Multilingual users of social media sometimes use multiple languages during conversation. Mixing multiple languages in content known as code-mixing. We annotate a subset of a trilingual code-mixed corpus (Barman al., 2014) with part-of-speech (POS) tags. investigate two state-of-the-art POS tagging techniques for code-mixed content and the features of the two systems to a better POS tagger. Furthermore, we the use of a joint model which performs language identification (LID) and partof-speech (POS) tagging simultaneously.
No takes yet. Share an insight, caveat, or question.
Barman et al. (2016) studied this question.