Robust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Abstractive Text SummarizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Robust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information
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 vuln…
Abstractive Text SummarizationGradient-Based Adversarial Factual Consistency Evaluation for Abstractive Summarization
Neural abstractive summarization systems have gained significant progress in recent years. However, abstractive summarization often produce inconsisitent statements or false facts. How to automatically generate highly ab…
Abstractive Text SummarizationData AugmentationFRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness
Despite being able to generate fluent and grammatical text, current Seq2Seq summarization models still suffering from the unfaithful generation problem. In this paper, we study the faithfulness of existing systems from a…
Abstractive Text SummarizationAttacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions
Large Language Models have introduced novel opportunities for text comprehension and generation. Yet, they are vulnerable to adversarial perturbations and data poisoning attacks, particularly in tasks like text classific…
Abstractive Text SummarizationAdversarial RobustnessData PoisoningReading Comprehension+3FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness
Though current Seq2Seq summarization models are capable of generating fluent and grammatical summaries, they are still suffering from the unfaithful generation problem.In this paper, we study the faithfulness of existing…
Abstractive Text Summarization