Modeling the Music Genre Perception across Language-Bound Cultures

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 4765–4779, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 4765 Modeling the Music Genre Perception across Language-Bound Cultures Elena V. Epure1, Guillaume Salha1,2, Manuel Moussallam1, Romain Hennequin1 1 Deezer Research, Paris, France 2 LIX, ´Ecole Polytechnique, Palaiseau, France research@deezer.com Abstract The music genre perception expressed through human annotations of artists or albums varies significantly across language-bound cultures. These variations cannot be modeled as mere translations since we also need to account for cultural differences in the music genre per- ception. In this work, we study the feasibil- ity of obtaining relevant cross-lingual, culture- specific music genre annotations based only on language-specific semantic representations, namely distributed concept embeddings and ontologies. Our study, focused on six lan- guages, shows that unsupervised cross-lingual music genre annotation is feasible with high accuracy, especially when combining both types of representations. This approach of studying music genres is the most extensive to date and has many implications in musicol- ogy and music information retrieval. Besides, we introduce a new, domain-dependent cross- lingual corpus to benchmark state of the art multilingual pre-trained embedding models. 1 Introduction A prevalent approach to culturally study music gen- res starts with a common set of music items, e.g. artists, albums, tracks, and assumes that the same music genres would be associated with the items in all cultures (Ferwerda and Schedl, 2016; Skowron et al., 2017). However, music genres are subjective. Cultures themselves and individual musicological backgrounds influence the music genre perception, which can differ among individuals (Sordo et al., 2008; Lee et al., 2013). For instance, a Westerner may relate funk to soul and jazz, while a Brazil- ian to baile funk that is a type of rap (Hennequin et al., 2018). Thus, accounting for cultural dif- ferences in music genres’ perception could give a more grounded basis for such cultural studies. However, ensuring both a common set of music items and culture-sensitive annotations with broad coverage of music genres is strenuous (Bogdanov et al., 2019). To address this challenge, we study the feasi- bility of cross-culturally annotating music items with music genres, without relying on a parallel corpus. In this work, culture is related to a com- munity speaking the same language (Kramsch and Widdowson, 1998). The specific research ques- tion we build upon is: assuming consistent pat- terns of music genres association with music items within cultures, can a mapping between these pat- terns be learned by relying on language-specific semantic representations? It is worth noting that, since music genres fall within the class of Culture- Specific Items (Aixel´a, 1996; Newmark, 1988), cross-lingual annotation, in this case, cannot be framed as standard translation, as one also needs to model the dissimilar perception of music genres across cultures. Our work focuses on four language families, Germanic (English-en and Dutch-nl), Romance (Spanish-es and French-fr), Japonic (Japanese-ja), Slavic (Czech-cs), and on two types of language- specific semantic representations, ontologies and multi-word expression embeddings. First, ontologies are often used to …

Content truncated to 500 words