ALL-IN-1: Short Text Classification with One Model for All Languages
It addresses the problem of handling multiple languages in text classification for applications like customer feedback, though it is incremental as it builds on existing methods.
The paper tackled multilingual text classification without parallel data by developing ALL-IN-1, a model using SVM with multilingual embeddings and character n-grams, which achieved first place in a shared task on customer feedback analysis across four languages.
We present ALL-IN-1, a simple model for multilingual text classification that does not require any parallel data. It is based on a traditional Support Vector Machine classifier exploiting multilingual word embeddings and character n-grams. Our model is simple, easily extendable yet very effective, overall ranking 1st (out of 12 teams) in the IJCNLP 2017 shared task on customer feedback analysis in four languages: English, French, Japanese and Spanish.