Abstractive Summarization Improved by WordNet-based Extractive Sentences

TL;DR

This paper introduces a novel abstractive summarization method that integrates WordNet-based extractive sentence ranking with a dual attentional seq2seq model, enhancing semantic relevance and addressing OOV and duplication issues, achieving competitive results.

Contribution

It proposes a combined extractive-abstractive framework using WordNet for sentence selection and a dual attention model, improving semantic relevance and handling OOV and duplicate words.

Findings

Achieves competitive ROUGE scores on CNN/Daily Mail dataset.

Human evaluations confirm high semantic relevance of summaries.

Effectively addresses OOV and duplicate word problems.

Abstract

Recently, the seq2seq abstractive summarization models have achieved good results on the CNN/Daily Mail dataset. Still, how to improve abstractive methods with extractive methods is a good research direction, since extractive methods have their potentials of exploiting various efficient features for extracting important sentences in one text. In this paper, in order to improve the semantic relevance of abstractive summaries, we adopt the WordNet based sentence ranking algorithm to extract the sentences which are most semantically to one text. Then, we design a dual attentional seq2seq framework to generate summaries with consideration of the extracted information. At the same time, we combine pointer-generator and coverage mechanisms to solve the problems of out-of-vocabulary (OOV) words and duplicate words which exist in the abstractive models. Experiments on the CNN/Daily Mail dataset show that our models achieve competitive performance with the state-of-the-art ROUGE scores. Human evaluations also show that the summaries generated by our models have high semantic relevance to the original text.