mlsanityData to 7 Oct 2026

Improving Factual Error Correction for Abstractive Summarization via Data Distillation and Conditional-generation Cloze

arXiv 2402.08581 ↗First posted 13 Feb 2024cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Improving factual consistency in abstractive summarization has been a focus of current research. One promising approach is the post-editing method. However, previous works have yet to make sufficient use of factual factors in summaries and suffers from the negative effect of the training datasets. In this paper, we first propose a novel factual error correction model FactCloze based on a conditional-generation cloze task. FactCloze can construct the causality among factual factors while being able to determine whether the blank can be answered or not. Then, we propose a data distillation method to generate a more faithful summarization dataset SummDSC via multiple-dimensional evaluation. We experimentally validate the effectiveness of our approach, which leads to an improvement in multiple factual consistency metrics compared to baselines.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 41 of its 54 references that are in the map. First posted on arXiv 13 Feb 2024.

Builds on

41 of 54 references.

References · 41

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  6. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  7. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  8. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  9. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  10. 2015Teaching Machines to Read and Comprehendcited by 1,039
  11. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,026
  12. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
29 more
  1. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 578
  2. 2023Benchmarking Large Language Models for News Summarizationcited by 444
  3. 2021SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarizationcited by 402
  4. 2020Asking and Answering Questions to Evaluate the Factual Consistency of Summariescited by 376
  5. 2020FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarizationcited by 292
  6. 2021Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metricscited by 285
  7. 2021QuestEval: Summarization Asks for Fact-based Evaluationcited by 241
  8. 2021QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarizationcited by 233
  9. 2017Faithful to the Original: Fact Aware Neural Abstractive Summarizationcited by 141
  10. 2021Annotating and Modeling Fine-grained Factuality in Summarizationcited by 131
  11. 2020Evaluating Factuality in Generation with Dependency-level Entailmentcited by 122
  12. 2021Entity-level Factual Consistency of Abstractive Text Summarizationcited by 118
  13. 2020Factual Error Correction for Abstractive Summarization Modelscited by 108
  14. 2022Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectorscited by 103
  15. 2021Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selectioncited by 75
  16. 2023Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedbackcited by 71
  17. 2020Multi-Fact Correction in Abstractive Text Summarizationcited by 66
  18. 2021Improving Factual Consistency of Abstractive Summarization via Question Answeringcited by 55
  19. 2022FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarizationcited by 49
  20. 2022mFACE: Multilingual Summarization with Factual Consistency Evaluationcited by 42
  21. 2022Correcting Diverse Factual Errors in Abstractive Summarization via Post-Editing and Language Model Infillingcited by 38
  22. 2022On Improving Summarization Factual Consistency from Natural Language Feedbackcited by 38
  23. 2022Faithful to the Document or to the World? Mitigating Hallucinations via Entity-linked Knowledge in Abstractive Summarizationcited by 20
  24. 2020Adversarial NLI for Factual Correctness in Text Summarisation Modelscited by 13
  25. 2022Improving Factual Consistency in Summarization with Compression-Based Post-Editingcited by 13
  26. 2021CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarizationcited by 11
  27. 2022Questioning the Validity of Summarization Datasets and Improving Their Factual Consistencycited by 9
  28. 2023Evaluating Factual Consistency of Summaries with Large Language Modelscited by 9
  29. 2022Factual Error Correction for Abstractive Summaries Using Entity Retrievalcited by 8

Built on by

Not cited yet.