paper-with-me

Papers

Controlling Decoding for More Abstractive Summaries with Copy-Based Networks

2018-03-19 · Noah Weber, Leena Shekhar, Niranjan Balasubramanian, Kyunghyun Cho

Attention-based neural abstractive summarization systems equipped with copy mechanisms have shown promising results. Despite this success, it has been noticed that such a system generates a summary by mostly, if not entirely, copying over phrases, sentences, and sometimes multiple consecutive sentences from an input paragraph, effectively performing extractive summarization. In this paper, we verify this behavior using the latest neural abstractive summarization system - a pointer-generator network. We propose a simple baseline method that allows us to control the amount of copying without retraining. Experiments indicate that the method provides a strong baseline for abstractive systems looking to obtain high ROUGE scores while minimizing overlap with the source article, substantially reducing the n-gram overlap with the original article while keeping within 2 points of the original model's ROUGE score.

📄 PDF Abstract BibTeX arXiv:1803.07038

Code (0)

등록된 구현이 없습니다.

Tasks

Abstractive Text SummarizationExtractive Summarization

Similar Papers 제목 키워드 기반

Controlling the Amount of Verbatim Copying in Abstractive Summarization

2019-11-23 · Kaiqiang Song, Bingqing Wang, Zhe Feng, Liu Ren 외

An abstract must not change the meaning of the original text. A single most effective way to achieve that is to increase the amount of copying while still allowing for text abstraction. Human editors can usually exercise…

Abstractive Text SummarizationLanguage ModelingLanguage ModellingText Summarization

Learning with Rejection for Abstractive Text Summarization

2023-02-16 · Meng Cao, Yue Dong, Jingyi He, Jackie Chi Kit Cheung

State-of-the-art abstractive summarization systems frequently hallucinate content that is not supported by the source document, mainly due to noise in the training dataset. Existing methods opt to drop the noisy samples …

Abstractive Text SummarizationText Summarization

Sentence-level Planning for Especially Abstractive Summarization

2021-11-01 · EMNLP (newsum) 2021 11 · Andreas Marfurt, James Henderson

Abstractive summarization models heavily rely on copy mechanisms, such as the pointer network or attention, to achieve good performance, measured by textual overlap with reference summaries. As a result, the generated su…

Abstractive Text SummarizationDecoderSentence

Generating Abstractive Summaries with Finetuned Language Models

2019-10-01 · WS 2019 10 · Sebastian Gehrmann, Zachary Ziegler, Alex Rush, er

Neural abstractive document summarization is commonly approached by models that exhibit a mostly extractive behavior. This behavior is facilitated by a copy-attention which allows models to copy words from a source docum…

Document SummarizationInductive BiasNews SummarizationTransfer Learning

VAE-PGN based Abstractive Model in Multi-stage Architecture for Text Summarization

2019-10-01 · WS 2019 10 · Hyungtak Choi, Lohith Ravuru, Tomasz Dryja{\'n}ski, Sunghan Rye 외

This paper describes our submission to the TL;DR challenge. Neural abstractive summarization models have been successful in generating fluent and consistent summaries with advancements like the copy (Pointer-generator) a…

Abstractive Text SummarizationExtractive SummarizationSentenceText Summarization