Recognizing Implicit Discourse Relations in the Penn Discourse Treebank

Recognizing Implicit Discourse Relations in the Penn Discourse Treebank
复制标题

DOI:
10.3115/1699510.1699555
复制
发表时间:
2009-08
期刊:
--
影响因子:
--
通讯作者:
Ziheng Lin;Min-Yen Kan;H. Ng
Ziheng Lin;Min-Yen Kan;H. Ng
中科院分区:
其他
文献类型:
--
作者:
Ziheng Lin;Min-Yen Kan;H. Ng

文献摘要

被引文献

相似文献

我们提出了一个隐含的话语关系分类在宾夕法尼亚大学话语树库(PDTB)。我们的分类器考虑了两个参数的上下文,词对信息,以及参数的内部成分和依赖分析。我们对PDTB的研究结果比基线有14.1%的显著改善。在我们的错误分析中,我们讨论了识别PDTB中的隐含关系的四个挑战。
We present an implicit discourse relation classifier in the Penn Discourse Treebank (PDTB). Our classifier considers the context of the two arguments, word pair information, as well as the arguments' internal constituent and dependency parses. Our results on the PDTB yields a significant 14.1% improvement over the baseline. In our error analysis, we discuss four challenges in recognizing implicit relations in the PDTB.