To Point or Not to Point: Understanding How Abstractive Summarizers Paraphrase Text

• URL: http://arxiv.org/abs/2106.01581v1
• Date: Thu, 3 Jun 2021 04:03:15 GMT
• Title: To Point or Not to Point: Understanding How Abstractive Summarizers Paraphrase Text
• Authors: Matt Wilber, William Timkey, Marten Van Schijndel
• Abstract summary: We characterize how one popular abstractive model, the pointer-generator model of See et al., uses its explicit copy/generation switch to control its level of abstraction. When we modify the copy/generation switch and force the model to generate, only simple neural abilities are revealed alongside factual inaccuracies and hallucinations. In line with previous research, these results suggest that abstractive summarization models lack the semantic understanding necessary to generate paraphrases that are both abstractive and faithful to the source document.
• Score: 4.4044968357361745
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Abstractive neural summarization models have seen great improvements in recent years, as shown by ROUGE scores of the generated summaries. But despite these improved metrics, there is limited understanding of the strategies different models employ, and how those strategies relate their understanding of language. To understand this better, we run several experiments to characterize how one popular abstractive model, the pointer-generator model of See et al. (2017), uses its explicit copy/generation switch to control its level of abstraction (generation) vs extraction (copying). On an extractive-biased dataset, the model utilizes syntactic boundaries to truncate sentences that are otherwise often copied verbatim. When we modify the copy/generation switch and force the model to generate, only simple paraphrasing abilities are revealed alongside factual inaccuracies and hallucinations. On an abstractive-biased dataset, the model copies infrequently but shows similarly limited abstractive abilities. In line with previous research, these results suggest that abstractive summarization models lack the semantic understanding necessary to generate paraphrases that are both abstractive and faithful to the source document.

Related papers

• Improving Sequence-to-Sequence Models for Abstractive Text Summarization Using Meta Heuristic Approaches [0.0]
  Humans have a unique ability to create abstractions. The use of sequence-to-sequence (seq2seq) models for neural abstractive text summarization has been ascending as far as prevalence. In this article, we aim toward enhancing the present architectures and models for abstractive text summarization.
  arXiv  Detail & Related papers  (2024-03-24T17:39:36Z)
• 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)
• mFACE: Multilingual Summarization with Factual Consistency Evaluation [79.60172087719356]
  Abstractive summarization has enjoyed renewed interest in recent years, thanks to pre-trained language models and the availability of large-scale datasets. Despite promising results, current models still suffer from generating factually inconsistent summaries. We leverage factual consistency evaluation models to improve multilingual summarization.
  arXiv  Detail & Related papers  (2022-12-20T19:52:41Z)
• Subjective Bias in Abstractive Summarization [11.675414451656568]
  We formulate the differences among possible multiple expressions summarizing the same content as subjective bias and examine the role of this bias in the context of abstractive summarization. Results of summarization models trained on style-clustered datasets show that there are certain types of styles that lead to better convergence, abstraction and generalization.
  arXiv  Detail & Related papers  (2021-06-18T12:17:55Z)
• Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection [54.38512834521367]
  We study contrast candidate generation and selection as a model-agnostic post-processing technique. We learn a discriminative correction model by generating alternative candidate summaries. This model is then used to select the best candidate as the final output summary.
  arXiv  Detail & Related papers  (2021-04-19T05:39:24Z)
• Understanding Neural Abstractive Summarization Models via Uncertainty [54.37665950633147]
  seq2seq abstractive summarization models generate text in a free-form manner. We study the entropy, or uncertainty, of the model's token-level predictions. We show that uncertainty is a useful perspective for analyzing summarization and text generation models more broadly.
  arXiv  Detail & Related papers  (2020-10-15T16:57:27Z)
• Multi-Fact Correction in Abstractive Text Summarization [98.27031108197944]
  Span-Fact is a suite of two factual correction models that leverages knowledge learned from question answering models to make corrections in system-generated summaries via span selection. Our models employ single or multi-masking strategies to either iteratively or auto-regressively replace entities in order to ensure semantic consistency w.r.t. the source text. Experiments show that our models significantly boost the factual consistency of system-generated summaries without sacrificing summary quality in terms of both automatic metrics and human evaluation.
  arXiv  Detail & Related papers  (2020-10-06T02:51:02Z)
• 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)
• Unsupervised Opinion Summarization with Noising and Denoising [85.49169453434554]
  We create a synthetic dataset from a corpus of user reviews by sampling a review, pretending it is a summary, and generating noisy versions thereof. At test time, the model accepts genuine reviews and generates a summary containing salient opinions, treating those that do not reach consensus as noise.
  arXiv  Detail & Related papers  (2020-04-21T16:54:57Z)

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.