论文标题
各种流派的方面性：一种分布语义方法
Aspectuality Across Genre: A Distributional Semantics Approach
论文作者
论文摘要
英语中动词词汇方面的解释对于认识文本需要和学习话语级别的推论至关重要。我们表明，可以通过分布语义有效地对方面类别，状态，事件与远程事件的两个基本维度进行有效建模。我们发现动词的局部环境最能表明其方面类别，并证明封闭的班级单词往往比内容词更强大。我们的方法在三个数据集上的表现优于先前的工作。最后，我们贡献了一个人类的人类对话数据集，该数据集用词汇方面和目前的实验注释，这些对话显示了伸展性与流派和话语目标的相关性。
The interpretation of the lexical aspect of verbs in English plays a crucial role for recognizing textual entailment and learning discourse-level inferences. We show that two elementary dimensions of aspectual class, states vs. events, and telic vs. atelic events, can be modelled effectively with distributional semantics. We find that a verb's local context is most indicative of its aspectual class, and demonstrate that closed class words tend to be stronger discriminating contexts than content words. Our approach outperforms previous work on three datasets. Lastly, we contribute a dataset of human--human conversations annotated with lexical aspect and present experiments that show the correlation of telicity with genre and discourse goals.
