Unsupervised Reference-Free Summary Quality Evaluation via Contrastive Learning
This addresses the need for reference-free evaluation in document summarization, offering a more flexible and generalizable approach, though it is incremental as it builds on existing contrastive learning and BERT techniques.
The paper tackles the problem of evaluating summary quality without needing human-generated references by proposing an unsupervised contrastive learning method based on BERT, which covers linguistic and semantic aspects; experiments on Newsroom and CNN/Daily Mail show it outperforms other metrics.
Evaluation of a document summarization system has been a critical factor to impact the success of the summarization task. Previous approaches, such as ROUGE, mainly consider the informativeness of the assessed summary and require human-generated references for each test summary. In this work, we propose to evaluate the summary qualities without reference summaries by unsupervised contrastive learning. Specifically, we design a new metric which covers both linguistic qualities and semantic informativeness based on BERT. To learn the metric, for each summary, we construct different types of negative samples with respect to different aspects of the summary qualities, and train our model with a ranking loss. Experiments on Newsroom and CNN/Daily Mail demonstrate that our new evaluation method outperforms other metrics even without reference summaries. Furthermore, we show that our method is general and transferable across datasets.