search

prdwb / bert_hae

BERT with History Answer Embedding for Conversational Question Answering
Other
115 stars 23 forks source link

What does the n_best_size parameter mean? #6

Open zhangsanaixuexi opened 4 years ago

zhangsanaixuexi commented 4 years ago

thank you!

prdwb commented 4 years ago

The model predicts the probabilities of each token in the passage being the begin and end tokens of the answer span. When we combine a begin token and an end token, we get an answer span. n_best_size is how many top combinations of begin and end tokens we consider for the final output.

zhangsanaixuexi commented 4 years ago

thank you a lot. If, for an example, the length of the text is greater than the maximum length, then a sliding window will be used. So, how to deal with it if the answer is not in this sliding window.

prdwb commented 4 years ago

For training, if a document chunk does not contain an annotation, we throw it out, since there is nothing to predict.