HI and thanks for Great package ;)
Why when You initialize 'train_examples' , list of InputExample' s istances in ClassificationModel class, You don't allow to pass additional feature as second text, like a 'text_b' in df_train, for example...? to process sequences pair model...?
It's because I only had single sentence tasks in mind when I first published the library. Most of the code to support sentence pair tasks should already be in place though, so I'll see what I can do about testing this and adding it quickly.
I am new to SimpleTransformers but I modified the part where text_b is considered as:
train_examples = [InputExample(i, text, text2, label) for i, (text, text2, label) in enumerate(zip(train_df.iloc[:, 0], train_df.iloc[:, 1], train_df.iloc[:, 2]))]
Is it ok to do that? I was getting value error before this edit, it seems that solved it. Of course, I do not know if it leads to more problems or not.
There's a chance it might work. If your final results are good, then it's probably working. Please let me know if it is!
Sentence pair tasks are now supported.
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
Most helpful comment
It's because I only had single sentence tasks in mind when I first published the library. Most of the code to support sentence pair tasks should already be in place though, so I'll see what I can do about testing this and adding it quickly.