Sequential Short-Text Classification with Recurrent and Convolutional Neural Networks

TL;DR

This paper introduces a neural network model combining recurrent and convolutional layers to leverage sequential context in short-text classification, achieving state-of-the-art results on dialog act prediction datasets.

Contribution

The work presents a novel neural network architecture that incorporates preceding short texts for improved classification in sequential short-text scenarios.

Findings

Achieved state-of-the-art results on three dialog act datasets.

Effectively leverages sequence context for short-text classification.

Demonstrates superiority over existing models in sequential short-text tasks.

Abstract

Recent approaches based on artificial neural networks (ANNs) have shown promising results for short-text classification. However, many short texts occur in sequences (e.g., sentences in a document or utterances in a dialog), and most existing ANN-based systems do not leverage the preceding short texts when classifying a subsequent one. In this work, we present a model based on recurrent neural networks and convolutional neural networks that incorporates the preceding short texts. Our model achieves state-of-the-art results on three different datasets for dialog act prediction.