Code for the paper "Relation of the Relations: A New Formalization of the Relation Extraction Problem"

您好： 当我运行：python main.py --dataset=semeval2018_task7 --auto_hyperparam 错误：File "/home/RoR/models/graph_trans.py", line 7, in from .loss_func import * ModuleNotFoundError: No module named 'models.loss_func' 谢谢！

Hi @zhijing-jin ,

Sorry for disturbing you, but I already tried to run your source code as guided. However, on SemEval2018, I obtain Macro F1 score is 35.9% (the best result), whereas the reported result is 38.83% with RoR_base. I use the same auto hyper-parameters and the same environment configuration (as in requirement.txt). What should I do to get the reported performance? Thanks so much!

Hi @FFTYYY , thanks for releasing your source code. For the SemEval 2018 Task 7, you guide to use the command: bash prep_data_and_env.sh . I wonder about how to preprocess the ACE_2005 dataset, as I downloaded it from LDC?

很有意思的工作，关系的关系，通过transformer来自动寻找关系间的依赖，很有启发，但是我看完代码有一些不太了解的地方，在dataloader_semeval_2018_task7文件的parse_a_key_file函数里有 if dtype == "train": if rel == "COMPARE": datas[text_id].ans.append(Relation(ent_b , ent_a , rel)) 这里是只考虑了COMPARE这一种关系吗？如果是这是为什么呢？谢谢。

(base) raphy@pc:~/RoR_relation_extraction$ python main.py --dataset=ace_2005 --auto_hyperparam
Hyper parameters autoset. | now time: 0s
------------------------------------------------------ | now time: 0s
{'auto_hyperparam': True,
 'binary': False,
 'dataset': 'ace_2005',
 'dropout': 0.0,
 'ensemble': 1,
 'ensemble_size': 5,
 'epoch_numb': 30,
 'gene_file': 'watch/gene',
 'gene_in_data': True,
 'gene_no_rel': False,
 'gnn': True,
 'log_file': 'log.txt',
 'loss': 'loss_1',
 'matrix_nlayer': 4,
 'matrix_trans': True,
 'model_save': 'model_ace.pkl',
 'model_save_2': '',
 'no_log': False,
 'no_rel_name': 'NO_RELATION',
 'no_rel_weight': 0.25,
 'no_valid': True,
 'pos_only': False,
 'pos_thresh': 0.3,
 'rel_weight_norm': False,
 'rel_weight_smooth': 0,
 'scheduler': 'cosine',
 't2g_batch_size': 8,
 't2g_lr': 5e-05,
 't2g_seed': 2333,
 'test_rels': './data/semeval_2018_task7/keys.test.2.txt',
 'test_script': './data/semeval_2018_task7/semeval2018_task7_scorer-v1.2.pl',
 'test_text': './data/ace_2005/ace_05_processed/ace-05-splits/json-pm13/bc_test.json',
 'tmp_file_name': 'tmp_17300649.txt',
 'train_rels_1': './data/semeval_2018_task7/1.1.relations.txt',
 'train_rels_2': './data/semeval_2018_task7/1.2.relations.txt',
 'train_text_1': './data/ace_2005/ace_05_processed/ace-05-splits/json-pm13/bn+nw.json',
 'train_text_2': './data/semeval_2018_task7/1.2.text.xml',
 'valid_metric': 'macro',
 'valid_rels': './data/semeval_2018_task7/keys.test.1.1.txt',
 'valid_text': './data/ace_2005/ace_05_processed/ace-05-splits/json-pm13/bc_dev.json',
 'warmup_prop': 0.02,
 'watch_type': 'test'} | now time: 0s
------------------------------------------------------ | now time: 0s
Seed set. 2333 | now time: 0s
Traceback (most recent call last):
  File "main.py", line 95, in <module>
    main()
  File "main.py", line 54, in main
    C , logger = get_config()
  File "/home/raphy/RoR_relation_extraction/config.py", line 177, in get_config
    C , logger = after_parse_t2g(before_parse_t2g(argparse.ArgumentParser()).parse_args() , need_logger = True)
  File "/home/raphy/RoR_relation_extraction/config.py", line 168, in after_parse_t2g
    tc.cuda.set_device(C.gpus[0])
IndexError: list index out of range
(base) raphy@pc:~/RoR_relation_extraction$ 

I do not have CUDA .....

When I run python main.py --dataset=semeval_2018_task7 --auto_hyperparam I got AttributeError: module 'fitlog' has no attribute 'add_to_line' Is there a way to fix it?