no code implementations • 12 Oct 2021 • Vihan Lakshman, Choon Hui Teo, Xiaowen Chu, Priyanka Nigam, Abhinandan Patni, Pooja Maknikar, SVN Vishwanathan
When training a dyadic model, one seeks to embed two different types of entities (e. g., queries and documents or users and movies) in a common vector space such that pairs with high relevance are positioned nearby.