diff --git a/data/unified_datasets/multiwoz21/data.zip b/data/unified_datasets/multiwoz21/data.zip index d62ee13bcf3f266f18761e9bf2110783167f5236..e520798d4035d05333f56718420f65766bc33461 100644 Binary files a/data/unified_datasets/multiwoz21/data.zip and b/data/unified_datasets/multiwoz21/data.zip differ diff --git a/data/unified_datasets/multiwoz21/dummy_data.json b/data/unified_datasets/multiwoz21/dummy_data.json index ec7aed39735bed82218038a31722b6fdf8e3aac8..3a33d916ffbf22305a188fff05f372bd5f1a20c7 100644 --- a/data/unified_datasets/multiwoz21/dummy_data.json +++ b/data/unified_datasets/multiwoz21/dummy_data.json @@ -91,6 +91,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -113,6 +116,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -174,6 +178,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -212,6 +219,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -290,6 +298,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -324,6 +335,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -387,6 +399,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -423,6 +438,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [ { "name": "the cambridge belfry", @@ -488,6 +504,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -510,6 +529,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [ { "name": "the cambridge belfry", @@ -600,6 +620,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -641,6 +664,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -701,6 +725,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -734,6 +761,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -794,6 +822,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -810,6 +841,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -870,6 +902,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -892,6 +927,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -946,6 +982,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -973,6 +1012,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -1082,6 +1122,9 @@ "arrive by": "20:45", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -1119,6 +1162,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -1182,6 +1226,9 @@ "arrive by": "20:45", "departure": "birmingham new street", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -1204,6 +1251,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -1265,6 +1313,9 @@ "arrive by": "20:45", "departure": "birmingham new street", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -1313,6 +1364,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -1376,6 +1428,9 @@ "arrive by": "20:45", "departure": "birmingham new street", "book people": "5" + }, + "hospital": { + "department": "" } } }, @@ -1407,6 +1462,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [ @@ -1479,6 +1535,9 @@ "arrive by": "20:45", "departure": "birmingham new street", "book people": "5" + }, + "hospital": { + "department": "" } } }, @@ -1504,6 +1563,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [ @@ -1563,6 +1623,9 @@ "arrive by": "20:45", "departure": "birmingham new street", "book people": "5" + }, + "hospital": { + "department": "" } } }, @@ -1585,6 +1648,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [ @@ -1668,6 +1732,9 @@ "arrive by": "20:45", "departure": "birmingham new street", "book people": "5" + }, + "hospital": { + "department": "" } } }, @@ -1699,6 +1766,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [ { "name": "the cambridge belfry", @@ -1769,6 +1837,9 @@ "arrive by": "20:45", "departure": "birmingham new street", "book people": "5" + }, + "hospital": { + "department": "" } } }, @@ -1791,6 +1862,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [ { "name": "the cambridge belfry", @@ -1880,6 +1952,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -1905,6 +1980,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -1975,6 +2051,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -2016,6 +2095,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -2076,6 +2156,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -2098,6 +2181,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -2152,6 +2236,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -2174,6 +2261,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -2272,6 +2360,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -2308,6 +2399,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -2375,6 +2467,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -2411,6 +2506,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -2474,6 +2570,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -2521,6 +2620,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -2575,6 +2675,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -2614,6 +2717,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -2681,6 +2785,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -2737,6 +2844,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -2800,6 +2908,9 @@ "arrive by": "", "departure": "ely", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -2837,6 +2948,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -2908,6 +3020,9 @@ "arrive by": "dontcare", "departure": "cambridge", "book people": "8" + }, + "hospital": { + "department": "" } } }, @@ -2939,6 +3054,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -3017,6 +3133,9 @@ "arrive by": "11:30", "departure": "cambridge", "book people": "8" + }, + "hospital": { + "department": "" } } }, @@ -3056,6 +3175,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [ @@ -3121,6 +3241,9 @@ "arrive by": "11:30", "departure": "cambridge", "book people": "8" + }, + "hospital": { + "department": "" } } }, @@ -3143,6 +3266,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [ @@ -3260,6 +3384,9 @@ "arrive by": "", "departure": "norwich", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -3282,6 +3409,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -3345,6 +3473,9 @@ "arrive by": "", "departure": "norwich", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -3384,6 +3515,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -3462,6 +3594,9 @@ "arrive by": "", "departure": "norwich", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -3484,6 +3619,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -3579,6 +3715,9 @@ "arrive by": "", "departure": "norwich", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -3636,6 +3775,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -3703,6 +3843,9 @@ "arrive by": "", "departure": "norwich", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -3734,6 +3877,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -3795,6 +3939,9 @@ "arrive by": "", "departure": "norwich", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -3847,6 +3994,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -3901,6 +4049,9 @@ "arrive by": "", "departure": "norwich", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -3917,6 +4068,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -3977,6 +4129,9 @@ "arrive by": "", "departure": "norwich", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -3999,6 +4154,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -4070,6 +4226,9 @@ "arrive by": "", "departure": "norwich", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -4092,6 +4251,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -4153,6 +4313,9 @@ "arrive by": "", "departure": "norwich", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -4197,6 +4360,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [ { "name": "acorn guest house", @@ -4262,6 +4426,9 @@ "arrive by": "", "departure": "norwich", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -4284,6 +4451,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [ { "name": "acorn guest house", @@ -4387,6 +4555,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -4423,6 +4594,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -4484,6 +4656,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -4524,6 +4699,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -4584,6 +4760,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -4615,6 +4794,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -4678,6 +4858,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -4721,6 +4904,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -4805,6 +4989,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -4865,6 +5052,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -4935,6 +5123,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -4974,6 +5165,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -5034,6 +5226,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -5061,6 +5256,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -5145,6 +5341,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "emergency department" } } }, @@ -5167,6 +5366,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -5227,6 +5427,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "emergency department" } } }, @@ -5252,6 +5455,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -5312,6 +5516,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "emergency department" } } }, @@ -5334,6 +5541,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -5444,6 +5652,9 @@ "arrive by": "", "departure": "cambridge", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -5490,6 +5701,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -5561,6 +5773,9 @@ "arrive by": "", "departure": "cambridge", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -5601,6 +5816,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -5666,6 +5882,9 @@ "arrive by": "", "departure": "cambridge", "book people": "" + }, + "hospital": { + "department": "" } } }, @@ -5713,6 +5932,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -5776,6 +5996,9 @@ "arrive by": "", "departure": "cambridge", "book people": "1" + }, + "hospital": { + "department": "" } } }, @@ -5859,6 +6082,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [ @@ -5947,6 +6171,9 @@ "arrive by": "", "departure": "cambridge", "book people": "1" + }, + "hospital": { + "department": "" } } }, @@ -6002,6 +6229,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [ @@ -6067,6 +6295,9 @@ "arrive by": "", "departure": "cambridge", "book people": "1" + }, + "hospital": { + "department": "" } } }, @@ -6094,6 +6325,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [ @@ -6189,6 +6421,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "paediatric clinic" } } }, @@ -6214,6 +6449,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] @@ -6284,6 +6520,9 @@ "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "paediatric clinic" } } }, @@ -6306,6 +6545,7 @@ "booked": { "taxi": [], "restaurant": [], + "hospital": [], "hotel": [], "attraction": [], "train": [] diff --git a/data/unified_datasets/multiwoz21/preprocess.py b/data/unified_datasets/multiwoz21/preprocess.py index 305e16d54d67ec0e345ffd002126fc76d342f8bd..07fcc261e557855c34e77cca393345b3898e44f0 100644 --- a/data/unified_datasets/multiwoz21/preprocess.py +++ b/data/unified_datasets/multiwoz21/preprocess.py @@ -521,6 +521,9 @@ ontology = { "arrive by": "", "departure": "", "book people": "" + }, + "hospital": { + "department": "" } }, "dialogue_acts": {