Commit ba39cee3 authored by Swaroop Vattam's avatar Swaroop Vattam

synced more datasets

parent 9cc7cd9d
Pipeline #22 passed with stage
in 55 minutes and 16 seconds
This diff is collapsed.
{
"about": {
"datasetID": "32_wikiqa_MIN_METADATA_dataset",
"datasetName": "WikiQA: A Challenge Dataset for Open-Domain Question Answering",
"description": "WikiQA dataset is a publicly available set of question and sentence (QS) pairs, collected and annotated for research on open-domain question answering",
"citation": "\n@inproceedings{wikiqa-a-challenge-dataset-for-open-domain-question-answering,\nauthor = {Yang, Yi and Yih, Scott Wen-tau and Meek, Chris},\ntitle = {WikiQA: A Challenge Dataset for Open-Domain Question Answering},\nyear = {2015},\nmonth = {September},\npublisher = {ACL – Association for Computational Linguistics},\nurl = {https://www.microsoft.com/en-us/research/publication/wikiqa-a-challenge-dataset-for-open-domain-question-answering/},\n}\n",
"license": "MICROSOFT RESEARCH DATA LICENSE AGREEMENT",
"source": "Microsoft",
"sourceURI": "https://www.microsoft.com/en-us/research/publication/wikiqa-a-challenge-dataset-for-open-domain-question-answering/#",
"approximateSize": "5 MB",
"datasetSchemaVersion": "4.0.0",
"redacted": false,
"datasetVersion": "4.0.0",
"digest": "ba73e9df96194f478296feddc96685cd03b72f37f91070766bbf1ddfc216fc67"
},
"dataResources": [
{
"resID": "0",
"resPath": "tables/questions.csv",
"resType": "table",
"resFormat": {
"text/csv": [
"csv"
]
},
"columns": [
{
"colIndex": 0,
"colName": "qIndex",
"colType": "integer",
"role": [
"index"
]
}
]
},
{
"resID": "1",
"resPath": "tables/sentences.csv",
"resType": "table",
"resFormat": {
"text/csv": [
"csv"
]
},
"columns": [
{
"colIndex": 0,
"colName": "sIndex",
"colType": "integer",
"role": [
"index"
]
}
]
},
{
"resID": "2",
"resPath": "tables/vocabulary.csv",
"resType": "table",
"resFormat": {
"text/csv": [
"csv"
]
},
"columns": [
{
"colIndex": 0,
"colName": "index",
"colType": "integer",
"role": [
"index"
]
}
]
},
{
"resID": "learningData",
"resPath": "tables/learningData.csv",
"resType": "table",
"resFormat": {
"text/csv": [
"csv"
]
},
"columns": [
{
"colIndex": 0,
"colName": "d3mIndex",
"colType": "integer",
"role": [
"index"
]
},
{
"colIndex": 1,
"colName": "qIndex",
"colType": "integer",
"role": [
"attribute"
],
"refersTo": {
"resID": "0",
"resObject": {
"columnName": "qIndex"
}
}
},
{
"colIndex": 2,
"colName": "sIndex",
"colType": "integer",
"role": [
"attribute"
],
"refersTo": {
"resID": "1",
"resObject": {
"columnName": "sIndex"
}
}
}
]
}
]
}
\ No newline at end of file
This source diff could not be displayed because it is stored in LFS. You can view the blob instead.
This source diff could not be displayed because it is stored in LFS. You can view the blob instead.
This source diff could not be displayed because it is stored in LFS. You can view the blob instead.
This source diff could not be displayed because it is stored in LFS. You can view the blob instead.
This source diff could not be displayed because it is stored in LFS. You can view the blob instead.
{
"about": {
"problemID": "32_wikiqa_MIN_METADATA_problem",
"problemName": "WikiQA: A Challenge Dataset for Open-Domain Question Answering",
"problemDescription": "Given a question sentence and a candidate sentence, the task is to predict if the candidate is an answer sentence or not.",
"problemSchemaVersion": "4.0.0",
"problemVersion": "4.0.0",
"taskKeywords": [
"classification",
"binary",
"text",
"relational"
]
},
"inputs": {
"data": [
{
"datasetID": "32_wikiqa_MIN_METADATA_dataset",
"targets": [
{
"targetIndex": 0,
"resID": "learningData",
"colIndex": 3,
"colName": "isAnswer"
}
]
}
],
"dataSplits": {
"method": "holdOut",
"testSize": 0.3,
"numRepeats": 0,
"splitsFile": "dataSplits.csv",
"datasetViewMaps": {
"train": [
{
"from": "32_wikiqa_MIN_METADATA_dataset",
"to": "32_wikiqa_MIN_METADATA_dataset_TRAIN"
}
],
"test": [
{
"from": "32_wikiqa_MIN_METADATA_dataset",
"to": "32_wikiqa_MIN_METADATA_dataset_TEST"
}
],
"score": [
{
"from": "32_wikiqa_MIN_METADATA_dataset",
"to": "32_wikiqa_MIN_METADATA_dataset_SCORE"
}
]
}
},
"performanceMetrics": [
{
"metric": "f1",
"posLabel": "1"
}
]
},
"expectedOutputs": {
"predictionsFile": "predictions.csv"
}
}
\ No newline at end of file
{
"about": {
"datasetID": "32_wikiqa_MIN_METADATA_dataset_SCORE",
"datasetName": "NULL",
"license": "MICROSOFT RESEARCH DATA LICENSE AGREEMENT",
"approximateSize": "5 MB",
"datasetSchemaVersion": "4.0.0",
"redacted": true,
"datasetVersion": "4.0.0",
"digest": "32a1328c816f06ab88c96a503a40dd7b5d27cb5f9c7ec8355ad84ca95592b6a2"
},
"dataResources": [
{
"resID": "0",
"resPath": "tables/questions.csv",
"resType": "table",
"resFormat": {
"text/csv": [
"csv"
]
},
"columns": [
{
"colIndex": 0,
"colName": "qIndex",
"colType": "integer",
"role": [
"index"
]
}
]
},
{
"resID": "1",
"resPath": "tables/sentences.csv",
"resType": "table",
"resFormat": {
"text/csv": [
"csv"
]
},
"columns": [
{
"colIndex": 0,
"colName": "sIndex",
"colType": "integer",
"role": [
"index"
]
}
]
},
{
"resID": "2",
"resPath": "tables/vocabulary.csv",
"resType": "table",
"resFormat": {
"text/csv": [
"csv"
]
},
"columns": [
{
"colIndex": 0,
"colName": "index",
"colType": "integer",
"role": [
"index"
]
}
]
},
{
"resID": "learningData",
"resPath": "tables/learningData.csv",
"resType": "table",
"resFormat": {
"text/csv": [
"csv"
]
},
"columns": [
{
"colIndex": 0,
"colName": "d3mIndex",
"colType": "integer",
"role": [
"index"
]
},
{
"colIndex": 1,
"colName": "qIndex",
"colType": "integer",
"role": [
"attribute"
],
"refersTo": {
"resID": "0",
"resObject": {
"columnName": "qIndex"
}
}
},
{
"colIndex": 2,
"colName": "sIndex",
"colType": "integer",
"role": [
"attribute"
],
"refersTo": {
"resID": "1",
"resObject": {
"columnName": "sIndex"
}
}
}
]
}
]
}
\ No newline at end of file
This source diff could not be displayed because it is stored in LFS. You can view the blob instead.
This source diff could not be displayed because it is stored in LFS. You can view the blob instead.
This source diff could not be displayed because it is stored in LFS. You can view the blob instead.
This source diff could not be displayed because it is stored in LFS. You can view the blob instead.
{
"about": {
"problemID": "32_wikiqa_MIN_METADATA_problem",
"problemName": "WikiQA: A Challenge Dataset for Open-Domain Question Answering",
"problemDescription": "Given a question sentence and a candidate sentence, the task is to predict if the candidate is an answer sentence or not.",
"problemSchemaVersion": "4.0.0",
"problemVersion": "4.0.0",
"taskKeywords": [
"classification",
"binary",
"text",
"relational"
]
},
"inputs": {
"data": [
{
"datasetID": "32_wikiqa_MIN_METADATA_dataset",
"targets": [
{
"targetIndex": 0,
"resID": "learningData",
"colIndex": 3,
"colName": "isAnswer"
}
]
}
],
"dataSplits": {
"method": "holdOut",
"testSize": 0.3,
"numRepeats": 0,
"splitsFile": "dataSplits.csv",
"datasetViewMaps": {
"train": [
{
"from": "32_wikiqa_MIN_METADATA_dataset",
"to": "32_wikiqa_MIN_METADATA_dataset_TRAIN"
}
],
"test": [
{
"from": "32_wikiqa_MIN_METADATA_dataset",
"to": "32_wikiqa_MIN_METADATA_dataset_TEST"
}
],
"score": [
{
"from": "32_wikiqa_MIN_METADATA_dataset",
"to": "32_wikiqa_MIN_METADATA_dataset_SCORE"
}
]
}
},
"performanceMetrics": [
{
"metric": "f1",
"posLabel": "1"
}
]
},
"expectedOutputs": {
"predictionsFile": "predictions.csv"
}
}
\ No newline at end of file
{
"about": {
"datasetID": "32_wikiqa_MIN_METADATA_dataset_TEST",
"datasetName": "NULL",
"license": "MICROSOFT RESEARCH DATA LICENSE AGREEMENT",
"approximateSize": "5 MB",
"datasetSchemaVersion": "4.0.0",
"redacted": true,
"datasetVersion": "4.0.0",
"digest": "b83cd24e99cede6c82b38334743c863802cc49b359c01c9f1e2fe583ef142ba6"
},
"dataResources": [
{
"resID": "0",
"resPath": "tables/questions.csv",
"resType": "table",
"resFormat": {
"text/csv": [
"csv"
]
},
"columns": [
{
"colIndex": 0,
"colName": "qIndex",
"colType": "integer",
"role": [
"index"
]
}
]
},
{
"resID": "1",
"resPath": "tables/sentences.csv",
"resType": "table",
"resFormat": {
"text/csv": [
"csv"
]
},
"columns": [
{
"colIndex": 0,
"colName": "sIndex",
"colType": "integer",
"role": [
"index"
]
}
]
},
{
"resID": "2",
"resPath": "tables/vocabulary.csv",
"resType": "table",
"resFormat": {
"text/csv": [
"csv"
]
},
"columns": [
{
"colIndex": 0,
"colName": "index",
"colType": "integer",
"role": [
"index"
]
}
]