# SWING: Balancing Coverage and Faithfulness for Dialogue Summarization

arXiv: https://arxiv.org/abs/2301.10483 · HTML: https://mlsanity.com/paper/2301.10483/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 50 references that are in the map.
- First posted on arXiv 25 Jan 2023.

## Builds on (most cited first, 30 of 36)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization](https://mlsanity.com/paper/1911.12237/) (2019)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://mlsanity.com/paper/2008.00401/) (2020)
- [Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics](https://mlsanity.com/paper/2104.13346/) (2021)
- [QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization](https://mlsanity.com/paper/2112.08542/) (2021)
- [DialogSum: A Real-Life Scenario Dialogue Summarization Dataset](https://mlsanity.com/paper/2105.06762/) (2021)
- [CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2109.09209/) (2021)
- [Factual Error Correction for Abstractive Summarization Models](https://mlsanity.com/paper/2010.08712/) (2020)
- [Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports](https://mlsanity.com/paper/1911.02541/) (2019)
- [DocNLI: A Large-scale Dataset for Document-level Natural Language Inference](https://mlsanity.com/paper/2106.09449/) (2021)
- [Multi-Fact Correction in Abstractive Text Summarization](https://mlsanity.com/paper/2010.02443/) (2020)
- [Improving Factual Consistency of Abstractive Summarization via Question Answering](https://mlsanity.com/paper/2105.04623/) (2021)
- [Abstractive Dialogue Summarization with Sentence-Gated Modeling Optimized by Dialogue Acts](https://mlsanity.com/paper/1809.05715/) (2018)
- [CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning](https://mlsanity.com/paper/2112.08713/) (2021)
- [Zero-shot Fact Verification by Claim Generation](https://mlsanity.com/paper/2105.14682/) (2021)
- [Faking Fake News for Real Fake News Detection: Propaganda-loaded Training Data Generation](https://mlsanity.com/paper/2203.05386/) (2022)
- [Controllable Neural Dialogue Summarization with Personal Named Entity Planning](https://mlsanity.com/paper/2109.13070/) (2021)
- [Falsesum: Generating Document-level NLI Examples for Recognizing Factual Inconsistency in Summarization](https://mlsanity.com/paper/2205.06009/) (2022)
- [Learning to Revise References for Faithful Summarization](https://mlsanity.com/paper/2204.10290/) (2022)

## Built on by (most cited first, 10 of 10)

- [From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models](https://mlsanity.com/paper/2403.12027/) (2024)
- [Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles](https://mlsanity.com/paper/2309.09369/) (2023)
- [Zero-shot Faithful Factual Error Correction](https://mlsanity.com/paper/2305.07982/) (2023)
- [Fast and Accurate Factual Inconsistency Detection Over Long Documents](https://mlsanity.com/paper/2310.13189/) (2023)
- [Controllable Text Summarization: Unraveling Challenges, Approaches, and Prospects -- A Survey](https://mlsanity.com/paper/2311.09212/) (2023)
- [To Generate or to Retrieve? On the Effectiveness of Artificial Contexts for Medical Open-Domain Question Answering](https://mlsanity.com/paper/2403.01924/) (2024)
- [Factual Dialogue Summarization via Learning from Large Language Models](https://mlsanity.com/paper/2406.14709/) (2024)
- [Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection](https://mlsanity.com/paper/2403.04073/) (2024)
- [Persona Extraction Through Semantic Similarity for Emotional Support Conversation Generation](https://mlsanity.com/paper/2403.04212/) (2024)
- [MARS: Multilingual Aspect-centric Review Summarisation](https://mlsanity.com/paper/2410.09991/) (2024)

## Abstract (arXiv)

Missing information is a common issue of dialogue summarization where some information in the reference summaries is not covered in the generated summaries. To address this issue, we propose to utilize natural language inference (NLI) models to improve coverage while avoiding introducing factual inconsistencies. Specifically, we use NLI to compute fine-grained training signals to encourage the model to generate content in the reference summaries that have not been covered, as well as to distinguish between factually consistent and inconsistent generated sentences. Experiments on the DialogSum and SAMSum datasets confirm the effectiveness of the proposed approach in balancing coverage and faithfulness, validated with automatic metrics and human evaluations. Additionally, we compute the correlation between commonly used automatic metrics with human judgments in terms of three different dimensions regarding coverage and factual consistency to provide insight into the most suitable metric for evaluating dialogue summaries.