hxx97 / gmt-kbqa Goto Github PK
View Code? Open in Web Editor NEWCode and data for GMT-KBQA
License: BSD 3-Clause "New" or "Revised" License
Code and data for GMT-KBQA
License: BSD 3-Clause "New" or "Revised" License
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?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.