UCDP-AEC

Models and data for the UCDP Abstractive Event analysis Corpus paper
git clone https://esimon.eu/repos/UCDP-AEC.git
Log | Files | Refs | README | LICENSE

dataset_info.json (2250B)

      1 {
      2   "builder_name": "ucdp_connector.UCDPDataset",
      3   "citation": "",
      4   "config_name": "aec",
      5   "dataset_name": "ucdp-aec",
      6   "dataset_size": 156390318,
      7   "description": "UCDP Abstractive Event analysis Corpus",
      8   "download_checksums": {},
      9   "download_size": 0,
     10   "features": {
     11     "id": {
     12       "dtype": "uint32",
     13       "_type": "Value"
     14     },
     15     "source_article": {
     16       "dtype": "string",
     17       "_type": "Value"
     18     },
     19     "source_date": {
     20       "dtype": "timestamp[s]",
     21       "_type": "Value"
     22     },
     23     "deaths_side_a": {
     24       "dtype": "uint32",
     25       "_type": "Value"
     26     },
     27     "deaths_side_b": {
     28       "dtype": "uint32",
     29       "_type": "Value"
     30     },
     31     "deaths_civilian": {
     32       "dtype": "uint32",
     33       "_type": "Value"
     34     },
     35     "deaths_unknown": {
     36       "dtype": "uint32",
     37       "_type": "Value"
     38     },
     39     "deaths_low": {
     40       "dtype": "uint32",
     41       "_type": "Value"
     42     },
     43     "deaths_high": {
     44       "dtype": "uint32",
     45       "_type": "Value"
     46     },
     47     "side_a_name": {
     48       "dtype": "string",
     49       "_type": "Value"
     50     },
     51     "side_b_name": {
     52       "dtype": "string",
     53       "_type": "Value"
     54     },
     55     "location_root_name": {
     56       "dtype": "string",
     57       "_type": "Value"
     58     },
     59     "location_adm1_name": {
     60       "dtype": "string",
     61       "_type": "Value"
     62     },
     63     "location_adm2_name": {
     64       "dtype": "string",
     65       "_type": "Value"
     66     },
     67     "location_where_name": {
     68       "dtype": "string",
     69       "_type": "Value"
     70     },
     71     "start_date": {
     72       "dtype": "date32",
     73       "_type": "Value"
     74     },
     75     "end_date": {
     76       "dtype": "date32",
     77       "_type": "Value"
     78     }
     79   },
     80   "homepage": "https://github.com/ltgoslo/ucdp-aec",
     81   "license": "CC-BY",
     82   "size_in_bytes": 156390318,
     83   "splits": {
     84     "train": {
     85       "name": "train",
     86       "num_bytes": 102388962,
     87       "num_examples": 74216,
     88       "dataset_name": "ucdp-aec"
     89     },
     90     "validation": {
     91       "name": "validation",
     92       "num_bytes": 9352886,
     93       "num_examples": 6784,
     94       "dataset_name": "ucdp-aec"
     95     },
     96     "test": {
     97       "name": "test",
     98       "num_bytes": 44648470,
     99       "num_examples": 29194,
    100       "dataset_name": "ucdp-aec"
    101     }
    102   },
    103   "version": {
    104     "version_str": "2025.04.22",
    105     "major": 2025,
    106     "minor": 4,
    107     "patch": 22
    108   }
    109 }