AkihikoWatanabe / paper_notes

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

SummEval: Re-evaluating Summarization Evaluation, Fabbri+, TACL'21 #984

Open AkihikoWatanabe opened 1 year ago

AkihikoWatanabe commented 1 year ago

https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00373/100686/SummEval-Re-evaluating-Summarization-Evaluation

AkihikoWatanabe commented 1 year ago

The scarcity of comprehensive up-to-date studies on evaluation metrics for text summarization and the lack of consensus regarding evaluation protocols continue to inhibit progress. We address the existing shortcomings of summarization evaluation methods along five dimensions: 1) we re-evaluate 14 automatic evaluation metrics in a comprehensive and consistent fashion using neural summarization model outputs along with expert and crowd-sourced human annotations; 2) we consistently benchmark 23 recent summarization models using the aforementioned automatic evaluation metrics; 3) we assemble the largest collection of summaries generated by models trained on the CNN/DailyMail news dataset and share it in a unified format; 4) we implement and share a toolkit that provides an extensible and unified API for evaluating summarization models across a broad range of automatic metrics; and 5) we assemble and share the largest and most diverse, in terms of model types, collection of human judgments of model-generated summaries on the CNN/Daily Mail dataset annotated by both expert judges and crowd-source workers. We hope that this work will help promote a more complete evaluation protocol for text summarization as well as advance research in developing evaluation metrics that better correlate with human judgments.

Translation (by gpt-3.5-turbo)

AkihikoWatanabe commented 1 year ago

自動評価指標が人手評価の水準に達しないことが示されており、結局のところROUGEを上回る自動性能指標はほとんどなかった。human judgmentsとのKendall;'s Tauを見ると、chrFがCoherenceとRelevance, METEORがFluencyで上回ったのみだった。また、LEAD-3はやはりベースラインとしてかなり強く、LEAD-3を上回ったのはBARTとPEGASUSだった。