Enhancing Sentence Relation Modeling with Auxiliary Character-level Embedding

TL;DR

This paper introduces a neural network architecture that combines pre-trained word embeddings with auxiliary character embeddings to improve sentence relation modeling, achieving better performance on standard datasets.

Contribution

The novel approach jointly leverages word and character embeddings within a deep neural network for enhanced sentence relation understanding.

Findings

Outperforms existing methods on standard datasets

Effectively captures complex semantic relations

Improves sentence matching accuracy

Abstract

Neural network based approaches for sentence relation modeling automatically generate hidden matching features from raw sentence pairs. However, the quality of matching feature representation may not be satisfied due to complex semantic relations such as entailment or contradiction. To address this challenge, we propose a new deep neural network architecture that jointly leverage pre-trained word embedding and auxiliary character embedding to learn sentence meanings. The two kinds of word sequence representations as inputs into multi-layer bidirectional LSTM to learn enhanced sentence representation. After that, we construct matching features followed by another temporal CNN to learn high-level hidden matching feature representations. Experimental results demonstrate that our approach consistently outperforms the existing methods on standard evaluation datasets.