Reference Matters: Benchmarking Factual Error Correction for Dialogue Summarization with Fine-grained Evaluation Framework
Mingqi Gao, Xiaojun Wan, Jia Su, Zhefeng Wang, baoxing Huai
Main: Summarization Main-poster Paper
Session 1: Summarization (Virtual Poster)
Conference Room: Pier 7&8
Conference Time: July 10, 11:00-12:30 (EDT) (America/Toronto)
Global Time: July 10, Session 1 (15:00-16:30 UTC)
Keywords:
conversational summarization, evaluation, factuality
TLDR:
Factuality is important to dialogue summarization. Factual error correction (FEC) of model-generated summaries is one way to improve factuality. Current FEC evaluation that relies on factuality metrics is not reliable and detailed enough. To address this problem, we are the first to manually annotat...
You can open the
#paper-P378
channel in a separate window.
Abstract:
Factuality is important to dialogue summarization. Factual error correction (FEC) of model-generated summaries is one way to improve factuality. Current FEC evaluation that relies on factuality metrics is not reliable and detailed enough. To address this problem, we are the first to manually annotate a FEC dataset for dialogue summarization containing 4000 items and propose FERRANTI, a fine-grained evaluation framework based on reference correction that automatically evaluates the performance of FEC models on different error categories. Using this evaluation framework, we conduct sufficient experiments with FEC approaches under a variety of settings and find the best training modes and significant differences in the performance of the existing approaches on different factual error categories.