Cross-lingual syntactic variation over age and gender

Proceedings of the 19th Conference on Computational Language Learning, pages 103–112, Beijing, China, July 30-31, 2015. c⃝2015 Association for Computational Linguistics Cross-lingual syntactic variation over age and gender Anders Johannsen, Dirk Hovy, and Anders Søgaard Center for Language Technology University of Copenhagen, Denmark Njalsgade 140 {ajohannsen,dirk.hovy,soegaard}@hum.ku.dk Abstract Most computational sociolinguistics stud- ies have focused on phonological and lexical variation. We present the first large-scale study of syntactic variation among demographic groups (age and gen- der) across several languages. We har- vest data from online user-review sites and parse it with universal dependencies. We show that several age and gender-specific variations hold across languages, for ex- ample that women are more likely to use VP conjunctions. 1 Introduction Language varies between demographic groups. To detect this variation, sociolinguistic studies require both a representative corpus of text and meta-information about the speakers. Tradition- ally, this data was collected from a combination of interview transcriptions and questionnaires. Both methods are time-consuming, so population sizes have been small, sometimes including less than five subjects (Rickford and Price, 2013). While these resources enable detailed qualitative analy- ses, small sample sizes may lead to false research findings (Button et al., 2013). Sociolinguistic studies, in other words, often lack statistical power to establish relationships between language use and socio-economic variables. Obtaining large enough data sets becomes even more challenging the more complex the target variables are. So while syntactic variation has been identified as an important factor of variation (Cheshire, 2005), it was not approached, due to its high complexity. This paper addresses the issue systematically on a large scale. In contrast to pre- vious work in both sociolinguistics and NLP, we consider syntactic variation across groups at the level of treelets, as defined by dependency struc- tures, and make use of a large corpus that includes demographic information on both age and gender. The impact of such findings goes beyond soci- olinguistic insights: knowledge about systematic differences among demographic groups can help us build better and fairer NLP tools. Volkova et al. (2013), Hovy and Søgaard (2015), Jørgensen et al. (2015), and Hovy (2015) have shown the impact of demographic factors on NLP performance. Recently, the company Textio introduced a tool to help phrase job advertisements in a gender-neutral way.1 While their tool addresses lexical variation, our results indicate that linguistic differences extend to the syntactic level. Previous work on demographic variation in both sociolinguistics and NLP has begun to rely on cor- pora from social media, most prominently Twitter. Twitter offers a sufficiently large data source with broad coverage (albeit limited to users with access to social media). Indeed, results show that this resource reflects the phonological and morpho- lexical variation of spoken language (Eisenstein, 2013b; Eisenstein, 2013a; Doyle, 2014). However, Twitter is not well-suited for the study of syntactic variation for two reasons. First, the limited length of the posts compels the users to adopt a terse style that leaves out many grammatical markers. As a consequence, performance of syntactic parsers is prohibitive for …

Content truncated to 500 words