def __init__(self, dataset_file_path: str,
event_type_vocabulary: Vocabulary):
"""
初始化 ACE Event Dataset
:param dataset_file_path: 数据集的文件路基
"""
super().__init__()
self._ace_dataset = ACEDataset(dataset_file_path=dataset_file_path)
self._instances: List[Instance] = list()
for ori_instance in self._ace_dataset:
ori_event_types = ori_instance["event_types"]
ori_event_type_set = None
if ori_event_types is not None: # 实际预测的时候 ori_event_types is None
# 针对 training 和 validation 设置，因为 对于 pair<sentence, unk>, label = 1
ori_event_type_set = set(ori_event_types)
if len(ori_event_type_set) == 0:
ori_event_type_set.add(event_type_vocabulary.unk)
for index in range(event_type_vocabulary.size):
# 遍历所有的label, 形成 pair<句子,事件类型>，作为样本
event_type = event_type_vocabulary.token(index)
instance = Instance()
instance["sentence"] = ori_instance["sentence"]
instance["entity_tag"] = ori_instance["entity_tag"]
instance["event_type"] = event_type
instance["metadata"] = ori_instance["metadata"]
if ori_event_type_set is not None:
if event_type in ori_event_type_set:
instance["label"] = 1
else:
instance["label"] = 0
else:
# 是针对实际的 prediction 设置的
pass
self._instances.append(instance)
def __init__(self, event_type_vocabulary: Vocabulary):
"""
初始化
:param event_type_vocabulary: event type vocabulary
"""
super().__init__()
self._event_type_f1: Dict[str, LabelF1Metric] = dict()
for index in range(0, event_type_vocabulary.size):
event_type = event_type_vocabulary.token(index)
if event_type != event_type_vocabulary.unk:
self._event_type_f1[event_type] = LabelF1Metric(
labels=[1], label_vocabulary=None)
self._event_type_f1[EventF1MetricAdapter.__OVERALL] = LabelF1Metric(
labels=[1], label_vocabulary=None)
self._event_type_vocabulary = event_type_vocabulary
