New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Questions about Results on Question Answering, Table 3 #8
Comments
Task-specific linear head is fine-tuned with prompt embeddings. |
Thanks! Secondly, I have tried PT with T5-base-v1.1 as in Lester et al. (2021) and with RoBERTa-base as described above (fine-tuning both prompt embeddings (input layer only) and task-specific QA heads). And the F1 scores exceed 80 easily without careful hyperparameters search. And the results in Table 3 are quite different. Are there any other constraints that need to be met in the implementation of PT? |
Yes, LM head can not be applied to sequence tagging as for now. |
Yes, I am sure. Only the prompt embeddings and qa heads are added to the optimizer. I think the little code snippets are enough for it is easy to implement.
In RobertEmbeddings,
Attention Mask,
RobertaForQuestionAnswering outputs,
|
@Xiao9905 Hi, could you share the hyperparameters and optimizer configuration used for PT2 SQuAD 1.1 Roberta-Large? |
In Lester et al. (2021), they use T5 as the pre-trained model and use LM head to generate answers.
For models like BERT, Roberta explored in this work, we can not use LM head to extract context spans as the answers, which means a linear QA head is essential.
Is the task-specific linear head fine-tuned with prompt embeddings in PT, Table 3?
If so, this implementation is a little different from the original implementation.
If not, the randomly initialized QA head is not expected to produce meaningful outputs and hinders PT training, which makes the PT results in Table 3 meaningless.
Or, do I have some misunderstandings about the LM head in QA tasks?
The text was updated successfully, but these errors were encountered: