20180829-NOOR

Experiment design

Designer: Iris Lohja (INRIA) (2018-06-01)

Revision of networks of ontologies with most general strengthening (4 agents; 10 runs; 10000 games; delete/replace/refine/add/addjoin/refadd)

Hypotheses: Strengthening (most general) improves recall over expansion, just like most specific strengthening

Experimental setting: Same as 20180828-NOOR replaying the same runs as 20180308-NOOR with most general strengthening.

Experiment

Experimenter: Jérôme Euzenat (INRIA) (2018-08-29)

Date: 2018-08-29

Lazy lavender hash: 759ff097b96520c12aa84f3749927f9a22022e62

Classpath: lib/lazylav/ll.jar:lib/slf4j/logback-classic-1.2.3.jar:lib/slf4j/logback-core-1.2.3.jar:.

OS: stretch

Variation of: 20180601-NOOR

Parameters: params.sh

Command line (script.sh):

. params.sh

OUTPUT=${OUTPUT}${LABEL}

for op in ${OPS}
do
  bash scripts/runexp.sh -p ${OUTPUT} -d ${DIRPREF}-${op}-${postfix} java -Dlog.level=INFO -cp ${JPATH} fr.inria.exmo.lazylavender.engine.Monitor ${OPT} ${LOADOPT} -DrevisionModality=${op} ${PARAMS}
  bash scripts/runexp.sh -p ${OUTPUT} -d ${DIRPREF}-${op}-clever-nr-${postfix} java -Dlog.level=INFO -cp ${JPATH} fr.inria.exmo.lazylavender.engine.Monitor ${OPT} ${LOADOPT} -DrevisionModality=${op} -DexpandAlignments=clever -DnonRedundancy ${PARAMS}
  bash scripts/runexp.sh -p ${OUTPUT} -d ${DIRPREF}-${op}-im80-${postfix} java -Dlog.level=INFO -cp ${JPATH} fr.inria.exmo.lazylavender.engine.Monitor ${OPT} ${LOADOPT} -DrevisionModality=${op} -DimmediateRatio=80 ${PARAMS}
  bash scripts/runexp.sh -p ${OUTPUT} -d ${DIRPREF}-${op}-clever-nr-im80-${postfix} java -Dlog.level=INFO -cp ${JPATH} fr.inria.exmo.lazylavender.engine.Monitor ${OPT} ${LOADOPT} -DrevisionModality=${op} -DexpandAlignments=clever -DnonRedundancy -DimmediateRatio=80 ${PARAMS}
  bash scripts/runexp.sh -p ${OUTPUT} -d ${DIRPREF}-${op}-clever-nr-im80-gen-${postfix} java -Dlog.level=INFO -cp ${JPATH} fr.inria.exmo.lazylavender.engine.Monitor ${OPT} ${LOADOPT} -DrevisionModality=${op} -DexpandAlignments=clever -DnonRedundancy -DimmediateRatio=80 -Dgenerative ${PARAMS}
  bash scripts/runexp.sh -p ${OUTPUT} -d ${DIRPREF}-${op}-clever-nr-im80-gen-empty-${postfix} java -Dlog.level=INFO -cp ${JPATH} fr.inria.exmo.lazylavender.engine.Monitor ${OPT} ${LOADOPT} -DrevisionModality=${op} -DexpandAlignments=clever -DnonRedundancy -DimmediateRatio=80 -Dgenerative -DstartEmpty ${PARAMS}
done

Class used: NOOEnvironment, AlignmentAdjustingAgent, AlignmentRevisionExperiment, ActionLogger, AverageLogger, Monitor

Execution environment: 24 * Intel(R) Xeon(R) CPU E5-2420 0 @ 1.90GHz with 20GB RAM / Linux ProxMox 2 / Linux 4.15.17-1-pve / Java Java(TM) SE Runtime Environment 1.8.0_151 with 4.33G max heap size

Note: These experiments are an independent rerun of Iris Lohja (INRIA)'s MSc thesis experiment 7. Actually, experiment 7 was only concerned with The tables and plots above cover these results and confirm them. Hence the analysis is conform to hers.

Input: Input required for reproducibility can be retrieved from: https://files.inria.fr/sakere/input/expeRun.zip Then unzip expeRun.zip -d input

Raw results

4-10000-add-clever-nr-im80-gen-empty-strgen.tsv 4-10000-add-clever-nr-im80-gen-empty-strgen.txt 4-10000-add-clever-nr-im80-gen-strgen.tsv 4-10000-add-clever-nr-im80-gen-strgen.txt 4-10000-add-clever-nr-im80-strgen.tsv 4-10000-add-clever-nr-im80-strgen.txt 4-10000-add-clever-nr-strgen.tsv 4-10000-add-clever-nr-strgen.txt 4-10000-add-im80-strgen.tsv 4-10000-add-im80-strgen.txt 4-10000-add-strgen.tsv 4-10000-add-strgen.txt 4-10000-addjoin-clever-nr-im80-gen-empty-strgen.tsv 4-10000-addjoin-clever-nr-im80-gen-empty-strgen.txt 4-10000-addjoin-clever-nr-im80-gen-strgen.tsv 4-10000-addjoin-clever-nr-im80-gen-strgen.txt 4-10000-addjoin-clever-nr-im80-strgen.tsv 4-10000-addjoin-clever-nr-im80-strgen.txt 4-10000-addjoin-clever-nr-strgen.tsv 4-10000-addjoin-clever-nr-strgen.txt 4-10000-addjoin-im80-strgen.tsv 4-10000-addjoin-im80-strgen.txt 4-10000-addjoin-strgen.tsv 4-10000-addjoin-strgen.txt 4-10000-delete-clever-nr-im80-gen-empty-strgen.tsv 4-10000-delete-clever-nr-im80-gen-empty-strgen.txt 4-10000-delete-clever-nr-im80-gen-strgen.tsv 4-10000-delete-clever-nr-im80-gen-strgen.txt 4-10000-delete-clever-nr-im80-strgen.tsv 4-10000-delete-clever-nr-im80-strgen.txt 4-10000-delete-clever-nr-strgen.tsv 4-10000-delete-clever-nr-strgen.txt 4-10000-delete-im80-strgen.tsv 4-10000-delete-im80-strgen.txt 4-10000-delete-strgen.tsv 4-10000-delete-strgen.txt 4-10000-refadd-clever-nr-im80-gen-empty-strgen.tsv 4-10000-refadd-clever-nr-im80-gen-empty-strgen.txt 4-10000-refadd-clever-nr-im80-gen-strgen.tsv 4-10000-refadd-clever-nr-im80-gen-strgen.txt 4-10000-refadd-clever-nr-im80-strgen.tsv 4-10000-refadd-clever-nr-im80-strgen.txt 4-10000-refadd-clever-nr-strgen.tsv 4-10000-refadd-clever-nr-strgen.txt 4-10000-refadd-im80-strgen.tsv 4-10000-refadd-im80-strgen.txt 4-10000-refadd-strgen.tsv 4-10000-refadd-strgen.txt 4-10000-refine-clever-nr-im80-gen-empty-strgen.tsv 4-10000-refine-clever-nr-im80-gen-empty-strgen.txt 4-10000-refine-clever-nr-im80-gen-strgen.tsv 4-10000-refine-clever-nr-im80-gen-strgen.txt 4-10000-refine-clever-nr-im80-strgen.tsv 4-10000-refine-clever-nr-im80-strgen.txt 4-10000-refine-clever-nr-strgen.tsv 4-10000-refine-clever-nr-strgen.txt 4-10000-refine-im80-strgen.tsv 4-10000-refine-im80-strgen.txt 4-10000-refine-strgen.tsv 4-10000-refine-strgen.txt 4-10000-replace-clever-nr-im80-gen-empty-strgen.tsv 4-10000-replace-clever-nr-im80-gen-empty-strgen.txt 4-10000-replace-clever-nr-im80-gen-strgen.tsv 4-10000-replace-clever-nr-im80-gen-strgen.txt 4-10000-replace-clever-nr-im80-strgen.tsv 4-10000-replace-clever-nr-im80-strgen.txt 4-10000-replace-clever-nr-strgen.tsv 4-10000-replace-clever-nr-strgen.txt 4-10000-replace-im80-strgen.tsv 4-10000-replace-im80-strgen.txt 4-10000-replace-strgen.tsv 4-10000-replace-strgen.txt

Result exploration

We reproduce the same plots as with (20180828-NOOR):

Analysis

Analyst: Jérôme Euzenat (INRIA) (2018-09-13)

Key points:

• Globally, the results are the same with most general and most specific (20180828-NOOR) strengthening
• The only exception is that, with delete, replace, and refine, using the generation modality, higher results are obtained with most specific. This was also visible in the results of Iris Lohja (INRIA).

Further experiments:

• Redo the last two experiments on 20000 games in order to check is 100% recall can be achieved (see 20180913-NOOR).

This file can be retrieved from URL https://sake.re/20180829-NOOR

It is possible to check out the repository by cloning https://felapton.inrialpes.fr/cakes/20180829-NOOR.git

This experiment has been transferred from its initial location at https://gforge.inria.fr (not available any more)

The original, unaltered associated zip file can be obtained from https://files.inria.fr/sakere/gforge/20180829-NOOR.zip