Learning to Substitute Words with Model-based Score Ranking

TL;DR

This paper introduces a model-based approach for word substitution that uses sentence quality scores to improve text without relying on human-labeled data, outperforming existing models.

Contribution

It proposes a novel, annotation-free method for word substitution using model-based scoring and a new loss function to optimize sentence quality.

Findings

Outperforms BERT, BART, GPT-4, and LLaMA in substitution quality.

Avoids reliance on human annotations, reducing labeling costs.

Enhances sentence quality through a novel scoring and ranking approach.

Abstract

Smart word substitution aims to enhance sentence quality by improving word choices; however current benchmarks rely on human-labeled data. Since word choices are inherently subjective, ground-truth word substitutions generated by a small group of annotators are often incomplete and likely not generalizable. To circumvent this issue, we instead employ a model-based score (BARTScore) to quantify sentence quality, thus forgoing the need for human annotations. Specifically, we use this score to define a distribution for each word substitution, allowing one to test whether a substitution is statistically superior relative to others. In addition, we propose a loss function that directly optimizes the alignment between model predictions and sentence scores, while also enhancing the overall quality score of a substitution. Crucially, model learning no longer requires human labels, thus avoiding the cost of annotation while maintaining the quality of the text modified with substitutions. Experimental results show that the proposed approach outperforms both masked language models (BERT, BART) and large language models (GPT-4, LLaMA). The source code is available at https://github.com/Hyfred/Substitute-Words-with-Ranking.