Knowledge Enhanced Hybrid Neural Network for Text Matching

TL;DR

This paper introduces KEHNN, a neural network that incorporates prior knowledge into text matching, especially for long texts, by fusing knowledge into representations and combining multiple matching channels.

Contribution

It proposes a novel hybrid neural network model that integrates prior knowledge with word and sentence structure matching for improved semantic matching.

Findings

Significantly outperforms state-of-the-art models on public datasets.

Improves matching accuracy on long text pairs.

Effectively combines knowledge, local, and global sentence features.

Abstract

Long text brings a big challenge to semantic matching due to their complicated semantic and syntactic structures. To tackle the challenge, we consider using prior knowledge to help identify useful information and filter out noise to matching in long text. To this end, we propose a knowledge enhanced hybrid neural network (KEHNN). The model fuses prior knowledge into word representations by knowledge gates and establishes three matching channels with words, sequential structures of sentences given by Gated Recurrent Units (GRU), and knowledge enhanced representations. The three channels are processed by a convolutional neural network to generate high level features for matching, and the features are synthesized as a matching score by a multilayer perceptron. The model extends the existing methods by conducting matching on words, local structures of sentences, and global context of sentences. Evaluation results from extensive experiments on public data sets for question answering and conversation show that KEHNN can significantly outperform the-state-of-the-art matching models and particularly improve the performance on pairs with long text.