AC-BLSTM: Asymmetric Convolutional Bidirectional LSTM Networks for Text Classification

TL;DR

This paper introduces AC-BLSTM, a novel neural network combining asymmetric convolution and bidirectional LSTM for improved text classification, achieving state-of-the-art results across multiple tasks, and further enhances performance with a semi-supervised G-AC-BLSTM framework.

Contribution

The paper presents a new AC-BLSTM model that integrates ACNN with BLSTM for better text classification, and proposes a semi-supervised G-AC-BLSTM to further boost accuracy.

Findings

Achieves state-of-the-art results on five text classification tasks.

Demonstrates the effectiveness of combining ACNN with BLSTM.

Semi-supervised G-AC-BLSTM improves performance further.

Abstract

Recently deeplearning models have been shown to be capable of making remarkable performance in sentences and documents classification tasks. In this work, we propose a novel framework called AC-BLSTM for modeling sentences and documents, which combines the asymmetric convolution neural network (ACNN) with the Bidirectional Long Short-Term Memory network (BLSTM). Experiment results demonstrate that our model achieves state-of-the-art results on five tasks, including sentiment analysis, question type classification, and subjectivity classification. In order to further improve the performance of AC-BLSTM, we propose a semi-supervised learning framework called G-AC-BLSTM for text classification by combining the generative model with AC-BLSTM.