I use the code published in this repo to conduct the experiment on the dataset published by ARNOR, and the model adopted in my experiment is SENT(BiLSTM)
However, I can only achieve the micro-f1 = 0.6 shown in the log.
Notice that the micro-f1 specific to the SENT(BiLSTM) of the paper is 0.64.
Above all, is there something wrong with the code in this repository?
I use the code published in this repo to conduct the experiment on the dataset published by ARNOR, and the model adopted in my experiment is SENT(BiLSTM) However, I can only achieve the micro-f1 = 0.6 shown in the log. Notice that the micro-f1 specific to the SENT(BiLSTM) of the paper is 0.64.
Above all, is there something wrong with the code in this repository?