paper-with-me

홈 › Papers

On Faithfulness and Factuality in Abstractive Summarization

2020-05-02 · ACL 2020 6 · Joshua Maynez, Shashi Narayan, Bernd Bohnet, Ryan Mcdonald

It is well known that the standard likelihood training and approximate decoding objectives in neural text generation models lead to less human-like responses for open-ended tasks such as language modeling and story generation. In this paper we have analyzed limitations of these models for abstractive document summarization and found that these models are highly prone to hallucinate content that is unfaithful to the input document. We conducted a large scale human evaluation of several neural abstractive summarization systems to better understand the types of hallucinations they produce. Our human annotators found substantial amounts of hallucinated content in all model generated summaries. However, our analysis does show that pretrained models are better summarizers not only in terms of raw metrics, i.e., ROUGE, but also in generating faithful and factual summaries as evaluated by humans. Furthermore, we show that textual entailment measures better correlate with faithfulness than standard metrics, potentially leading the way to automatic evaluation metrics as well as training and decoding criteria.

📄 PDF Abstract BibTeX arXiv:2005.00661

Code (2)

google-research-datasets/xsum_hallucination_annotations 공식 구현
tagoyal/factuality-datasets pytorch

Tasks

Abstractive Text SummarizationDocument SummarizationLanguage ModelingLanguage ModellingNatural Language InferenceStory GenerationText Generation

Similar Papers 제목 키워드 기반

Evaluating the Tradeoff Between Abstractiveness and Factuality in Abstractive Summarization

2021-08-05 · Markus Dreyer, Mengwen Liu, Feng Nan, Sandeep Atluri 외

Neural models for abstractive summarization tend to generate output that is fluent and well-formed but lacks semantic faithfulness, or factuality, with respect to the input documents. In this paper, we analyze the tradeo…

Abstractive Text Summarization

Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive Summarization

2021-08-31 · ACL 2022 5 · Faisal Ladhak, Esin Durmus, He He, Claire Cardie 외

Despite recent progress in abstractive summarization, systems still suffer from faithfulness errors. While prior work has proposed models that improve faithfulness, it is unclear whether the improvement comes from an inc…

Abstractive Text Summarization

Faithful to the Document or to the World? Mitigating Hallucinations via Entity-linked Knowledge in Abstractive Summarization

2022-04-28 · Yue Dong, John Wieting, Pat Verga

Despite recent advances in abstractive summarization, current summarization systems still suffer from content hallucinations where models generate text that is either irrelevant or contradictory to the source document. H…

Abstractive Text SummarizationWorld Knowledge

Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive Summarization

2021-10-16 · ACL ARR October 2021 10 · Anonymous

Despite recent progress in abstractive summarization, systems still suffer from faithfulness errors. While prior work has proposed models that improve faithfulness, it is unclear whether the improvement comes from an inc…

Abstractive Text Summarization

CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization

2021-09-19 · EMNLP 2021 11 · Shuyang Cao, Lu Wang

We study generating abstractive summaries that are faithful and factually consistent with the given articles. A novel contrastive learning formulation is presented, which leverages both reference summaries, as positive t…

Abstractive Text SummarizationArticlesContrastive LearningReranking