Sentence-level Rewriting Detection

Abstract

Writers usually need iterations of revisions and edits during their writings. To better understand the process of rewriting, we need to know what has changed between the revisions. Prior work mainly focuses on detecting corrections within sentences, which is at the level of words or phrases. This paper proposes to detect revision changes at the sentence level. Looking at revisions at a higher level allows us to have a different understanding of the revision process. This paper also proposes an approach to automatically detect sentence revision changes. The proposed approach shows high accuracy in an evaluation using first and final draft essays from an undergraduate writing class.

Using Context to Predict the Purpose of Argumentative Writing Revisions

“…Our prior work (Zhang and Litman, 2014) proposed an approach for the alignment of sentences. The approach achieves 92% accuracy on both corpora.…”

ArgRewrite: A Web-based Revision Assistant for Argumentative Writings

“…Tutorial to the web and java interface: www.cs.pitt.edu/ zhangfan/argrewrite/tutorial.pdf aligned pairs where the sentences in the pair are not identical are extracted as revisions. We first use the Stanford Parser (Klein and Manning, 2003) to break the original text into sentences and then align the sentences using the algorithm in our prior work (Zhang and Litman, 2014) which considers both sentence similarity (calculated using TF*IDF score) and the global context of sentences. Revision classification.…”

“…We argue that an intelligent writing assistant ought to be aware of the revision process; it should: 1) identify all significant changes made by a writer between the essay drafts, 2) automatically determine the purposes of these changes, 3) provide the writer the means to compare between drafts in an easy to understand visualization, and 4) support instructor monitoring and corrections in the revision process as well. In our previous work (Zhang and Litman, 2014;Zhang and Litman, 2015), we focused on 1) and 2), the automatic extraction and classification of revisions for argumentative writings. In this work, we extend our framework to integrate the automatic analyzer with a web-based interface to support student argumentative writings.…”

An Empirical Analysis of Edit Importance between Document Versions

“…We use the sentence alignment module proposed by Zhang et al (Zhang and Litman, 2014) to obtain the mapped pairs of sentences (s, s ), where s represents a sentence in the first version d and s is its modified variant in d .…”