I'm trying to create a question answering model follow the guide provided by Huggingface. But in the training data for each question and context pair there is only one correct answer and its start_index. So what if the context contains more than one correct answer, I get that we can use topk to get the highest score pairs of [start_index, end_index] from the outputs but is there a way to make the model can learn more than one answer for a question to have a better result?
Asked
Active
Viewed 277 times
0
-
Please remember that Stack Overflow is not your favourite Python forum, but rather a question and answer site for all programming related questions. Thus, please always include the tag of the language you are programming in, that way other users familiar with that language can more easily find your question. Take the [tour] and read up on [ask] to get more information on how this site works, then [edit] the question with the relevant tags. – Adriaan Nov 29 '22 at 11:14