A Framework for Translating SMS Messages

Short Messaging Service (SMS) has become a popular form of communication. While it is predominantly used for monolingual communication, it can be extremely useful for facilitating cross-lingual communication through statistical machine translation. In this work we present an application of statistical machine translation to SMS messages. We decouple the SMS translation task into normalization followed by translation so that one can exploit existing bitext resources and present a novel unsupervised normalization approach using distributed representation of words learned through neural networks. We describe several surrogate data that are good approximations to real SMS data feeds and use a hybrid translation approach using finite-state transducers. Both objective and subjective evaluation indicate that our approach is highly suitable for translating SMS messages.