Crowdsourcing Lightweight Pyramids for Manual Summary Evaluation
This work addresses the problem of expensive manual evaluation for researchers in natural language processing by making summary evaluation more accessible and scalable through crowdsourcing.
The paper tackled the high cost and expertise requirements of the Pyramid method for manual summary evaluation by proposing a lightweight, sampling-based version that is crowdsourcable, showing higher correlation with expert-based evaluations compared to the common Responsiveness method.
Conducting a manual evaluation is considered an essential part of summary evaluation methodology. Traditionally, the Pyramid protocol, which exhaustively compares system summaries to references, has been perceived as very reliable, providing objective scores. Yet, due to the high cost of the Pyramid method and the required expertise, researchers resorted to cheaper and less thorough manual evaluation methods, such as Responsiveness and pairwise comparison, attainable via crowdsourcing. We revisit the Pyramid approach, proposing a lightweight sampling-based version that is crowdsourcable. We analyze the performance of our method in comparison to original expert-based Pyramid evaluations, showing higher correlation relative to the common Responsiveness method. We release our crowdsourced Summary-Content-Units, along with all crowdsourcing scripts, for future evaluations.