A General-Purpose Tagger with Convolutional Neural Networks

Abstract

We present a general-purpose tagger based on convolutional neural networks (CNN), used for both composing word vectors and encoding context information. The CNN tagger is robust across different tagging tasks: without task-specific tuning of hyper-parameters, it achieves state-of-theart results in part-of-speech tagging, morphological tagging and supertagging. The CNN tagger is also robust against the outof-vocabulary problem; it performs well on artificially unnormalized texts.

4 Figures and Tables

Cite this paper

@inproceedings{Yu2017AGT, title={A General-Purpose Tagger with Convolutional Neural Networks}, author={Xiang Yu and Agnieszka Falenska and Ngoc Thang Vu}, booktitle={SWCN@EMNLP}, year={2017} }