How do you correct run-on sentences it's not as easy as it seems

TL;DR

This paper presents two machine learning models designed to correct run-on sentences, demonstrating that artificially generated training data can effectively improve correction performance despite limited annotated datasets.

Contribution

Introduces novel machine learning models for run-on sentence correction and explores the use of artificially generated training data to overcome limited annotated resources.

Findings

Models outperform existing methods in related tasks

Artificial training data is effective for run-on correction

Implications for correcting low-coverage grammatical errors

Abstract

Run-on sentences are common grammatical mistakes but little research has tackled this problem to date. This work introduces two machine learning models to correct run-on sentences that outperform leading methods for related tasks, punctuation restoration and whole-sentence grammatical error correction. Due to the limited annotated data for this error, we experiment with artificially generating training data from clean newswire text. Our findings suggest artificial training data is viable for this task. We discuss implications for correcting run-ons and other types of mistakes that have low coverage in error-annotated corpora.