NAIST.Japan: Temporal Relation Identification Using Dependency Parsed Tree
NAIST.Japan: Temporal Relation Identification Using Dependency Parsed Tree
复制标题
DOI：
10.3115/1621474.1621526
复制
发表时间：
2007-06
期刊：
影响因子：
--
通讯作者：
Yuchang Cheng;Masayuki Asahara;Yuji Matsumoto
中科院分区：
文献类型：
--
作者：
Yuchang Cheng;Masayuki Asahara;Yuji Matsumoto
在本文中，我们尝试使用带有依赖性树的特征的序列标记模型进行时间关系识别。在序列标记模型中，上下文对的关系可以用作当前对的关系识别的特征。一个句子中的单词对之间的头部模型关系也可以用作特征。在我们的初步实验中，这些特征对于时间关系识别任务有效。
In this paper, we attempt to use a sequence labeling model with features from dependency parsed tree for temporal relation identification. In the sequence labeling model, the relations of contextual pairs can be used as features for relation identification of the current pair. Head-modifier relations between pairs of words within one sentence can be also used as the features. In our preliminary experiments, these features are effective for the temporal relation identification tasks.