Sent2Matrix: Folding Character Sequences in Serpentine Manifolds for Two-Dimensional Sentence

TL;DR

Sent2Matrix introduces a novel 2-D text representation method that folds character sequences into serpentine manifolds, capturing both word morphology and boundaries, leading to improved text classification performance.

Contribution

This paper presents the first 2-D text representation method using serpentine folding, enhancing the encoding of morphological and boundary information.

Findings

Outperforms prior embedding methods in text classification

Effectively captures word morphology and boundaries

Visualizes text data in innovative 2-D formats

Abstract

We study text representation methods using deep models. Current methods, such as word-level embedding and character-level embedding schemes, treat texts as either a sequence of atomic words or a sequence of characters. These methods either ignore word morphologies or word boundaries. To overcome these limitations, we propose to convert texts into 2-D representations and develop the Sent2Matrix method. Our method allows for the explicit incorporation of both word morphologies and boundaries. When coupled with a novel serpentine padding method, our Sent2Matrix method leads to an interesting visualization in which 1-D character sequences are folded into 2-D serpentine manifolds. Notably, our method is the first attempt to represent texts in 2-D formats. Experimental results on text classification tasks shown that our method consistently outperforms prior embedding methods.