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

Abstract

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 different curriculum learning strategies and different batching strategies. We consider multiple datasets for three tasks: text classification, sentence and phrase similarity, and part-of-speech tagging. Our experiments demonstrate that certain curriculum learning and batching decisions do increase performance substantially for some tasks.

Document Details

Document Type
Pub Defense Publication
Publication Date
Sep 11, 2021
Source ID
10.3390/math9182234

Entities

People

  • Jonathan K. Kummerfeld
  • Laura Burdick
  • Rada Mihalcea

Organizations

  • Defense Advanced Research Projects Agency
  • National Science Foundation

Tags

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Neural Network Machine Learning.
  • Parallel and Distributed Computing.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Machine Translation
  • AI & ML - Neural Networks