Cue Annotation : A Heuristic Cue Selection Approach. J. Nat. Lang. Process. 21, 27–40 (2014). 概要(*引用): This paper present a simple yet effective approch to sentence- level uncertainty detection which does not rewuire cue word annotation. Unlike previous works, the proposed method focuses on cue selection, decoupling it from disambiguation and by optimizing it over sentence hedgin error rate. High perfomance for the task is achieved in experiments, even for settings with poor disambiguation, without cue annotaion and with otherwise unreliable corpora from a machine learning point-of-view. キーワード:Hedge Detection, Text Mining 文献紹介:Sentence Hedge Detection without Cue Annotation: Aheuristic Cue Selection Approch 2014/4/17 長岡技術科学大学 自然言語処理研究室 2014年度 文献紹介ゼミ