We present an end-to-end multi-scale Convolutional Neural
Network (CNN) framework for topic identification (topic ID).
In this work, we examined multi-scale CNN for classification
using raw text input. Topical word embeddings are learnt at
multiple scales using parallel convolutional layers. A technique
to integrate verification and identification objectives is
examined to improve topic ID performance. With this approach,
we achieved significant improvement in identification
task. We evaluated our framework on two contrasting
datasets: 20 newsgroups and Fisher. We obtained 92.93% accuracy
on Fisher and 86.12% on 20 newsgroups, which to our
knowledge are the best published results on these datasets at
the moment.