Adaptive Region Embedding for Text Classification

TL;DR

This paper introduces an adaptive region embedding method that learns context representations for text classification, outperforming existing models by being more flexible and parameter-efficient.

Contribution

The paper proposes a novel adaptive region embedding approach with a meta-network for generating context matrices, improving text classification accuracy.

Findings

Achieves state-of-the-art results on 8 benchmark datasets.

Effectively captures context information and reduces word ambiguity.

Contains fewer parameters than previous context modeling models.

Abstract

Deep learning models such as convolutional neural networks and recurrent networks are widely applied in text classification. In spite of their great success, most deep learning models neglect the importance of modeling context information, which is crucial to understanding texts. In this work, we propose the Adaptive Region Embedding to learn context representation to improve text classification. Specifically, a metanetwork is learned to generate a context matrix for each region, and each word interacts with its corresponding context matrix to produce the regional representation for further classification. Compared to previous models that are designed to capture context information, our model contains less parameters and is more flexible. We extensively evaluate our method on 8 benchmark datasets for text classification. The experimental results prove that our method achieves state-of-the-art performances and effectively avoids word ambiguity.