Search Results for author: Manos Tsagkias

Found 5 papers, 1 papers with code

Error-driven Pruning of Language Models for Virtual Assistants

no code implementations14 Feb 2021 Sashank Gondala, Lyan Verwimp, Ernest Pusateri, Manos Tsagkias, Christophe Van Gysel

We customize entropy pruning by allowing for a keep list of infrequent n-grams that require a more relaxed pruning threshold, and propose three methods to construct the keep list.

Cannot find the paper you are looking for? You can Submit a new open access paper.