paper-with-me

홈 › Papers

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

2021-06-03 · Findings (ACL) 2021 8 · Matt Wilber, William Timkey, Marten Van Schijndel

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.

📄 PDF Abstract BibTeX arXiv:2106.01581

Code (0)

등록된 구현이 없습니다.

Tasks

Abstractive Text Summarization

Similar Papers 제목 키워드 기반

Understanding Points of Correspondence between Sentences for Abstractive Summarization

2020-06-10 · ACL 2020 6 · Logan Lebanoff, John Muchovej, Franck Dernoncourt, Doo Soon Kim 외

Fusing sentences containing disparate content is a remarkable human ability that helps create informative and succinct summaries. Such a simple task for humans has remained challenging for modern abstractive summarizers,…

Abstractive Text Summarizationcoreference-resolutionCoreference ResolutionSentence+1

Assessing LLMs for Zero-shot Abstractive Summarization Through the Lens of Relevance Paraphrasing

2024-06-06 · Hadi Askari, Anshuman Chhabra, Muhao Chen, Prasant Mohapatra

Large Language Models (LLMs) have achieved state-of-the-art performance at zero-shot generation of abstractive summaries for given articles. However, little is known about the robustness of such a process of zero-shot su…

Abstractive Text SummarizationArticles

Understanding the Behaviour of Neural Abstractive Summarizers using Contrastive Examples

2019-06-01 · NAACL 2019 6 · Krtin Kumar, Jackie Chi Kit Cheung

Neural abstractive summarizers generate summary texts using a language model conditioned on the input source text, and have recently achieved high ROUGE scores on benchmark summarization datasets. We investigate how they…

Language ModelingLanguage Modelling

Analyzing Sentence Fusion in Abstractive Summarization

2019-10-01 · WS 2019 11 · Logan Lebanoff, John Muchovej, Franck Dernoncourt, Doo Soon Kim 외

While recent work in abstractive summarization has resulted in higher scores in automatic metrics, there is little understanding on how these systems combine information taken from multiple document sentences. In this pa…

Abstractive Text SummarizationSentenceSentence Fusion

Semantic Extractor-Paraphraser based Abstractive Summarization

2021-05-04 · ICON 2020 12 · Anubhav Jangra, Raghav Jain, Vaibhav Mavi, Sriparna Saha 외

The anthology of spoken languages today is inundated with textual information, necessitating the development of automatic summarization models. In this manuscript, we propose an extractor-paraphraser based abstractive su…

Abstractive Text Summarization