Nice question, how to learn something global in a NN approach.

Interesting detail from answer by Mostafa Deghani: include extra value into embedding to help it learn an (i?)df-like feature.

And @suzan mentions recent paper on Bert rediscovering the NLP pipeline.


Sign in to participate in the conversation

The "unofficial" Information Retrieval Mastodon Instance.

Goal: Make a viable and valuable social space for anyone working in Information Retrieval and related scientific research.

Everyone welcome but expect some level of geekiness on the instance and federated timelines.