Reducing Quantity Hallucinations in Abstractive Summarization

• URL: http://arxiv.org/abs/2009.13312v1
• Date: Mon, 28 Sep 2020 13:32:59 GMT
• Title: Reducing Quantity Hallucinations in Abstractive Summarization
• Authors: Zheng Zhao, Shay B. Cohen, Bonnie Webber
• Abstract summary: Herman learns to recognize and verify quantity entities (dates, numbers, sums of money, etc.) in a beam-worth of abstractive summaries. Experimental results demonstrate that the ROUGE scores of such up-ranked summaries have a higher Precision than summaries that have not been up-ranked. Preliminary human evaluation of up-ranked vs. original summaries shows people's preference for the former.
• Score: 32.89486074807331
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: It is well-known that abstractive summaries are subject to hallucination---including material that is not supported by the original text. While summaries can be made hallucination-free by limiting them to general phrases, such summaries would fail to be very informative. Alternatively, one can try to avoid hallucinations by verifying that any specific entities in the summary appear in the original text in a similar context. This is the approach taken by our system, Herman. The system learns to recognize and verify quantity entities (dates, numbers, sums of money, etc.) in a beam-worth of abstractive summaries produced by state-of-the-art models, in order to up-rank those summaries whose quantity terms are supported by the original text. Experimental results demonstrate that the ROUGE scores of such up-ranked summaries have a higher Precision than summaries that have not been up-ranked, without a comparable loss in Recall, resulting in higher F$_1$. Preliminary human evaluation of up-ranked vs. original summaries shows people's preference for the former.

Related papers

• AugSumm: towards generalizable speech summarization using synthetic labels from large language model [61.73741195292997]
  Abstractive speech summarization (SSUM) aims to generate human-like summaries from speech. conventional SSUM models are mostly trained and evaluated with a single ground-truth (GT) human-annotated deterministic summary. We propose AugSumm, a method to leverage large language models (LLMs) as a proxy for human annotators to generate augmented summaries.
  arXiv  Detail & Related papers  (2024-01-10T18:39:46Z)
• Correction with Backtracking Reduces Hallucination in Summarization [29.093092115901694]
  Abstractive summarization aims at generating natural language summaries of a source document that are succinct while preserving the important elements. Despite recent advances, neural text summarization models are known to be susceptible to hallucinating. We introduce a simple yet efficient technique, CoBa, to reduce hallucination in abstractive summarization.
  arXiv  Detail & Related papers  (2023-10-24T20:48:11Z)
• Enhancing Abstractiveness of Summarization Models through Calibrated Distillation [30.199051061633803]
  DisCal is a novel approach to enhance the level of abstractiveness without sacrificing informativeness. Our experiments show that DisCal outperforms prior methods in abstractive summarization distillation.
  arXiv  Detail & Related papers  (2023-10-20T18:43:49Z)
• Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback [57.816210168909286]
  We leverage recent progress on textual entailment models to address this problem for abstractive summarization systems. We use reinforcement learning with reference-free, textual entailment rewards to optimize for factual consistency. Our results, according to both automatic metrics and human evaluation, show that our method considerably improves the faithfulness, salience, and conciseness of the generated summaries.
  arXiv  Detail & Related papers  (2023-05-31T21:04:04Z)
• Generating Multiple-Length Summaries via Reinforcement Learning for Unsupervised Sentence Summarization [44.835811239393244]
  Sentence summarization shortens given texts while maintaining core contents of the texts. Unsupervised approaches have been studied to summarize texts without human-written summaries. We devise an abstractive model based on reinforcement learning without ground-truth summaries.
  arXiv  Detail & Related papers  (2022-12-21T08:34:28Z)
• Salience Allocation as Guidance for Abstractive Summarization [61.31826412150143]
  We propose a novel summarization approach with a flexible and reliable salience guidance, namely SEASON (SaliencE Allocation as Guidance for Abstractive SummarizatiON) SEASON utilizes the allocation of salience expectation to guide abstractive summarization and adapts well to articles in different abstractiveness.
  arXiv  Detail & Related papers  (2022-10-22T02:13:44Z)
• Don't Say What You Don't Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Search [54.286450484332505]
  We analyze the connection between hallucinations and training data, and find evidence that models hallucinate because they train on target summaries that are unsupported by the source. We present PINOCCHIO, a new decoding method that improves the consistency of a transformer-based abstractive summarizer by constraining beam search to avoid hallucinations.
  arXiv  Detail & Related papers  (2022-03-16T07:13:52Z)
• Inspecting the Factuality of Hallucinated Entities in Abstractive Summarization [36.052622624166894]
  State-of-the-art abstractive summarization systems often generate emphhallucinations; i.e., content that is not directly inferable from the source text. We propose a novel detection approach that separates factual from non-factual hallucinations of entities.
  arXiv  Detail & Related papers  (2021-08-30T15:40:52Z)
• Few-Shot Learning for Opinion Summarization [117.70510762845338]
  Opinion summarization is the automatic creation of text reflecting subjective information expressed in multiple documents. In this work, we show that even a handful of summaries is sufficient to bootstrap generation of the summary text. Our approach substantially outperforms previous extractive and abstractive methods in automatic and human evaluation.
  arXiv  Detail & Related papers  (2020-04-30T15:37:38Z)
• Enhancing Factual Consistency of Abstractive Summarization [57.67609672082137]
  We propose a fact-aware summarization model FASum to extract and integrate factual relations into the summary generation process. We then design a factual corrector model FC to automatically correct factual errors from summaries generated by existing systems.
  arXiv  Detail & Related papers  (2020-03-19T07:36:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.