mlsanityData to 7 Oct 2026

Entity-based SpanCopy for Abstractive Summarization to Improve the Factual Consistency

arXiv 2209.03479 ↗First posted 7 Sep 2022cs.CLcited by 11

Not on the map. Why?

Abstract (arXiv)

Despite the success of recent abstractive summarizers on automatic evaluation metrics, the generated summaries still present factual inconsistencies with the source document. In this paper, we focus on entity-level factual inconsistency, i.e. reducing the mismatched entities between the generated summaries and the source documents. We therefore propose a novel entity-based SpanCopy mechanism, and explore its extension with a Global Relevance component. Experiment results on four summarization datasets show that SpanCopy can effectively improve the entity-level factual consistency with essentially no change in the word-level and entity-level saliency. The code is available at https://github.com/Wendy-Xiao/Entity-based-SpanCopy

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 29 of its 39 references that are in the map. First posted on arXiv 7 Sep 2022.

Builds on

29 of 39 references.

References · 29

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  4. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  5. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  6. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
  7. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  8. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 809
  9. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 578
  10. 2019Text Summarization with Pretrained Encoderscited by 553
  11. 2018A Discourse-Aware Attention Model for Abstractive Summarization of Long Documentscited by 477
  12. 2017A Deep Reinforced Model for Abstractive Summarizationcited by 364
17 more
  1. 2018Generating Wikipedia by Summarizing Long Sequencescited by 333
  2. 2020FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarizationcited by 292
  3. 2021LongT5: Efficient Text-To-Text Transformer for Long Sequencescited by 232
  4. 2017Faithful to the Original: Fact Aware Neural Abstractive Summarizationcited by 141
  5. 2019Hierarchical Transformers for Multi-Document Summarizationcited by 132
  6. 2020GSum: A General Framework for Guided Neural Abstractive Summarizationcited by 129
  7. 2021Entity-level Factual Consistency of Abstractive Text Summarizationcited by 118
  8. 2019Discourse-Aware Neural Extractive Text Summarizationcited by 104
  9. 2020CTRLsum: Towards Generic Controllable Text Summarizationcited by 98
  10. 2021Planning with Learned Entity Prompts for Abstractive Summarizationcited by 75
  11. 2020Multi-Fact Correction in Abstractive Text Summarizationcited by 66
  12. 2021PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarizationcited by 62
  13. 2019Extractive Summarization of Long Documents by Combining Global and Local Contextcited by 59
  14. 2020PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generationcited by 42
  15. 2022Don't Say What You Don't Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Searchcited by 23
  16. 2018Sequential Copying Networkscited by 10
  17. 2021BioCopy: A Plug-And-Play Span Copy Mechanism in Seq2Seq Modelscited by 2

Built on by

Cited by year

Citing papers per year: 2023: 7; 2024: 4.

11 papers.

  1. 2024A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Modelscited by 52
  2. 2023Faithfulness-Aware Decoding Strategies for Abstractive Summarizationcited by 31
  3. 2024Localizing Factual Inconsistencies in Attributable Text Generationcited by 13
  4. 2023Can LMs Generalize to Future Data? An Empirical Analysis on Text Summarizationcited by 9
  5. 2023Neural Natural Language Processing for Long Texts: A Survey on Classification and Summarizationcited by 7
  6. 2024GUMsley: Evaluating Entity Salience in Summarization for 12 English Genrescited by 5
  7. 2024ETF: An Entity Tracing Framework for Hallucination Detection in Code Summariescited by 5
  8. 2023PROM: A Phrase-level Copying Mechanism with Pre-training for Abstractive Summarizationcited by 2
  9. 2023GUMSum: Multi-Genre Data and Evaluation for English Abstractive Summarizationcited by 2
  10. 2023Counterfactual Debiasing for Generating Factually Consistent Text Summariescited by 1
  11. 2023Evaluation of Faithfulness Using the Longest Supported Subsequencecited by 0