The DOI matches its Crossref record; 40 of the 42 references it cites were found in a registry or an index.
Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports
Open accessAbstract
Neural abstractive summarization models are able to generate summaries which have high overlap with human references.However, existing models are not optimized for factual correctness, a critical metric in real-world applications.In this work, we develop a general framework where we evaluate the factual correctness of a generated summary by factchecking it automatically against its reference using an information extraction module.We further propose a training strategy which optimizes a neural summarization model with a factual correctness reward via reinforcement learning.We apply the proposed method to the summarization of radiology reports, where factual correctness is a key requirement.On two separate datasets collected from hospitals, we show via both automatic and human evaluation that the proposed approach substantially improves the factual correctness and overall quality of outputs over a competitive neural summarization system, producing radiology summaries that approach the quality of humanauthored ones.Background: radiographic examination of the chest.clinical history: 80 years of age, male ... Findings: frontal radiograph of the chest demonstrates repositioning of the right atrial lead possibly into the ivc.... a right apical pneumothorax can be seen from the image.moderate right and small left pleural effusions continue.no pulmonary edema is observed.heart size is upper limits of normal. Human Summary: pneumothorax is seen. bilateral pleural effusions continue.Summary A (ROUGE-L = 0.77): no pneumothorax is observed.bilateral pleural effusions continue.Summary B (ROUGE-L = 0.44): pneumothorax is observed on radiograph.bilateral pleural effusions continue to be seen.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“generating Impression is related to Radiology Report Summarization (Zhang et al., 2020) where a system has to summarize the Findings section of a report into Impression , making this choice even more relevant.”
From Improving the Factual Correctness of Radiology Report Generation with Semantic Rewards (2022) · cites this paper as Zhang et al., 2020
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071
Self-citation(2014) · Cited by 33,419
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213
Introduction to information retrieval
(2009) · Choice Reviews Online · doi:10.5860/choice.46-2715 · Cited by 12,278
Self-citationIntroduction to Information Retrieval
Manning, C. D., Raghavan, P., & Schütze, H. (2008) · doi:10.1017/cbo9780511809071 · Cited by 11,288
Self-citation(2004) · Cited by 9,718
Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
Williams, R. J. (1992) · Machine Learning · doi:10.1007/bf00992696 · Cited by 8,608
The Stanford CoreNLP Natural Language Processing Toolkit
Manning, C. D., Surdeanu, M., Bauer, J., Finkel, J. R., Bethard, S. J., & McClosky, D. (2014) · Annual Meeting of the Association for Computational Linguistics: System Demonstrations (ACL Demo) · doi:10.3115/v1/p14-5010 · Cited by 7,252
Self-citationA Learning Algorithm for Continually Running Fully Recurrent Neural Networks
Williams, R. J., & Zipser, D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.2.270 · Cited by 4,369
Cited by
Sorted by citations
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025
“[231] propose to explicitly measure the factual correctness of a generated text against the reference by first extracting facts via an information extraction (IE) module.”
BackgroundNeural Natural Language Processing for unstructured data in electronic health records: A review
Li, I., Pan, J. N., Goldwasser, J., Verma, N., Wong, W. P., Nuzumlalı, M. Y., Rosand, B., Li, Y., Zhang, M. M., Chang, D., et al. (2022) · Computer Science Review · doi:10.1016/j.cosrev.2022.100511 · Cited by 280
SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization
Laban, P., Schnabel, T., Bennett, P. N., & Hearst, M. A. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00453 · Cited by 238
A systematic review of natural language processing applied to radiology reports
Casey, A., Davidson, E., Poon, M., Dong, H., Duma, D., Grivas, A., Grover, C., Suárez-Paniagua, V., Tobin, R., Whiteley, W., et al. (2021) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-021-01533-7 · Cited by 244
Evaluation of Text Generation: A Survey
Celikyilmaz, A., Clark, E., & Gao, J. (2020) · arXiv · doi:10.48550/arxiv.2006.14799 · Cited by 207
Metadata
- Authors
- Zhang, Y., Merck, D., Tsai, E., Manning, C. D., & Langlotz, C.
- Affiliations
- Stanford University (US)
- University of Florida (US)
- Venue
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Published
- 2020
- Pages
- 5108-5120
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W3034863243
- Cited by
- 171
- References
- 42
- Citations by year
- 2026: 9 · 2025: 16 · 2024: 20 · 2023: 30 · 2022: 32 · 2021: 49 · 2020: 15
- FWCI
- 11.79
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Text Analysis Techniques
- Keywords
- factual accuracy, abstractive summarization, radiology reports, fact-checking, information extraction, reinforcement learning, medical report summarization, ROUGE evaluation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
