Improving Emotional Expression and Cohesion in Image-Based Playlist Description and Music Topics: A Continuous Parameterization Approach

TL;DR

This paper introduces a novel continuous parameterization method for controlled text generation in image-based music content platforms, enabling precise manipulation of style, emotion, and cohesion to improve relevance and coherence.

Contribution

It proposes CPCTG, a continuous control framework that integrates style learning, semantic cohesion, and emotional expression, advancing beyond discrete input limitations in text generation.

Findings

Significant ROUGE score improvements in experiments

Enhanced relevance and coherence in generated playlist descriptions

Effective manipulation of emotional expression and style

Abstract

Text generation in image-based platforms, particularly for music-related content, requires precise control over text styles and the incorporation of emotional expression. However, existing approaches often need help to control the proportion of external factors in generated text and rely on discrete inputs, lacking continuous control conditions for desired text generation. This study proposes Continuous Parameterization for Controlled Text Generation (CPCTG) to overcome these limitations. Our approach leverages a Language Model (LM) as a style learner, integrating Semantic Cohesion (SC) and Emotional Expression Proportion (EEP) considerations. By enhancing the reward method and manipulating the CPCTG level, our experiments on playlist description and music topic generation tasks demonstrate significant improvements in ROUGE scores, indicating enhanced relevance and coherence in the generated text.