Open freesunshine0316 opened 5 years ago
https://github.com/shayneobrien/coreference-resolution/blob/f368f5a06e1d646d60c50d824235576bb8fe4198/src/coref.py#L211
I think there's a bug around the above code. The LSTM encoding does not go along each sentence, as
pack_sequence
does not work as you thought.
Author's note in span representation section (Lee 2017): Independent LSTM for every sentence should be used as cross sentence context was not useful.
https://github.com/shayneobrien/coreference-resolution/blob/f368f5a06e1d646d60c50d824235576bb8fe4198/src/coref.py#L211
I think there's a bug around the above code. The LSTM encoding does not go along each sentence, as
does not work as you thought.