pkuserc/chatgpt_for_ie

Evaluating ChatGPT’s Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness

chatgpt_for_ie's Issues

Data format of SemEval2010?

Thanks to the authors for publicizing the code, I am trying to reproduce the results for the RC task, which uses the SemEval2010 dataset, the format used in the code seems to be different from the official release, can the authors please let me know where the data is obtained from? I want to make sure the results (sentence ordering etc.) are consistent, thanks!

Also a side question, I assume the results in ChatGPT_Output are the authors' own experiment results, why are the 'sentence' entries all redacted? Is it because of the use of LDC-licensed datasets?

KeyError: 'trigger_word'

在运行python Code/ED/score_ED_E.py命令时，出现

trigger_word = event['trigger_word']
KeyError: 'trigger_word'

通过查找ED_E_gold.json文件，并未发现有trigger_word这个键

最后，通过参考score_EE_E.py的代码，发现event的key可能设置错误了，修改后，可以正常运行