Problem about the usage of trigger information in arg_detection model

[xiezhiyu01]

Dear Author:

Thanks for sharing you work! I have a question about the usage of trigger information in arg_detection model.

In your arg_detection model,
https://github.com/VT-NLP/Event_Query_Extract/blob/main/model/argument_detection/arg_detection.py#L205
after getting the trigger embeddings, it seems that you did not use them for further calculations, which doesn't align with the definition of "trigger-aware entity representations" in your paper "2.2 Event Argument Extraction, Multiway Attention".
In other words, I could not find where the trigger information is used in arg_detection models.

Could you help me with this problem if possible? Thanks!