A Sequence Labelling Approach to Quote Attribution.

EMNLP-CoNLL '12: Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning(2012)

引用 23|浏览61
暂无评分
摘要
Quote extraction and attribution is the task of automatically extracting quotes from text and attributing each quote to its correct speaker. The present state-of-the-art system uses gold standard information from previous decisions in its features, which, when removed, results in a large drop in performance. We treat the problem as a sequence labelling task, which allows us to incorporate sequence features without using gold standard information. We present results on two new corpora and an augmented version of a third, achieving a new state-of-the-art for systems using only realistic features.
更多
查看译文
关键词
gold standard information,new corpus,present result,present state-of-the-art system,quote extraction,sequence feature,augmented version,correct speaker,large drop,previous decision
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要