Fast and Accurate Prediction of Sentence Specificity

• DOI: 10.1609/aaai.v29i1.9517
• Publication Date: 2022-06-23T12:10:24Z
• Authors: Junyi Li; Ani Nenkova
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

Recent studies have demonstrated that specificity is an important characterization of texts potentially beneficial for a range applications such as multi-document news summarization and analysis science journalism. The feasibility automatically predicting sentence from rich set features has also been confirmed in prior work. In this paper we present practical system which exploits only require minimum processing trained semi-supervised manner. Our outperforms the state-of-the-art method does not part speech tagging or syntactic parsing methods did. With tool developed --- Speciteller study role simplification. We show useful indicator finding sentences need to be simplified objective simplification, descriptive differences between original sentences.