A question about the number of labels
Closed this issue · 1 comments
Thanks for your extremely great work.
I have a question about the number of labels C mentioned in 4.2 section.
In your dataset, it seems that there are 4 labels for one aspect-category (1 - positive, 0 - neural, -1 - negative, -2 - not mentioned), but in the ACSA part, it looks like C is equal to 3 (positive, neural, negative)
C is the number of labels (i.e, 3 in our task).
so, I wonder why the label not mentioned was scrapped.
I have noticed that the gate function p_i is used to ensure only the mentioned aspect categories can participate in the calculation of the loss function.
but it seems like the gate function p_i is not a trainable parameter, so when using the trained model to do prediction, how the model knows which aspect-category are mentioned in a review?
for example, for an input review R written by a user,
the output of the ACSA part might be:
\hat{y}_1 = [0.7, 0.2, 0.1]
\hat{y}_2 = [0.5, 0.2, 0.3]
...
\hat{y}_18 = [0.05, 0.05, 0.9]
(Please correct me if I have misunderstood something)
in this case, we can know that this user has positive sentiment with the first and second aspect-category, and has negative sentiment with the 18th aspect-category, but how do we know which aspect-category are mentioned in this review?
Thanks for your extremely great work.
I have a question about the number of labels C mentioned in 4.2 section.
In your dataset, it seems that there are 4 labels for one aspect-category (1 - positive, 0 - neural, -1 - negative, -2 - not mentioned), but in the ACSA part, it looks like C is equal to 3 (positive, neural, negative)
C is the number of labels (i.e, 3 in our task).
so, I wonder why the label not mentioned was scrapped.
I have noticed that the gate function p_i is used to ensure only the mentioned aspect categories can participate in the calculation of the loss function. but it seems like the gate function p_i is not a trainable parameter, so when using the trained model to do prediction, how the model knows which aspect-category are mentioned in a review?
for example, for an input review R written by a user, the output of the ACSA part might be:
\hat{y}_1 = [0.7, 0.2, 0.1] \hat{y}_2 = [0.5, 0.2, 0.3] ... \hat{y}_18 = [0.05, 0.05, 0.9]
(Please correct me if I have misunderstood something)
in this case, we can know that this user has positive sentiment with the first and second aspect-category, and has negative sentiment with the 18th aspect-category, but how do we know which aspect-category are mentioned in this review?
hi,the label "-2 - not mentioned" is not used to train model , it serves as a placeholder for format beauty.
The ACSA task aims to predict sentiment polarities on given aspect categories. The gate function p_i needs to be given by expert instead of being learned from the model, both in training and prediction stages.
I hope this helps!