Aicyber's System for NLPCC 2017 Shared Task 2: Voting of Baselines

TL;DR

This paper describes Aicyber's ensemble system for NLPCC 2017 shared task 2, combining deep learning models with traditional bag-of-word methods to improve performance.

Contribution

The paper introduces a novel voting ensemble that integrates deep learning and traditional models for Chinese text classification.

Findings

Voting ensemble outperforms individual models

Deep learning models leverage character-enhanced word vectors

Traditional bag-of-word model contributes to overall accuracy

Abstract

This paper presents Aicyber's system for NLPCC 2017 shared task 2. It is formed by a voting of three deep learning based system trained on character-enhanced word vectors and a well known bag-of-word model.