Sequence-to-sequence (seq2seq) neural models have been actively investigated for abstractive summarization. Nevertheless, existing neural abstractive systems frequently generate factually incorrect summaries and are vulnerable to adversarial information, suggesting a crucial lack of semantic understanding. In this paper, we propose a novel semantic-aware neural abstractive summarization model that learns to generate high quality summaries through semantic interpretation over salient content. A novel evaluation scheme with adversarial samples is introduced to measure how well a model identifies off-topic information, where our model yields significantly better performance than the popular pointer-generator summarizer. Human evaluation also confirms that our system summaries are uniformly more informative and faithful as well as less redundant than the seq2seq model.
@article{arxiv.1810.06065,
title = {Robust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information},
author = {Lisa Fan and Dong Yu and Lu Wang},
journal= {arXiv preprint arXiv:1810.06065},
year = {2018}
}