BiMPM

BiMPM copied to clipboard

This PR will help in maintaining consistency of training results by saving the embeddings created. In accordance with issue 62- https://github.com/zhiguowang/BiMPM/issues/62 This embedding can then be used as a SentenceMatchDecoder.py...

kaustubhagarwal

Hello, I used your Quora data set and the corresponding configuration to train 10 EPOCHs on the model. During the whole training process, the ACC of the verification set performed...

13593574504

sir plz explain how the two vectors are made up of equal size. plz reply ASAP.

aimaaonline

Error while testing with the default config file

1

I ran into several errors when I tried to run the testing script with the provided instructions: ``` python ${workspace}/BiMPM/src/SentenceMatchDecoder.py --in_path ${your_path_to}/dev.tsv --word_vec_path ${your_path_to}/wordvec.txt --out_path ${your_path_to}/result.json --model_prefix ${model_dir}/SentenceMatch.${suffix} ``` And...

OXPHOS

questions about quora data split

1

Hi, thanks for your excellent work! Your split for quora data is used for so many succeed works, and now I want to use it. But I find the pairID...

ZizhenWang

SentenceMatchDecoder.py gives a wrong answer

5

I trained my model and got a 82% accuracy on dev set. Then I tried to evaluated it on test set, but it gave me 37% accuracy. I thought it...

BluesBai

I tried to start training the model by using the default configuration file for quora. This has `use_cudnn=true`. But it has run into some unexpected error, when I run the...

TLfERLS

* plus some formatting proposals on certain paragraphs (mostly code)

kant

Could you please also share the configuration file for the WikiQA and TrecQA experiments to achieve your best results in the paper? Thank you very much!

WenRichard

Without calling rstrip(), the \n character is its own token, which causes numpy to raise a ValueError when it tries to cast that into a float32

nielsboecker