Role of Dependency Distance in Text Simplification: A Human vs ChatGPT Simplification Comparison
This work addresses text simplification for natural language processing applications, but it is incremental as it compares existing methods without introducing new techniques.
The study compared human and ChatGPT text simplification by analyzing dependency distances across 220 sentences of varying grammatical difficulty, finding that original sentences had the highest mean dependency distance, ChatGPT simplified ones were intermediate, and human simplified ones had the lowest.
This study investigates human and ChatGPT text simplification and its relationship to dependency distance. A set of 220 sentences, with increasing grammatical difficulty as measured in a prior user study, were simplified by a human expert and using ChatGPT. We found that the three sentence sets all differed in mean dependency distances: the highest in the original sentence set, followed by ChatGPT simplified sentences, and the human simplified sentences showed the lowest mean dependency distance.