Towards a model of formal and informal address in English

Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, pages 623–633, Avignon, France, April 23 - 27 2012. c⃝2012 Association for Computational Linguistics Towards a model of formal and informal address in English Manaal Faruqui Computer Science and Engineering Indian Institute of Technology Kharagpur, India manaalfar@gmail.com Sebastian Padó Institute of Computational Linguistics Heidelberg University Heidelberg, Germany pado@cl.uni-heidelberg.de Abstract Informal and formal (“T/V”) address in dia- logue is not distinguished overtly in mod- ern English, e.g. by pronoun choice like in many other languages such as French (“tu”/“vous”). Our study investigates the status of the T/V distinction in English liter- ary texts. Our main findings are: (a) human raters can label monolingual English utter- ances as T or V fairly well, given sufficient context; (b), a bilingual corpus can be ex- ploited to induce a supervised classifier for T/V without human annotation. It assigns T/V at sentence level with up to 68% accu- racy, relying mainly on lexical features; (c), there is a marked asymmetry between lex- ical features for formal speech (which are conventionalized and therefore general) and informal speech (which are text-specific). 1 Introduction In many Indo-European languages, there are two pronouns corresponding to the English you. This distinction is generally referred to as the T/V di- chotomy, from the Latin pronouns tu (informal, T) and vos (formal, V) (Brown and Gilman, 1960). The V form (such as Sie in German and Vous in French) can express neutrality or polite distance and is used to address social superiors. The T form (German du, French tu) is employed towards friends or addressees of lower social standing, and implies solidarity or lack of formality. English used to have a T/V distinction until the 18th century, using you as V pronoun and thou for T. However, in contemporary English, you has taken over both uses, and the T/V distinction is not marked anymore. In NLP, this makes generation in English and translation into English easy. Con- versely, many NLP tasks suffer from the lack of information about formality, e.g. the extraction of social relationships or, notably, machine transla- tion from English into languages with a T/V dis- tinction which involves a pronoun choice. In this paper, we investigate the possibility to recover the T/V distinction for (monolingual) sen- tences of 19th and 20th-century English such as: (1) Can I help you, Sir? (V) (2) You are my best friend! (T) After describing the creation of an English corpus of T/V labels via annotation projection (Section 3), we present an annotation study (Section 4) which establishes that taggers can indeed assign T/V la- bels to monolingual English utterances in context fairly reliably. Section 5 investigates how T/V is expressed in English texts by experimenting with different types of features, including words, seman- tic classes, and expressions based on Politeness Theory. We find word features to be most reliable, obtaining an accuracy of close to 70%. 2 Related Work There is a large body of work on the …

Content truncated to 500 words