Multi-Lingual Meta Embeddings in LinCE data set

Multilingual Meta-Embeddings (MME) leverage information from pre-trained mono-lingual embeddings. The exploited multi-lingual information can be effectively used in the code-mixed domain. This paper maneuvers MME to propose a language identification mechanism for code-mixed text. Empirical evaluation of conventional deep learning models in discrete, and permutated forms, GRU, LSTM, CRF, GRU with CRF, LSTM with CRF, LSTM with CNN, and GRU with CNN. Multi-Task Learning approach and evaluated our models on the Lince Hindi- English Code Mixed Language Identification data set.