Acquiring a Formality-Informed Lexical Resource for Style Analysis

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, pages 2028–2041 April 19 - 23, 2021. ©2021 Association for Computational Linguistics 2028 Acquiring a Formality-Informed Lexical Resource for Style Analysis Elisabeth Eder1, Ulrike Krieg-Holz1, Udo Hahn2 1 Institut f¨ur Germanistik, Alpen-Adria-Universit¨at Klagenfurt, Klagenfurt, Austria 2 Jena University Language & Information Engineering (JULIE) Lab, Friedrich-Schiller-Universit¨at Jena, Jena, Germany {elisabeth.eder, ulrike.krieg-holz}@aau.at, udo.hahn@uni-jena.de Abstract To track different levels of formality in written discourse, we introduce a novel type of lexicon for the German language, with entries ordered by their degree of (in)formality. We start with a set of words extracted from traditional lexico- graphic resources, extend it by sentence-based similarity computations, and let crowdwork- ers assess the enlarged set of lexical items on a continuous informal-formal scale as a gold standard for evaluation. We submit this lex- icon to an intrinsic evaluation related to the best regression models and their effect on pre- dicting formality scores and complement our investigation by an extrinsic evaluation of for- mality on a German-language email corpus. 1 Introduction The computational treatment of style in verbal com- munication has long been dominated by applica- tion concerns, e.g., the identification or profiling of authors in forensic linguistics (Ding et al., 2019) or the recognition of plagiarism (Alzahrani et al., 2012). This research was conducted assuming that simple lexico-statistic patterns identified by stylo- metric computations were sufficient to solve au- thorship and plagiarism assignment problems. Despite their undisputed success in those limited fields, these studies scratched only the surface of the notion of ‘style’ as discussed in linguistic prag- matics (Hickey, 1993). From the many ways ‘style’ can be approached from a pragmatics perspective, we here focus on its inherent formality dimension, i.e., the distinction between formal (standard) and informal (colloquial) language use (for a survey, cf. Heylighen and Dewaele (1999)), with further ex- tensions directed at the higher level of formal (e.g., elevated style) and the lower level of informal (e.g., vulgar) phrasing. Such distinctions of formality levels are crucial for the appropriateness of verbal expressions in a given discourse context. In order to track different levels of formality in written communication, we introduce a novel type of lexicon for the German language, with entries ordered by their degree of (in)formality.1 We start with a set of words extracted from traditional lexico- graphic resources, extend it by sentence-based sim- ilarity computations, and let crowdworkers assess the enlarged set of lexical items on a continuous informal-formal scale. This workflow is described in Section 3. The resulting lexicon comprising words with their respective formality scores sub- sequently serves as a gold standard for evaluation. In Section 4, we submit this lexicon to an intrin- sic evaluation related to the best regression models and their effect on predicting formality scores, and complement our investigation by an extrinsic eval- uation of formality on a German-language email corpus in Section 5. 2 Related Work The relevance of ‘style’ for NLP is obvious for language output-focused core applications such …

Content truncated to 500 words