 ± 0.33 0.74 ± 0.432 0.56 ± 0.33 0.61 ± 0.39 0.35 ± 0.47 0.74 ± 0.423 0.59 ± 0.45 0.72 ± 0.38 0.10 ± 0.23 0.72 ± 0.424 0.33 ± 0.29 0.72 ± 0.41 0.16 ± 0.35 0.70 ± 0.455 0.74 ± 0.39 0.68 ± 0.47 0.38 ± 0.47 0.85 ± 0.306 0.59 ± 0.13 0.81 ± 0.35 0.01 ± 0.04 0.88 ± 0.317 0.63 ± 0.39 0.79 ± 0.31 0.28 ± 0.36 0.62 ± 0.418 0.70 ± 0.31 0.93 ± 0.17 0.01 ± 0.02 0.61 ± 0.499 0.66 ± 0.33 0.76 ± 0.43 0.21 ± 0.39 0.79 ± 0.3910 0.61 ± 0.35 0.75 ± 0.26 0.25 ± 0.42 0.79 ± 0.3911 0.65 ± 0.43 0.86 ± 0.31 0.12 ± 0.27 0.80 ± 0.3612 0.63 ± 0.48 0.83 ± 0.30 0.03 ± 0.08 0.85 ± 0.34
ISKO 2010 Marianne Lykke
ConsistencyDocument Semantic
componentKeywords
Mean K ± SD(of all semantic
components in the document)
Binary K
(all vocabularies)Traditional 1 ± SD
consistency = c / (a + b – c)
1 0.46 ± 0.35 -0.08 0.05 ± 0.13
2 0.21 ± 0.16 0.001 0.18 ± 0.19
3 0.25 ± 0.30 -0.08 0.05 ± 0.11
4 0.35 ± 0.23 0.02 0.19 ± 0.30
5 0.50 ± 0.30 0.32 0.33 ± 0.23
6 0.05 ± 0.11 -0.07 0.23 ± 0.41
7 0.40 ± 0.48 0.26 0.27 ± 0.18
8 0.66 ± 0.11 -0.08 0.05 ± 0.11
9 0.04 ± 0.24 -0.02 0.09 ± 0.14
10 0.44 ± 0.16 0.27 0.29 ± 0.13
11 0.48 ± 0.41 -0.06 0.04 ± 0.09
12 0.01 ± 0.07 -0.12 0.08 ± 0.24
Time to index
0
5
10
15
20
25
30
35
40
< 2min 2 - 5 min 5 - 10 min 10-15 min > 15 min
Time to Index
Num
ber o
f Ind
exin
g In
stan
ces
Semantic Component Indexing Keyword Indexing
Easiness
0
1
2
3
4
5
6
7
8
9
10
Chooseconcept
Choosekeyword
What each SCis
Designate SC Markboundaries
Choose doc.class
Num
ber o
f Ind
exer
s
Very difficult Very easy
ISKO 2010 Marianne Lykke
Conclusions• Varied accuracy for both indexing methods, but data
suggests that semantic component indexing might be more accurate
• Indications that feasibility and easiness of indexing methods are similar
• Semantic component indexing may be preferable alternative if no appropriate controlled vocabulary is available due to short time for development and easy customization to specific document collection
• Limitations:o Small sample and a single domaino Not directly comparable evaluation measure
• Retrieval test shows improvement of document ranking of 25.6% by nDCG (normalized Discounted Cumulative Gain)
ISKO 2009 Marianne Lykke
Future research• Development of model:
o Simpler versiono Up-marking by users (social tagging)o Automatic up-markingo Up-marking by XML
• Larger scale evaluation • Evaluation in other domains
HIO 2009 Marianne Lykke
LitteraturDillon, M (1991). Reader’s model of text structures: the case of academic articles. International Journal of
Man-Machine Studies, 35. 913 – 925.Ely, J, Osheroff, J, Ebell, M, Bergus, G, Levy, B Chambliss, M & Evans, E (1999). Analysis of wquestions asked
by family doctors regarding patient care. BMJ, 310 (7206). 358 – 361.Ely, J, Osheroff, J, Gorman, P, Ebell, M, Bergus, G, Levy, B Chambliss, M, Pifer, E & Stavri, P (2000). A
taxonomy of generic clinical questions: classification study. BMJ, 321 (7278). 429 - 432.Fagin, R., Kumar, R., McCurley, K S., Novak, J., Sivakumar, D., Tomlin, J.A. & Williamson, D.P. (2003).
Searching the workplace web. In: Proceedings of the 12th International World Wide Web Conference (WWW ’03), Budapest, Hungary, May 20-24, 2003. 366-375.
Freund, L., Toms, E. & Waterhouse, J. (2005). Modeling the information behaviour of software engineers using a work-task framework. In: Grove, A (ed.) ASIS&T ’05 Proceedings of the 68th Annual meeting, Charlotte, NC, October 28-ember 2, 2005.
Hearst, M & Plaunt, C (1993). Subtopic structuring for full length document access. Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval. 59 – 69.
Leckie, G.J., Pettigrew, K.E. & Sylvain, C. (1996). Modeling the information seeking of professionals. Library Quarterly, 66 (2). 161-193.
Orlikowaki, W J & Yates, J (1994). Genre repertoire: the structuring of communicative practices in organizations. Administrative Science Quarterly, 39. 541 – 574.
Price, S, Delcambre, L & Nielsen, M L (2006). Using semantic components to express questions against document collections. Proceedings International Workshop on Health Information and Knowledge Management (HIKM 2006), Arlington (VA).
Price, S, Nielsen, M L, Delcambre, L & Vedsted, P (2007). Semantic components enhance retrieval of domain-specific documents. Proceedings of the ACM Sixteenth Conference on Information and Knowledge Management (CIKM), Lisboa, November 6 - 8, 2007.
HIO 2009 Marianne Lykke
Search term should appear in specified semantic component
Search term
HIO 2009 Marianne Lykke
Semantic component should appear in document
0
50
100
150
200
250
< 2 min 2 - 5 min 5 - 10 min 10 - 15 min > 15 min
Time to Index
Num
ber o
f Doc
umen
ts
Time to index
Indexing Type
Total Documents
Indexed (max = 96)
Mean Num. Docs Indexed
Per Indexer (max = 6)
Mean Time (min:sec)
Min Time (min:sec)
Max Time (min:sec)
Semantic Components 83 5.2 07:03 00:24 27:05
Keywords 88 5.5 05:56 01:06 31:26
Time required for indexing documents
0
1
2
3
4
5
6
7
8
9
10
For indexing documents For searching
Task type
Num
ber o
f ind
exer
s
Prefer keyword indexing About the same Prefer semantic component indexing
HIO 2009 Marianne Lykke
Research teamGeneral practice Peter VedstedMD, Ph.D.Research Unit general Practice,Århus University
Jens RubakMDPraksis.dk, Region Midt
Information and computer science
Lois Delcambre, Ph.D., ProfessorSusan Price, MD, Ph.D. studentComputer Science DepartmentPortland State University, USA
Marianne Lykke, Ph.D., Associate professorInformation Interaktion and Information ArkitectureDanmarks Bibliotekskole
sundhed.dk Vibeke Luk Frans la CourInformation specialist IT consultantsundhed.dk Autonomy
Supported by grants from the National Science Foundation, grant numbers 0514238, 0511050 and 0534762, the National Library of
Medicine Training Grant 5-T15-LM07088 and Kvalitetsudviklingsudvalget for Almen Praksis, Aarhus Amt