Papers with non-linear projection

1 papers
Non-Linear Instance-Based Cross-Lingual Mapping for Non-Isomorphic Embedding Spaces (2020.acl-main)

Copied to clipboard

Challenge: InstaMap is a non-parametric model that learns a global linear projection by iterating between finding an optimal rotation of the source embedding space and moving each point along an instance-specific translation vector.
Approach: They propose a non-parametric model that learns a global linear projection by iteratively finding an optimal rotation of the source embedding space and moving each point along an instance-specific translation vector.
Outcome: The proposed model performs better than previous models on bilingual lexicon induction across a set of 28 diverse language pairs.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations