Loading README.md +1 −1 Original line number Original line Diff line number Diff line Loading @@ -13,7 +13,7 @@ execute the following commands: ``` sh ``` sh $ git add task/user/result.tsv # track your new result with Git $ git add task/user/result.tsv # track your new result with Git $ pip install -r requirements.txt # run the evaluation $ pip install -r requirements.txt # run the evaluation $ python -m evaluate $ python -m scripts.evaluate $ git add -u # add the updated leaderboard to Git $ git add -u # add the updated leaderboard to Git $ git push # publish your new result and the updated leaderboard $ git push # publish your new result and the updated leaderboard ``` ``` Loading __init__.py 0 → 100644 +0 −0 Empty file added. scripts/__init__.py 0 → 100644 +0 −0 Empty file added. evaluate.py→scripts/evaluate.py +1 −1 Original line number Original line Diff line number Diff line Loading @@ -9,7 +9,7 @@ from pytrec_eval import RelevanceEvaluator, parse_qrel, parse_run RELEVANCE_JUDGEMENTS = { RELEVANCE_JUDGEMENTS = { 'task1': 'qrel.V0.1.tsv', 'task1': 'qrel.V0.1-test.tsv', 'ntcir-11-math-2-main': 'NTCIR11_Math-qrels-test.dat', 'ntcir-11-math-2-main': 'NTCIR11_Math-qrels-test.dat', 'ntcir-12-mathir-arxiv-main': 'NTCIR12_Math-qrels_agg-test.dat', 'ntcir-12-mathir-arxiv-main': 'NTCIR12_Math-qrels_agg-test.dat', } } Loading task1/README.md +4 −4 Original line number Original line Diff line number Diff line Loading @@ -2,7 +2,7 @@ This table contains the best result for every user. | nDCG | User | Result name | | nDCG | User | Result name | |:-----|------|:------------| |:-----|------|:------------| | 0.5181 | xstefan3 | example, key1=value1, key2=value2, etc | | 0.5843 | xstefan3 | example, key1=value1, key2=value2, etc | | 0.5181 | xnovot32 | example, key1=value1, key2=value2, etc | | 0.5843 | xnovot32 | example, key1=value1, key2=value2, etc | | 0.5181 | xluptak4 | example, key1=value1, key2=value2, etc | | 0.5843 | xluptak4 | example, key1=value1, key2=value2, etc | | 0.5181 | ayetiran | example, key1=value1, key2=value2, etc | | 0.5843 | ayetiran | example, key1=value1, key2=value2, etc | Loading
README.md +1 −1 Original line number Original line Diff line number Diff line Loading @@ -13,7 +13,7 @@ execute the following commands: ``` sh ``` sh $ git add task/user/result.tsv # track your new result with Git $ git add task/user/result.tsv # track your new result with Git $ pip install -r requirements.txt # run the evaluation $ pip install -r requirements.txt # run the evaluation $ python -m evaluate $ python -m scripts.evaluate $ git add -u # add the updated leaderboard to Git $ git add -u # add the updated leaderboard to Git $ git push # publish your new result and the updated leaderboard $ git push # publish your new result and the updated leaderboard ``` ``` Loading
evaluate.py→scripts/evaluate.py +1 −1 Original line number Original line Diff line number Diff line Loading @@ -9,7 +9,7 @@ from pytrec_eval import RelevanceEvaluator, parse_qrel, parse_run RELEVANCE_JUDGEMENTS = { RELEVANCE_JUDGEMENTS = { 'task1': 'qrel.V0.1.tsv', 'task1': 'qrel.V0.1-test.tsv', 'ntcir-11-math-2-main': 'NTCIR11_Math-qrels-test.dat', 'ntcir-11-math-2-main': 'NTCIR11_Math-qrels-test.dat', 'ntcir-12-mathir-arxiv-main': 'NTCIR12_Math-qrels_agg-test.dat', 'ntcir-12-mathir-arxiv-main': 'NTCIR12_Math-qrels_agg-test.dat', } } Loading
task1/README.md +4 −4 Original line number Original line Diff line number Diff line Loading @@ -2,7 +2,7 @@ This table contains the best result for every user. | nDCG | User | Result name | | nDCG | User | Result name | |:-----|------|:------------| |:-----|------|:------------| | 0.5181 | xstefan3 | example, key1=value1, key2=value2, etc | | 0.5843 | xstefan3 | example, key1=value1, key2=value2, etc | | 0.5181 | xnovot32 | example, key1=value1, key2=value2, etc | | 0.5843 | xnovot32 | example, key1=value1, key2=value2, etc | | 0.5181 | xluptak4 | example, key1=value1, key2=value2, etc | | 0.5843 | xluptak4 | example, key1=value1, key2=value2, etc | | 0.5181 | ayetiran | example, key1=value1, key2=value2, etc | | 0.5843 | ayetiran | example, key1=value1, key2=value2, etc |
