PaddleNLP 运行UIE的例子，为啥得到的结果是错误的

代码如下： from paddlenlp import Taskflow from pprint import pprint

schema = ['时间', '选手', '赛事名称'] # Define the schema for entity extraction ie = Taskflow('information_extraction', schema=schema) pprint(ie("2月8日上午北京冬奥会自由式滑雪女子大跳台决赛中中国选手谷爱凌以188.25分获得金牌！")) # Better print results using pprint

输出的结果如下： :\mywork\project\NLPTest\venv\Scripts\python.exe D:\mywork\project\NLPTest\main.py D:\mywork\project\NLPTest\venv\lib\site-packages_distutils_hack_init_.py:33: UserWarning: Setuptools is replacing distutils. warnings.warn("Setuptools is replacing distutils.") [2023-12-03 21:13:22,814] [ INFO] - Downloading model_state.pdparams from https://bj.bcebos.com/paddlenlp/taskflow/information_extraction/uie_base_v1.1/model_state.pdparams 100%|██████████| 450M/450M [00:12<00:00, 39.0MB/s] [2023-12-03 21:13:36,515] [ INFO] - Downloading config.json from https://bj.bcebos.com/paddlenlp/taskflow/information_extraction/uie_base/config.json 100%|██████████| 610/610 [00:00<?, ?B/s] [2023-12-03 21:13:36,767] [ INFO] - Downloading vocab.txt from https://bj.bcebos.com/paddlenlp/taskflow/information_extraction/uie_base/vocab.txt 100%|██████████| 182k/182k [00:00<00:00, 852kB/s] [2023-12-03 21:13:37,280] [ INFO] - Downloading special_tokens_map.json from https://bj.bcebos.com/paddlenlp/taskflow/information_extraction/uie_base/special_tokens_map.json 100%|██████████| 112/112 [00:00<?, ?B/s] [2023-12-03 21:13:37,529] [ INFO] - Downloading tokenizer_config.json from https://bj.bcebos.com/paddlenlp/taskflow/information_extraction/uie_base/tokenizer_config.json 100%|██████████| 172/172 [00:00<?, ?B/s] [2023-12-03 21:13:37,747] [ INFO] - loading configuration file C:\Users\coudy.paddlenlp\taskflow\information_extraction\uie-base\config.json [2023-12-03 21:13:37,748] [ INFO] - Model config ErnieConfig { "architectures": [ "UIE" ], "attention_probs_dropout_prob": 0.1, "dtype": "float32", "enable_recompute": false, "fuse": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-12, "max_position_embeddings": 2048, "model_type": "ernie", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 0, "paddlenlp_version": null, "pool_act": "tanh", "task_id": 0, "task_type_vocab_size": 3, "type_vocab_size": 4, "use_task_id": true, "vocab_size": 40000 }

[2023-12-03 21:14:00,362] [ INFO] - All model checkpoint weights were used when initializing UIE.

[2023-12-03 21:14:00,362] [ INFO] - All the weights of UIE were initialized from the model checkpoint at C:\Users\coudy.paddlenlp\taskflow\information_extraction\uie-base. If your task is similar to the task the model of the checkpoint was trained on, you can already use UIE for predictions without further training. [2023-12-03 21:14:00,394] [ INFO] - Converting to the inference model cost a little time. I1203 21:14:03.044967 11032 interpretercore.cc:237] New Executor is Running. [2023-12-03 21:14:05,333] [ INFO] - The inference model save in the path:C:\Users\coudy.paddlenlp\taskflow\information_extraction\uie-base\static\inference [2023-12-03 21:14:06,164] [ INFO] - We are using <class 'paddlenlp.transformers.ernie.tokenizer.ErnieTokenizer'> to load 'C:\Users\coudy.paddlenlp\taskflow\information_extraction\uie-base'. [{'赛事名称': [{'end': 4, 'probability': 0.3464906954924629, 'start': 1, 'text': '月8日'}, {'end': 0, 'probability': 0.3239983692435544, 'start': 0, 'text': ''}, {'end': 0, 'probability': 0.28662281814175117, 'start': 0, 'text': ''}, {'end': 0, 'probability': 0.2829913402307511, 'start': 0, 'text': ''}]}]

Process finished with exit code 0