Analyzing Curriculum Learning for Sentiment Analysis along Task Difficulty, Pacing and Visualization Axes

TL;DR

This paper investigates how curriculum learning impacts sentiment analysis by analyzing task difficulty, pacing strategies, and attention visualization, revealing its strengths and limitations across different scenarios.

Contribution

It provides an in-depth analysis of curriculum learning in sentiment analysis along multiple axes, including task difficulty, pacing, and attention visualization, which was lacking in prior work.

Findings

Curriculum learning is most effective for difficult sentiment analysis tasks.

One-Pass curriculum strategies suffer from catastrophic forgetting.

Visualization shows curriculum breaks down tasks into easier sub-tasks.

Abstract

While Curriculum Learning (CL) has recently gained traction in Natural language Processing Tasks, it is still not adequately analyzed. Previous works only show their effectiveness but fail short to explain and interpret the internal workings fully. In this paper, we analyze curriculum learning in sentiment analysis along multiple axes. Some of these axes have been proposed by earlier works that need more in-depth study. Such analysis requires understanding where curriculum learning works and where it does not. Our axes of analysis include Task difficulty on CL, comparing CL pacing techniques, and qualitative analysis by visualizing the movement of attention scores in the model as curriculum phases progress. We find that curriculum learning works best for difficult tasks and may even lead to a decrement in performance for tasks with higher performance without curriculum learning. We see that One-Pass curriculum strategies suffer from catastrophic forgetting and attention movement visualization within curriculum pacing. This shows that curriculum learning breaks down the challenging main task into easier sub-tasks solved sequentially.