SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for Text Summarization
By Jesse Vig, Wojciech Kryscinski, Karan Goel, Nazneen Rajani. 2021
25 citations recorded by the source corpus.
Novel neural architectures, training strategies, and the availability of large-scale corpora haven been the driving force behind recent progress in abstractive text summarization. However, due to the black-box nature of neural models, uninformative evaluation metrics, and scarce tooling for model and data analysis the true performance and failure modes of summarization models remain largely unknown. To address this limitation, we introduce SummVis, an open-source tool for visualizing abstractive summaries that enables fine-grained analysis of the models, data, and evaluation metrics associated with text summarization. Through its lexical and semantic visualizations, the tools offers an easy entry point for in-depth model prediction exploration across important dimensions such as factual consistency or abstractiveness. The tool together with several pre-computed model outputs is available at https://summvis.com.
Subfields: Artificial Intelligence, Summarization, Human-Computer Interaction
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Douwe Kiela
- Mohit Bansal
- Nazneen Rajani
- Tristan Thrush
- Yacine Jernite
- Yejin Choi
- Margaret Mitchell
- Angelina McMillan-Major
In Human-Computer Interaction
Citations in the corpus
- Measuring Data (2022, background): “They can be useful for initial, high-level analyses of datasets and as indicators to guide further fine-grained analyses which can go deeper in terms of the intrinsic characteristics of outliers and representative samples in the dataset (e.g., (Vig et al., 2021; Kannan et al., 2017)).”
- SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization (2021, unknown): “Furthermore, fine-grained consistency scores can be incorporated into visual analysis tools for summarization such as SummViz (Vig et al., 2021).”