Generating flexible proper name references in text: Data, models and evaluation.
EACL(2017)
摘要
This study introduces a statistical model able to generate variations of a proper name, taking into account the person to be mentioned, the discourse context and individual variation. The model relies on the REGnames corpus, a dataset with 53,102 proper name references to 1,000 people in different discourse contexts. We evaluate the versions of our model in the perspective of how human writers produce proper names, and also how human readers process them.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络