search

THU-KEG / MAVEN-dataset

Source code and dataset for EMNLP 2020 paper "MAVEN: A Massive General Domain Event Detection Dataset".
MIT License
151 stars 39 forks source link

Where is the adversarial training of DMBERT? #13

Closed gabrer closed 2 years ago

gabrer commented 2 years ago

Just a quick question, as I cannot find the adversarial training in the DMBERT implementation.

It seems that it's just doing a sentence encoding and classification, without any generator/discriminator mechanism.

Is this implementation different from the one described in the original paper?

Thanks!

Bakser commented 2 years ago

Yes. The DMBERT model here is the vanilla baseline without adversarial training (corresponding to DMBERT notation in the original paper). The DMBERT with adversarial training (corresponding to DMBERT+ADV or DMBERT+Boot) is not included in MAVEN experiments since here are in the fully supervised setting rather than the weakly supervised setting.