Papers with neural summarization models
On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Study (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Modern deep models for summarization generate miscalibrated predictive uncertainty, compromising reliability and trustworthiness in real-world applications. |
| Approach: | They propose to use probabilistic methods to improve the uncertainty quality of neural summarization models by using three large-scale benchmarks with varying difficulty. |
| Outcome: | The proposed methods consistently improve the model’s generation and uncertainty quality, leading to improved selective generation performance (i.e., abstaining from low-quality summaries) in practice. |
BiSET: Bi-directional Selective Encoding with Template for Abstractive Summarization (P19-1)
Copied to clipboard
| Challenge: | Abstractive summarization models are limited in size and noisy training data. |
| Approach: | They propose a bi-directional selective encoding with template model which leverages template from training data to softly select key information from each source article to guide its summarization process. |
| Outcome: | The proposed model improves the summarization performance significantly on a standard summarizing dataset. |
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. |