Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.
Sign up to join this community
Can Facebook's LASER be fine-tuned like BERT for Question Answering tasks or Sentiment Analysis?
From my understanding, they created an embedding that allows for similar words in different languages to be close to each other. I just don't understand if this can be used for fine-tuning tasks like BERT can.
LASER creates multilingual contextualized word embeddings, what you do with them is up to you. You can use this as a feature extraction and add whatever you want to the end of the network.
I believe the implementation by facebook does not let you change the weights of the LASER model itself, they are froozen to the best of my knowledge.
So, yes, you can use LASER for downstream tasks, but you cannot change the actual weights of the LASER model.
