Handle short sentences
seominjoon opened this issue · comments
Partially resolved using concatenation.
Hi @RamanRajarathinam. We concatenated short sentences into a single paragraph (an input to BERT), then performed the indexing. This resolved the short sentence issues.
Oh okay.. But may I know why model is not performing as expected when the input text is short?
That's because the model was trained on SQuAD which usually contains a passage longer than a sentence.
So the only solution is to concatenate different texts? or Is there any other way to solve this?
So the only solution is to concatenate different texts? or Is there any other way to solve this?
=> For now, yes but I guess there can be plenty of other solutions that can de-bias the length bias like augmenting short passage QA training pairs.