To Batch or Not to Batch? Comparing Batching and Curriculum Learning Strategies across Tasks and Datasets

Many natural language processing architectures are greatly affected by seemingly small design decisions, such as batching and curriculum learning (how the training data are ordered during training). In order to better understand the impact of these decisions, we present a systematic analysis of diff...

Full description

Bibliographic Details

Published in:	Mathematics
Main Authors:	Laura Burdick, Jonathan K. Kummerfeld, Rada Mihalcea
Format:	Article
Language:	English
Published:	MDPI AG 2021-09-01
Subjects:	natural language processing word embeddings batching word2vec curriculum learning text classification
Online Access:	https://www.mdpi.com/2227-7390/9/18/2234