A Semantic Relevance Based Neural Network for Text Summarization and Text Simplification

TL;DR

This paper introduces a neural network model that enhances semantic relevance in text summarization and simplification, leading to more meaningful and accurate simplified texts for diverse readers.

Contribution

The paper proposes a semantic relevance-based neural model that improves the semantic similarity between source and simplified texts in summarization and simplification tasks.

Findings

Outperforms state-of-the-art systems on benchmark datasets

Achieves higher semantic relevance in generated texts

Improves quality of simplified texts for poor readers

Abstract

Text summarization and text simplification are two major ways to simplify the text for poor readers, including children, non-native speakers, and the functionally illiterate. Text summarization is to produce a brief summary of the main ideas of the text, while text simplification aims to reduce the linguistic complexity of the text and retain the original meaning. Recently, most approaches for text summarization and text simplification are based on the sequence-to-sequence model, which achieves much success in many text generation tasks. However, although the generated simplified texts are similar to source texts literally, they have low semantic relevance. In this work, our goal is to improve semantic relevance between source texts and simplified texts for text summarization and text simplification. We introduce a Semantic Relevance Based neural model to encourage high semantic similarity between texts and summaries. In our model, the source text is represented by a gated attention encoder, while the summary representation is produced by a decoder. Besides, the similarity score between the representations is maximized during training. Our experiments show that the proposed model outperforms the state-of-the-art systems on two benchmark corpus.