Sensitivity of BLANC to human-scored qualities of text summaries
Not on the map. Why?
Abstract (arXiv)
We explore the sensitivity of a document summary quality estimator, BLANC, to human assessment of qualities for the same summaries. In our human evaluations, we distinguish five summary qualities, defined by how fluent, understandable, informative, compact, and factually correct the summary is. We make the case for optimal BLANC parameters, at which the BLANC sensitivity to almost all of summary qualities is about as good as the sensitivity of a human annotator.
Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). First posted on arXiv 13 Oct 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 5; 2022: 0; 2023: 0; 2024: 1.
6 papers.
- 2021LightTag: Text Annotation Platformcited by 16
- 2021Play the Shannon Game With Language Models: A Human-Free Approach to Summary Evaluationcited by 13
- 2021Estimation of Summary-to-Text Inconsistency by Mismatched Embeddingscited by 5
- 2024Summarizing long regulatory documents with a multi-step pipelinecited by 4
- 2021Consistency and Coherence from Points of Contextual Similaritycited by 1
- 2021Towards Human-Free Automatic Quality Evaluation of German Summarizationcited by 0
- 2024Summarizing long regulatory documents with a multi-step pipeline19 Aug 2024
- 2021Consistency and Coherence from Points of Contextual Similarity22 Dec 2021
- 2021LightTag: Text Annotation Platform6 Sep 2021
- 2021Towards Human-Free Automatic Quality Evaluation of German Summarization13 May 2021
- 2021Estimation of Summary-to-Text Inconsistency by Mismatched Embeddings12 Apr 2021
- 2021Play the Shannon Game With Language Models: A Human-Free Approach to Summary Evaluation19 Mar 2021