arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.00299cs.AI
收藏

记叙文阅读理解机器评估综述

A Survey of Machine Narrative Reading Comprehension Assessments

Syracuse University(雪城大学);Rensselaer Polytechnic Institute(伦斯勒理工学院);New Jersey Institute of Technology(新泽西理工学院);WeChat AI, Tencent Inc.(腾讯公司微信人工智能)

Yisi Sang, Xiangyang Mou, Jing Li, Jeffrey Stanton, Mo Yu

摘要:

随着机器叙事理解研究的不断发展,迫切需要考虑性能评估策略以及不同基准任务的深度和范围。基于叙事理论,阅读理解理论,以及现有的机器叙事阅读理解任务和数据集,我们提出了一个类型学,抓住了主要的相似性和差异之间的评估任务,并讨论了我们的类型学的新任务设计的影响和叙事阅读理解的挑战。

英文摘要:

As the body of research on machine narrative comprehension grows, there is a critical need for consideration of performance assessment strategies as well as the depth and scope of different benchmark tasks. Based on narrative theories, reading comprehension theories, as well as existing machine narrative reading comprehension tasks and datasets, we propose a typology that captures the main similarities and differences among assessment tasks; and discuss the implications of our typology for new task design and the challenges of narrative reading comprehension.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑