Correcting Diverse Factual Errors in Abstractive Summarization via
Post-Editing and Language Model Infilling
- URL: http://arxiv.org/abs/2210.12378v1
- Date: Sat, 22 Oct 2022 07:16:19 GMT
- Title: Correcting Diverse Factual Errors in Abstractive Summarization via
Post-Editing and Language Model Infilling
- Authors: Vidhisha Balachandran, Hannaneh Hajishirzi, William Cohen, Yulia
Tsvetkov
- Abstract summary: We show that our approach vastly outperforms prior methods in correcting erroneous summaries.
Our model -- FactEdit -- improves factuality scores by over 11 points on CNN/DM and over 31 points on XSum.
- Score: 56.70682379371534
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Abstractive summarization models often generate inconsistent summaries
containing factual errors or hallucinated content. Recent works focus on
correcting factual errors in generated summaries via post-editing. Such
correction models are trained using adversarial non-factual summaries
constructed using heuristic rules for injecting errors. However, generating
non-factual summaries using heuristics often does not generalize well to actual
model errors. In this work, we propose to generate hard, representative
synthetic examples of non-factual summaries through infilling language models.
With this data, we train a more robust fact-correction model to post-edit the
summaries to improve factual consistency. Through quantitative and qualitative
experiments on two popular summarization datasets -- CNN/DM and XSum -- we show
that our approach vastly outperforms prior methods in correcting erroneous
summaries. Our model -- FactEdit -- improves factuality scores by over ~11
points on CNN/DM and over ~31 points on XSum on average across multiple
summarization models, producing more factual summaries while maintaining
competitive summarization quality.
Related papers
- AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation [57.8363998797433]
We propose AMRFact, a framework that generates perturbed summaries using Abstract Meaning Representations (AMRs)
Our approach parses factually consistent summaries into AMR graphs and injects controlled factual inconsistencies to create negative examples, allowing for coherent factually inconsistent summaries to be generated with high error-type coverage.
arXiv Detail & Related papers (2023-11-16T02:56:29Z) - Improving Factual Consistency in Summarization with Compression-Based
Post-Editing [146.24839415743358]
We show that a model-agnostic way to address this problem is post-editing the generated summaries.
We propose to use sentence-compression data to train the post-editing model to take a summary with extrinsic entity errors marked with special tokens.
We show that this model improves factual consistency while maintaining ROUGE, improving entity precision by up to 30% on XSum, and that this model can be applied on top of another post-editor.
arXiv Detail & Related papers (2022-11-11T13:35:38Z) - Understanding Factual Errors in Summarization: Errors, Summarizers,
Datasets, Error Detectors [105.12462629663757]
In this work, we aggregate factuality error annotations from nine existing datasets and stratify them according to the underlying summarization model.
We compare performance of state-of-the-art factuality metrics, including recent ChatGPT-based metrics, on this stratified benchmark and show that their performance varies significantly across different types of summarization models.
arXiv Detail & Related papers (2022-05-25T15:26:48Z) - CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in
Abstractive Summarization [6.017006996402699]
We study generating abstractive summaries that are faithful and factually consistent with the given articles.
A novel contrastive learning formulation is presented, which leverages both reference summaries, as positive training data, and automatically generated erroneous summaries, as negative training data, to train summarization systems that are better at distinguishing between them.
arXiv Detail & Related papers (2021-09-19T20:05:21Z) - Annotating and Modeling Fine-grained Factuality in Summarization [36.88018450067003]
A major barrier to their use in practice is their propensity to output summaries that are not faithful to the input and that contain factual errors.
We explore both synthetic and human-labeled data sources for training models to identify factual errors in summarization.
We show that our best factuality detection model enables training of more factual XSum summarization models by allowing us to identify non-factual tokens in the training data.
arXiv Detail & Related papers (2021-04-09T11:20:44Z) - Factual Error Correction for Abstractive Summarization Models [41.77317902748772]
We propose a post-editing corrector module to correct factual errors in generated summaries.
We show that our model is able to correct factual errors in summaries generated by other neural summarization models.
We also find that transferring from artificial error correction to downstream settings is still very challenging.
arXiv Detail & Related papers (2020-10-17T04:24:16Z) - Multi-Fact Correction in Abstractive Text Summarization [98.27031108197944]
Span-Fact is a suite of two factual correction models that leverages knowledge learned from question answering models to make corrections in system-generated summaries via span selection.
Our models employ single or multi-masking strategies to either iteratively or auto-regressively replace entities in order to ensure semantic consistency w.r.t. the source text.
Experiments show that our models significantly boost the factual consistency of system-generated summaries without sacrificing summary quality in terms of both automatic metrics and human evaluation.
arXiv Detail & Related papers (2020-10-06T02:51:02Z) - Enhancing Factual Consistency of Abstractive Summarization [57.67609672082137]
We propose a fact-aware summarization model FASum to extract and integrate factual relations into the summary generation process.
We then design a factual corrector model FC to automatically correct factual errors from summaries generated by existing systems.
arXiv Detail & Related papers (2020-03-19T07:36:10Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.