English

Robust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information

Computation and Language 2018-10-16 v1

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-23T04:39:05.931Z