recently, many researchers try to handle coreference resolution with statistical machine learning and gain some achievement.
近年来,许多学者尝试利用统计机器学习的方法来进行共指消解并取得了一定的进展。
facing the fact that the chinese training corpus for coreference resolution is heavily lacking, this paper presents a new unsupervised clustering algorithm for noun phrase coreference resolution.
针对当前中文指代标注训练语料非常缺乏的现状,本文提出一种无监督聚类算法实现对名词短语的指代消解。
coreference resolution is very important subtask of anaphora resolution and has quite widely practicality value and society value.
共指消解是指代消解中极其重要的子任务,并且具有很大的应用价值和社会价值。
the experimental result on ace dataset shows the improvement of coreference resolution after adding selected background semantic knowledge.
在ace数据集上实验结果表明,通过集成各种经过特征选择后的背景语义知识,共指消解的结果有进一步提高。
the coreference resolution is an important subtask of information extraction.
共指消解是信息抽取中一个重要子任务。
experimental results show that the method can improve the performance of coreference resolution system, and f-measure reaches 80.72%.
实验结果表明,该中文共指消解方法能提高共指消解的性能,值达到80.72%。
coreference resolution plays an important role in natural language processing.
指代消解是自然语言处理领域中的一个重要问题。