hxx97 / gmt-kbqa Goto Github PK

Hi, I read your paper, and it is a great job! But I can't reproduce the result F1=77 on the CWQ dataset. I am using the provided data along with the model CWQ_GMT_KBQA. I just ran the last step: evaluation: python3 eval_topk_prediction_final.py --split test --pred_file exps/CWQ_GMT_KBQA/beam_50_test_4_top_k_predictions.json --test_batch_size 4 --dataset CWQ --beam_size 50, and I got Total: 3531, ACC:0.6978193146417445, AVGP: 0.7499605933112178, AVGR: 0.7684635982032751, AVGF: 0.7445226124529617. Could you please tell me what might be the problem?

Sorry to interrupt.I am a novice. Can you tell me how to get zhe freebase_sparql_wrapper_url and freebase_odbc_port?
I follow the introduction but I don't understand.

Hello, I have a problem when I do entity linking with ELQ service.

from detect_and_link_entity import get_entity_linking_from_elq
mention = "what religions are practiced in the country that has the national anthem Afghan National Anthem"
entity = get_entity_linking_from_elq(mention)
print(entity)

I ran the code above, but I only got the output following:

[{'id': [], 'label': 'Afghan National Anthem', 'mention': 'afghan national anthem', 'score': -1.2437682151794434, 'perfect_match': True}, {'id': [], 'label': 'Religion', 'mention': 'religions', 'score': -3.7547619342803955, 'perfect_match': False}, {'id': [], 'label': 'Islam', 'mention': 'religions', 'score': -4.306562900543213, 'perfect_match': False}, {'id': [], 'label': 'Religion in Afghanistan', 'mention': 'religions', 'score': -5.706789016723633, 'perfect_match': False}, {'id': [], 'label': 'Abrahamic religions', 'mention': 'religions', 'score': -6.387351989746094, 'perfect_match': False}, {'id': [], 'label': 'Religion in Bangladesh', 'mention': 'religions', 'score': -6.408331871032715, 'perfect_match': False}, {'id': [], 'label': 'National anthem of the Kingdom of Afghanistan', 'mention': 'afghan national anthem', 'score': -7.044179439544678, 'perfect_match': False}, {'id': [], 'label': 'National anthem of the Democratic Republic of Afghanistan', 'mention': 'afghan national anthem', 'score': -8.992083549499512, 'perfect_match': False}, {'id': [], 'label': 'National anthem', 'mention': 'afghan national anthem', 'score': -9.269025802612305, 'perfect_match': False}, {'id': [], 'label': 'Anthem of the Republic of Kazakhstan', 'mention': 'afghan national anthem', 'score': -10.114151000976562, 'perfect_match': False}]
Why can't I get the freebase id?

Hello, thanks for your repository, it inspires me a lot. For the QA dataset, I wonder how to adapt this framework to the GrailQA dataset? What changes do I need to make to this framework？