Presentation is loading. Please wait.

Presentation is loading. Please wait.

Controlled Language for Ontology Editing Adam Funk, Valentin Tablan, Kalina Bontcheva, Hamish Cunningham, Brian Davis, Siegfried Handschuh.

Similar presentations


Presentation on theme: "Controlled Language for Ontology Editing Adam Funk, Valentin Tablan, Kalina Bontcheva, Hamish Cunningham, Brian Davis, Siegfried Handschuh."— Presentation transcript:

1 Controlled Language for Ontology Editing Adam Funk, Valentin Tablan, Kalina Bontcheva, Hamish Cunningham, Brian Davis, Siegfried Handschuh

2 University of Sheffield NLP 2 Purpose To provide a controlled language for basic ontology-editing (and later, querying) functions:  easy to learn from examples and simple rules  relatively easy to deploy (Java, GATE)  unambiguous  compact (e.g., create many classes or instances with one sentence)  natural but grammatically lax

3 University of Sheffield NLP 3 Implementation Developed and tested in the GATE GUI, but deployable as a service GATE application using text as input to modify an ontology Based partly on standard NLP components and modified IE components, with manipulation of the GATE ontology API

4 University of Sheffield NLP 4 Implementation

5 University of Sheffield NLP 5 Syntax Quoted chunks: words in pairs of single or double quotes Keyphrases: identified and tagged by the gazetteer (is, are: Copula; is a, InstanceOf; forget, Negate) Prepositions and determiners: POS-tagged Chunks: everything else ChunkLists: one or more chunks separated by and or commas

6 University of Sheffield NLP 6 Syntax and semantics 10 syntactic rules Some have up to three semantic rules; CLOnE refers to the ontology to select one deterministically Create and delete classes, subclass relations and instances Create and instantiate datatype and object properties

7 University of Sheffield NLP 7 Syntax and semantics Rule:  ChunkList0 InstanceOf Chunk1“.” Example:  Alice Jones and Bob Smith are persons. Semantics:  If Chunk1 names a class, create instances of it.  Otherwise return an error message.

8 University of Sheffield NLP 8 Syntax and semantics Rule:  ChunkList0 Copula Chunk Prep ChunkList1 “.” Examples:  Persons are authors of documents.  Carl Pollard and Ivan Sag are authors of 'Head-Driven Phrase-Structure Grammar'. Flexible semantics:  Create a property between two classes.  Instantiate a suitable property between two instances.  Return an error message (mixed classes and instances, or a chunk that can't be dereferenced).

9 University of Sheffield NLP 9 Syntax and semantics Rule:  Negate ChunkList “.” Example:  Forget projects, journals and 'Department of Computer Science'. Semantics:  Delete each class or instance in the list.

10 University of Sheffield NLP 10 Evaluation Pre-test questionnaire to let users rate their own knowledge of ontologies and CLs Short manual on ontologies and both tools Two progressive lists of 6 simple tasks, A & B  CLOnE task list A -> Protégé B or  Protégé A then CLOnE B SUS and SUS-based questionnaires

11 University of Sheffield NLP 11 Evaluation “Repeated-measures, task-based” evaluation of CLOnE in comparison with Protégé Sample size = 15 (sufficient for SUS) Evenly split by task-tool association and tool order

12 University of Sheffield NLP 12 Evaluation 95% confidence intervals of SUS scores (SUS baseline is 65 to 70%)

13 University of Sheffield NLP 13 Evaluation: correlations

14 University of Sheffield NLP 14 Evaluation: correlations Pre-test score has no correlation with task times or SUS results. Correlations between C/P, CLOnE SUS and Protégé SUS show coherence of the set of questionnaires.

15 University of Sheffield NLP 15 Evaluation: correlations Task times for both tools are moderately correlated with each other, but not with SUS values.  Both tools are technically suitable for both tasks.  We do not claim that CLOnE is faster for simple tasks, just that users prefer it.

16 University of Sheffield NLP 16 Evaluation: sample quality Sample is sufficient for SUS evaluation Sample quality according to task-tool association, tool order, and subject type?

17 University of Sheffield NLP 17 Evaluation: sample quality SUS values for both tools were slightly lower for task list B: waning interest as the evaluation progressed Similar task times for A & B: similar effort required (in any case, the task-tool association was almost evenly split) Consistent SUS and C/P values between groups G and NG

18 University of Sheffield NLP 18 Continuing work Bugfixes, technical improvements Better error messages Support for distinct string, date and numeric datatypes Development of CLOnE-QL query language Implementation of a web-service for question-answering from an ontology

19 University of Sheffield NLP 19 Acknowledgements KnowledgeWeb (EU Network of Excellence IST-2004-507482) TAO (EU FP6 project IST-2004-026460) SEKT (EU FP6 project IST IP-2003-506826 Líon (Science Foundation Ireland project SFI/02/CE1/1131) NEPOMUK (EU project FP6-027705)

20 University of Sheffield NLP 20

21 University of Sheffield NLP 21 Evaluation summary

22 University of Sheffield NLP 22 Questionnaire CIs A data sample’s 95% confidence interval is a range 95% likely to contain the mean of the whole population that the sample represents.

23 University of Sheffield NLP 23 Correlation coefficients

24 University of Sheffield NLP 24 Correlation coefficients +1 = perfect correlation  equivalent to a straight ascending line on a scatter plot +0.7 = strong correlation 0 = no correlation  random scatter plot) -0.7 = strong negative correlation -1 = perfect negative correlation

25 University of Sheffield NLP 25 Correlation coefficients Pearson's formula assumes that the two variables are linearly meaningful; especially suitable for physical measurements Spearman's formula assumes only that they are ordinally meaningful (ranking); suitable for subjective measures such as many in social sciences

26 University of Sheffield NLP 26 Sample quality

27 University of Sheffield NLP 27 Sample quality

28 University of Sheffield NLP 28 Sample quality

29 University of Sheffield NLP 29 Sample quality

30 University of Sheffield NLP 30 Subsequent improvements Better handling of punctuation inside quoted chunks A catch-all syntactic rule that produces an error message for unparseable sentences Support for different datatypes: string, date, numeric Better unit-testing Embedded in web-service

31 University of Sheffield NLP 31 Subsequent improvements Use the features of the new GATE ontology API for more efficient dereferencing of names and RDF-friendly handling of synonyms Web-application using CLOnE-QL for question answering Better documentation of the input language


Download ppt "Controlled Language for Ontology Editing Adam Funk, Valentin Tablan, Kalina Bontcheva, Hamish Cunningham, Brian Davis, Siegfried Handschuh."

Similar presentations


Ads by Google