A Lexical, Syntactic, and Semantic Perspective for Understanding Style in Text

Abstract

With a growing interest in modeling inherent subjectivity in natural language, we present a linguistically-motivated process to understand and analyze the writing style of individuals from three perspectives: lexical, syntactic, and semantic. We discuss the stylistically expressive elements within each of these levels and use existing methods to quantify the linguistic intuitions related to some of these elements. We show that such a multi-level analysis is useful for developing a wellknit understanding of style -which is independent of the natural language task at hand, and also demonstrate its value in solving three downstream tasks: authors' style analysis, authorship attribution, and emotion prediction. We conduct experiments on a variety of datasets, comprising texts from social networking sites, user reviews, legal documents, literary books, and newswire. The results on the aforementioned tasks and datasets illustrate that such a multi-level understanding of style, which has been largely ignored in recent works, models style-related subjectivity in text and can be leveraged to improve performance on multiple downstream tasks both qualitatively and quantitatively.

StyleDGPT: Stylized Response Generation with Pre-trained Language Models

“…In terms of style consistency, existing work only measures the style intensity using classifiers (Gao et al, 2019). However, the style of text is an amalgam, and differences between two styles are reflected in multiple linguistic dimensions (Verma and Srinivasan, 2019). Thus, we propose to evaluate the style of response from three perspectives:…”

Style Control for Schema-Guided Natural Language Generation

“…Style parameters are features of text that are stylistically expressive. These parameters can be roughly identified at lexical (vocabulary and words), syntactic (sentence structure) and semantic (abstract meaning/emotion) levels (Verma and Srinivasan, 2019). We focus primarily on lexical and semantic features.…”

DRAG: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting

“…There has been significant work on understanding binary stylization along dimensions like formalinformal, positive-negative sentiment (Rao and Tetreault, 2018;Kessler et al, 1997;Pavlick and Tetreault, 2016;Collins-Thompson and Callan, 2005;Hovy, 1990;Inkpen and Hirst, 2006;Kantrowitz, 2003), however, there is limited work on understanding an author's writing style (Mc-Carthy et al, 2006;Forgeard, 2008;Verma and Srinivasan, 2019). While style can be a mixture of several factors including, but not limited to, lexical preferences, syntactic/sentential choices, discourse structure, narrative style, tone, we follow Syed et al (2020) and consider an author's style at three levels:…”

“…With recent advances in language modeling techniques that have resulted in powerful language models Devlin et al, 2018;Brown et al, 2020) along with an increased interest in stylized content generation, (Hu et al, 2017;Shen et al, 2017;Subramanian et al, 2018;Fu et al, 2018;Niu and Bansal, 2018), large language models have been successfully tuned to achieve text stylization (Lample et al, 2018;Ziegler et al, 2019;Syed et al, 2020;Singh et al, 2020). Apart from transferring an input text to the target style, which has received recent interest from the community, understanding and measuring style have been persistently explored over the last few decades (Kessler et al, 1997;Garera and Yarowsky, 2009;Liu, 2012;Verma and Srinivasan, 2019). Lying at the intersection of style transfer enabled by advanced language models and a deep understanding of style as a nuanced combination of several linguistic concepts, problems like stylized generation or stylized rewriting have gained further traction.…”