Giters

seominjoon / denspi

Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index (DenSPI)

Home Page:https://nlp.cs.washington.edu/denspi

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Handle short sentences

seominjoon opened this issue · comments

commented

Partially resolved using concatenation.

commented

Hi @jhyuklee May I know what do you mean by concatenation? Is it a text concatenation or vector concatenation?

Please refer #13 for more details

commented

Hi @RamanRajarathinam. We concatenated short sentences into a single paragraph (an input to BERT), then performed the indexing. This resolved the short sentence issues.

commented

Oh okay.. But may I know why model is not performing as expected when the input text is short?

commented

That's because the model was trained on SQuAD which usually contains a passage longer than a sentence.

commented

So the only solution is to concatenate different texts? or Is there any other way to solve this?

commented

Can you also please comment on this issues #9 and #13?

commented

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.