lupantech/intergps

Data and Code for ACL 2021 Paper "Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning"

intergps's Issues

DataSet Generation

Hi Pan,
Loved your work in InterGPS. We were planning to extend the dataset, using the annotation tools shared. We wanted to know in logic_form.json for each question (Ground Truth), how was point positions added was this done manually or using some subroutine?
Thanks, Akshat

Cannot reproduce the results of symbol solver

Hi,
I follow the instruction to reproduce the results:
cd symbolic_solver
python test.py --label final --strategy final
But the obtained result is 40.27%, instead of the result 71.88% (in pred_results).
Can you help me with it?

Dataset generation

About Data Annotation Tools

Excuse me，how can I use the Data Collection tool? When I run app.py, it gets results

but without anything in the web link.
Best wish!

Providing a pretrained object detection model for text and symbols

Hello,
Thanks for your work!
Could you please provide a pretrained object detection model, e.g. the one mentioned in the documentation here: models/exp0/csv_retinanet_19.pt?

Thank you in advance :)

About datasets

Hello, how can I expand the data set of Geometry3K？ Where the math geometry problems of Geometry3K come from? Could you please provide more specific web links or other information?
Thank you very much!

Poor performance of theorem predictor

Hello, Pan. Thank you for your open source.

I download checkpoint model from https://acl2021-intergps.s3.us-west-1.amazonaws.com/tp_model_best.pt
But the evaluation results are empty. How can I get it back to normal? Thanks.

About the file of “diagram_logic_forms_pred.json”

Excuse me, could you tell me about whether the content of file “diagram_logic_forms_pred.json" is the predicted results of your diagram parser? Thanks every much!

Sharing Training Details

Hi Pan,

Your paper "Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning" is awesome.

However, when reproducing results of this work, I have one problem. I trained the symbol detection model with the data you provided, but the model could not perform as well as the box_result you released. Could you please share more training details?

Thank you very much and looking forward to your reply.