Named Entity Recognition for Code-Mixed Indian Corpus using Meta Embedding

In this paper, we utilize the pre-trained embedding, sub-word embedding and closely related languages of languages in the code mixed corpus to create a meta-embedding. We then use the Transformer to encode the code mixed sentence and use Conditional Random Field to predict the Named Entities in the code-mixed text. In contrast to classical Named Entity recognition where the text is monolingual, our approach can predict the Named Entities in code-mixed corpus written both in the native script as well as Roman script. Our method is a novel method to combine the embeddings of closely related languages to identify Named Entity from Code-Mixed Indian text written using native script and Roman script in social media.