Improving Machine Learning Approaches to Coreference Resolution
Improving Machine Learning Approaches to Coreference Resolution
复制标题
DOI：
10.3115/1073083.1073102
复制
发表时间：
2002-07
期刊：
影响因子：
--
通讯作者：
Vincent Ng;Claire Gardent
中科院分区：
文献类型：
--
作者：
Vincent Ng;Claire Gardent
我们提出了一个名词短语共指系统，该系统扩展了Soon等人（2001）的工作，据我们所知，在MUC-6和MUC-7共指分辨率数据集上产生了迄今为止最好的结果-F-测量值分别为70.4和63.4。改进来自两个来源：学习框架的语言外变化和功能集的大规模扩展，以包括更复杂的语言知识。
We present a noun phrase coreference system that extends the work of Soon et al. (2001) and, to our knowledge, produces the best results to date on the MUC-6 and MUC-7 coreference resolution data sets --- F-measures of 70.4 and 63.4, respectively. Improvements arise from two sources: extra-linguistic changes to the learning framework and a large-scale expansion of the feature set to include more sophisticated linguistic knowledge.