paper-with-me

홈 › Papers

Counterfactual Data Augmentation improves Factuality of Abstractive Summarization

2022-05-25 · Dheeraj Rajagopal, Siamak Shakeri, Cicero Nogueira dos santos, Eduard Hovy, Chung-Ching Chang

Abstractive summarization systems based on pretrained language models often generate coherent but factually inconsistent sentences. In this paper, we present a counterfactual data augmentation approach where we augment data with perturbed summaries that increase the training data diversity. Specifically, we present three augmentation approaches based on replacing (i) entities from other and the same category and (ii) nouns with their corresponding WordNet hypernyms. We show that augmenting the training data with our approach improves the factual correctness of summaries without significantly affecting the ROUGE score. We show that in two commonly used summarization datasets (CNN/Dailymail and XSum), we improve the factual correctness by about 2.5 points on average

📄 PDF Abstract BibTeX arXiv:2205.12416

Code (0)

등록된 구현이 없습니다.

Tasks

Abstractive Text SummarizationcounterfactualData AugmentationDiversity

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

Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization

2021-08-30 · ACL 2022 5 · Meng Cao, Yue Dong, Jackie Chi Kit Cheung

State-of-the-art abstractive summarization systems often generate \emph{hallucinations}; i.e., content that is not directly inferable from the source text. Despite being assumed incorrect, we find that much hallucinated …

Abstractive Text SummarizationReinforcement Learning (RL)World Knowledge

FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization

2022-05-16 · NAACL 2022 7 · David Wan, Mohit Bansal

We present FactPEGASUS, an abstractive summarization model that addresses the problem of factuality during pre-training and fine-tuning: (1) We augment the sentence selection strategy of PEGASUS's (Zhang et al., 2020) pr…

Abstractive Text SummarizationContrastive LearningSentence

Improving Factuality of Abstractive Summarization via Contrastive Reward Learning

2023-07-10 · I-Chun Chern, Zhiruo Wang, Sanjan Das, Bhavuk Sharma 외

Modern abstractive summarization models often generate summaries that contain hallucinated or contradictory information. In this paper, we propose a simple but effective contrastive learning framework that incorporates r…

Abstractive Text SummarizationContrastive Learning

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