ALL-IN-1: Short Text Classification with One Model for All Languages
Published in
arXiv.org(2017)External Links:
TL
TL;DR
This work presents ALL-IN-1, a simple model for multilingual text classification that does not require any parallel data, based on a traditional Support Vector Machine classifier exploiting multilingual word embeddings and character n-grams.
Abstract
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.
References14 items
1
The Power of Character N-grams in Native Language Identification
2
A survey of cross-lingual embedding models
3
Findings of the VarDial Evaluation Campaign 2017
4
When Sparse Traditional Models Outperform Dense Neural Networks: the Curious Case of Discriminating between Similar Languages
5