Code-switching is commonly used in the free-form text environment, such as social media, and it is especially favored in emotion expressions. Emotions in codeswitching texts differ from monolingual texts in that they can be expressed in either monolingual or bilingual forms. In this paper, we first utilize two kinds of knowledge, i.e. bilingual and sentimental information to bridge the gap betw...

Poplack (1993: 255) defines code-switching as the juxtaposition of multi-word sequences, each of which is internally consistent with the grammatical patterns of its respective language. Thus, in code-switching, the patterns of each language are maintained, as bilinguals switch between— not ‘mix’—their two languages (cf. Haugen 1950). Some, however, have claimed that codeswitching can have an ef...

Abstract Viewed from an interactional sociolinguistic perspective, this research addresses multilingual codeswitching practices of youngsters with North African roots the super-diverse Flemish city Ghent. Particular attention is paid here to their artistic – mainly interethnic performances, as these play a vital role in constructing ethnic and social belonging by voicing “glocal” identities. In...

This paper analyses negotiation of meaning and codeswitching in discourse between 29 language students from classes at a German and a North American university, who teamed up with their peers to collaborate on projects whose results they had to present to the other groups in the MOO during the final weeks of the project. From October to December 1998, these learners, who formed a total of eight...

Multilingualism presents both a challenge and an opportunity for Natural Language Processing, with code-switching representing particularly interesting problem computational models trained on monolingual datasets. In this paper, we explore how code-switched data affects the task of Machine Translation, which only recently has started to tackle multilingual data. We test three Translation system...

This paper presents our latest investigations of the jointly trained maximum entropy and recurrent neural network language models for Code-Switching speech. First, we explore extensively the integration of part-of-speech tags and language identifier information in recurrent neural network language models for CodeSwitching. Second, the importance of the maximum entropy model is demonstrated alon...