AkihikoWatanabe / paper_notes

たまに追加される論文メモ
https://AkihikoWatanabe.github.io/paper_notes
21 stars 0 forks source link

Reference-free Summarization Evaluation via Semantic Correlation and Compression Ratio, Liu+, NAACL'22 #956

Open AkihikoWatanabe opened 1 year ago

AkihikoWatanabe commented 1 year ago

https://aclanthology.org/2022.naacl-main.153/

AkihikoWatanabe commented 1 year ago

A document can be summarized in a number of ways. Reference-based evaluation of summarization has been criticized for its inflexibility. The more sufficient the number of abstracts, the more accurate the evaluation results. However, it is difficult to collect sufficient reference summaries. In this paper, we propose a new automatic reference-free evaluation metric that compares semantic distribution between source document and summary by pretrained language models and considers summary compression ratio. The experiments show that this metric is more consistent with human evaluation in terms of coherence, consistency, relevance and fluency.

Translation (by gpt-3.5-turbo)