search

hlt-mt / FBK-fairseq

Repository containing the open source code of works published at the FBK MT unit.
Other
42 stars 1 forks source link

About NE emb #4

Closed Crabbit-F closed 1 year ago

Crabbit-F commented 1 year ago

Would you mind introduce the 'NE emb' detailly? How to get the vector of it? Thanks!

mgaido91 commented 1 year ago

Hi, what do you mean exactly? The "+ NE emb." architecture from the paper corresponds to the conformer_with_tags architecture in the code with the --add-tags-embeddings argument (see the training command in https://github.com/hlt-mt/FBK-fairseq/blob/master/fbk_works/JOINT_ST_NER2023.md#parallel-joint-st-and-ner).

In the code, this corresponds to the ConformerWithTagsModel model, and the learned weights for the NE tags can be taken from the the decoder (TransformerDecoderWithTags), in particular in the field tags_embeddings.

Crabbit-F commented 1 year ago

Thanks a lot! ConformerWithTagsModel mode is helpful to me.

mgaido91 commented 1 year ago

Glad that it helped.