Дистилляция кросс-энкодеров
method
ID: crossencoderdistillation
Related Papers
Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval
AbstractPre-trained language models have been successful in many knowledge-intensive NLP tasks. However, recent work has shown that models such as BERT are not “structurally ready” to aggregate textual information into …...