Budding
Budding
非常感谢您的工作!关于您的工作中similarity calculation这个图的生成  请问是怎么获得的哇
加油加油 加油更新哇
您好,我注意到 您之前的工作中https://github.com/taishan1994/pytorch_bert_event_extraction 写道“要预先下载好[chinese-roberta-wwm-ext](https://huggingface.co/hfl/chinese-roberta-wwm-ext/tree/main)模型,并在运行时指定模型的位置。 已经训练好的模型:放在checkpoints下 链接:https://pan.baidu.com/s/1b5cqkjRH4uejO5h_587oGw 提取码:funk” 在这个项目中,也可以直接使用chinese-roberta-wwm-ext和您提供的checkpoints吗
Hello, I am currently studying the article 'ClipSitu: Effectively Leveling CLIP for Conditional Predictions in Situation Recognition'. While searching for information, I found your job and would like to inquire...
您好奥!我想请教一个问题,我将英文数据集改为了DuEEData的数据格式,并且将--bert_model='/home/pretrained_model/bert_en' \,在dee_task.py里面将 elif self.run_mode == "dueefin_wo_tgg": self.train_file_name = "dueefin_train_wo_tgg.json" self.dev_file_name = "dueefin_dev_wo_tgg.json" self.test_file_name = "dueefin_submit_wo_tgg.json" self.inference_file_name = "dueefin_submit_wo_tgg.json" self.doc_lang = "en" elif self.run_mode == "dueefin_w_tgg": self.train_file_name = "dueefin_train_w_tgg.json" self.dev_file_name =...
您好,我将"use_mention_lstm" 改为True后,出现了维度报错。 当"use_mention_lstm" 为False,trigger_aware.py中 ex_idx_list = doc_batch_dict["ex_idx"] #[2532, 992, 3053, 3108, 2902, 4000, 270, 2013], 此时,doc_token_emb_list[batch_idx],# [5, 128, 768] 当"use_mention_lstm" 改为True后, ex_idx_list = doc_batch_dict["ex_idx"] #[2523, 1829, 3851, 2892, 4017, 696,...