Style is NOT a single variable: Case Studies for Cross-Stylistic Language Understanding

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pages 2376–2387 August 1–6, 2021. ©2021 Association for Computational Linguistics 2376 Style is NOT a single variable: Case Studies for Cross-Style Language Understanding Dongyeop Kang∗ dongyeopk@berkeley.edu UC Berkeley Eduard Hovy hovy@cs.cmu.edu Carnegie Mellon University Abstract Every natural text is written in some style. Style is formed by a complex combination of different stylistic factors, including formality markers, emotions, metaphors, etc. One can- not form a complete understanding of a text without considering these factors. The fac- tors combine and co-vary in complex ways to form styles. Studying the nature of the co- varying combinations sheds light on stylistic language in general, sometimes called cross- style language understanding. This paper provides the benchmark corpus (XSLUE) that combines existing datasets and collects a new one for sentence-level cross-style language understanding and evaluation. The bench- mark contains text in 15 different styles un- der the proposed four theoretical groupings: figurative, personal, affective, and interper- sonal groups. For valid evaluation, we col- lect an additional diagnostic set by annotat- ing all 15 styles on the same text. Using XSLUE, we propose three interesting cross- style applications in classification, correlation, and generation. First, our proposed cross- style classifier trained with multiple styles together helps improve overall classification performance against individually-trained style classifiers. Second, our study shows that some styles are highly dependent on each other in human-written text. Finally, we find that com- binations of some contradictive styles likely generate stylistically less appropriate text. We believe our benchmark and case studies help explore interesting future directions for cross- style research. The preprocessed datasets and code are publicly available.1 1 Introduction People often use style as a strategic choice for their personal or social goals in communication (Hovy, ∗This work was done while DK was at CMU. 1https://github.com/dykang/xslue 1987; Silverstein, 2003; Jaffe et al., 2009; Kang, 2020). Some stylistic choices implicitly reflect the author’s characteristics, like personality, demo- graphic traits (Kang et al., 2019), and emotions (Buechel and Hahn, 2017), whereas others are ex- plicitly controlled by the author’s choices for their social goals like using polite language, for better relationship with the elder (Danescu et al., 2013). In this work, we broadly call each individual lin- guistic phenomena as one specific type of style. Style is not a single variable, but multiple vari- ables have their own degrees of freedom and they co-vary together. Imagine an orchestra, as a metaphor of style. What we hear from the orchestra is the harmonized sound of complex combinations of individual instruments played. A conductor, on top of it, controls their combinatory choices among them, such as tempo or score. Some instruments under the same category, such as violin and cello for bowed string type, make a similar pattern of sound. Similarly, text reflects complex combina- tion of multiple styles. Each has its own lexical and syntactic features and some are dependent on each other. Consistent combination …

Content truncated to 500 words