Cross-Cultural Similarity Features for Cross-Lingual Transfer Learning of Pragmatically Motivated Tasks

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, pages 2403–2414 April 19 - 23, 2021. ©2021 Association for Computational Linguistics 2403 Cross-Cultural Similarity Features for Cross-Lingual Transfer Learning of Pragmatically Motivated Tasks Jimin Sun1* Hwijeen Ahn2* Chan Young Park3* Yulia Tsvetkov3 David R. Mortensen3 1Seoul National University, Republic of Korea 2Sogang University, Republic of Korea 3Language Technologies Institute, Carnegie Mellon University, USA jiminsun@dm.snu.ac.kr, hwijeen@sogang.ac.kr, {chanyoun, ytsvetko, dmortens}@cs.cmu.edu Abstract Much work in cross-lingual transfer learning explored how to select better transfer lan- guages for multilingual tasks, primarily fo- cusing on typological and genealogical simi- larities between languages. We hypothesize that these measures of linguistic proximity are not enough when working with pragmatically- motivated tasks, such as sentiment analysis. As an alternative, we introduce three linguistic features that capture cross-cultural similarities that manifest in linguistic patterns and quantify distinct aspects of language pragmatics: lan- guage context-level, figurative language, and the lexification of emotion concepts. Our anal- yses show that the proposed pragmatic features do capture cross-cultural similarities and align well with existing work in sociolinguistics and linguistic anthropology. We further corrobo- rate the effectiveness of pragmatically-driven transfer in the downstream task of choosing transfer languages for cross-lingual sentiment analysis. 1 Introduction Hofstede et al. (2005) defined culture as the col- lective mind which “distinguishes the members of one group of people from another.” Cultural idiosyncrasies affect and shape people’s beliefs and behaviors. Linguists have particularly focused on the relationship between culture and language, revealing in qualitative case studies how cultural differences are manifested as linguistic variations (Siegel, 1977). Quantifying cross-cultural similarities from lin- guistic patterns has largely been unexplored in NLP, with the exception of studies that focused on cross-cultural differences in word usage (Garimella et al., 2016; Lin et al., 2018). In this work, we aim to quantify cross-cultural similarity, focusing *The first three authors contributed equally. on semantic and pragmatic differences across lan- guages.1 We devise a new distance measure be- tween languages based on linguistic proxies of cul- ture. We hypothesize that it can be used to se- lect transfer languages and improve cross-lingual transfer learning, specifically in pragmatically- motivated tasks such as sentiment analysis, since expressions of subtle sentiment or emotion—such as subjective well-being (Smith et al., 2016), anger (Oster, 2019), or irony (Karoui et al., 2017)—have been shown to vary significantly by culture. We focus on three distinct aspects in the intersec- tion of language and culture, and propose features to operationalize them. First, every language and culture rely on different levels of context in com- munication. Western European languages are gen- erally considered low-context languages, whereas Korean and Japanese are considered high-context languages (Hall, 1989). Second, similar cultures construct and construe figurative language simi- larly (Casas and Campoy, 1995; Vulanovi´c, 2014). Finally, emotion semantics is similar between lan- guages that are culturally-related (Jackson et al., 2019). For example, in Persian, ‘grief’ and ‘regret’ are expressed with the same word whereas ‘grief’ is co-lexified with ‘anxiety’ in Dargwa. There- fore, …

Content truncated to 500 words