Challenge: Abstractive summarization models often produce inconsistent statements or false facts.
Approach: They propose an efficient weak-supervised adversarial data augmentation approach to generate factual consistency datasets by backpropagating gradients on token embeddings.
Outcome: The proposed model can make interpretable factual errors tracing on public datasets and is cost-effective.

Similar Papers

Evaluating the Factual Consistency of Abstractive Text Summarization (2020.emnlp-main)

Copied to clipboard

Challenge: a weakly-supervised approach is needed to verify factual consistency . auxiliary span extraction tasks are useful for verifying factual consistent summaries .
Approach: They propose a weakly-supervised approach for verifying factual consistency . they transfer the model to summaries generated by several neural models .
Outcome: The proposed approach outperforms models trained with strong supervision on source documents and human evaluations.
Improving Factual Consistency of Abstractive Summarization via Question Answering (2021.acl-long)

Copied to clipboard

Challenge: Recent studies show that about 30% of summaries generated by neural text summarization suffer from fact fabrication.
Approach: They propose an automatic evaluation metric to measure factual consistency and a learning algorithm that maximizes the metric during model training.
Outcome: The proposed method improves factual consistency and overall quality of summarization models.
Factual Error Correction for Abstractive Summarization Models (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods for abstractive summarization are unable to ensure factual consistency of generated summaries.
Approach: They propose a post-editing corrector module to identify and correct factual errors in generated summaries.
Outcome: The proposed model outperforms existing models on CNN/DailyMail dataset on factual consistency evaluation.
Correcting Diverse Factual Errors in Abstractive Summarization via Post-Editing and Language Model Infilling (2022.emnlp-main)

Copied to clipboard

Challenge: Abstractive summarization models often generate inconsistent summaries containing factual errors or fabricated content.
Approach: They propose to generate representative examples of non-factual summaries through infilling language models and train a robust fact-correction model to post-edit them to improve factual consistency.
Outcome: The proposed model outperforms previous methods in correcting factual errors on two popular summarization datasets.
Are Factuality Checkers Reliable? Adversarial Meta-evaluation of Factuality in Summarization (2021.findings-emnlp)

Copied to clipboard

Challenge: Despite the progress of factual evaluation methods, they are limited in their opacity and lack the ability to assess the factuality of the summaries.
Approach: They propose to use a meta-evaluation methodology to diagnose the fine-grained strengths and weaknesses of 6 existing top-performing metrics over 24 diagnostic test datasets.
Outcome: The proposed method diagnoses the strengths and weaknesses of 6 existing top-performing metrics over 24 diagnostic test datasets and searches for directions for further improvement by data augmentation.
Multi-Fact Correction in Abstractive Text Summarization (2020.emnlp-main)

Copied to clipboard

Challenge: Existing abstractive summarization systems generate incorrect facts with respect to the source text.
Approach: They propose a suite of two factual correction models that leverages question-answering knowledge to make corrections in system-generated summaries via span selection.
Outcome: The proposed model improves factuality of news summarization without sacrificing summary quality.
On Faithfulness and Factuality in Abstractive Summarization (2020.acl-main)

Copied to clipboard

Challenge: Existing conditional text generation models produce unfaithful and unfaithed summaries . current models accomplish a high level of fluency and coherence .
Approach: They propose to use pretrained models for document summarization to better understand hallucinations . they find that textual entailment measures better correlate with faithfulness .
Outcome: The proposed models generate faithful and factual summaries as evaluated by humans.
Discourse Understanding and Factual Consistency in Abstractive Summarization (2021.eacl-main)

Copied to clipboard

Challenge: Existing abstractive summarization models often hallucinate information or generate factually incorrect summaries.
Approach: They propose a general framework for abstractive summarization with factual consistency and distinct modeling of the narrative flow in an output summary.
Outcome: The proposed framework generates abstracts with factual consistency and coherence significantly better than baselines.
Enhancing Factual Consistency of Abstractive Summarization (2021.naacl-main)

Copied to clipboard

Challenge: Abstractive summarization models often distort or fabricate facts in articles . factual inconsistency is a common problem with abstractive summaries .
Approach: They propose a fact-aware summarization model FASum to extract factual relations into the summary generation process via graph attention.
Outcome: The proposed model can produce abstractive summaries with higher factual consistency compared with existing systems and corrects factual errors via modifying only a few keywords.
Improving Factual Consistency in Abstractive Summarization with Sentence Structure Pruning (2024.lrec-main)

Copied to clipboard

Challenge: Abstractive summarization models suffer from factual inconsistency problem . post-editing methods focus on replacing suspicious entities, failing to modify incorrect content hidden in sentence structures.
Approach: They propose to use sentence pruning operation to correct possible errors . they propose to apply sentence pruning operations to the syntactic dependency tree .
Outcome: The proposed method improves factual consistency on the FRANK dataset compared with baselines . it is model-independent and can serve as the final step in ensuring factual consistentness.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations