0


归一化校准检测文本蕴涵的依存关系树

Normalized Alignment of Dependency Trees for Detecting Textual Entailment
课程网址: http://videolectures.net/pcw06_marsi_nadtd/  
主讲教师: Erwin Marsi
开课单位: 蒂尔堡大学
开课时间: 2007-02-25
课程语种: 英语
中文简介:
本文研究了依赖树归一化对齐在蕴涵预测中的作用。总的来说,我们的方法在rte2测试集上产生了60%的精确度,这是相对于基线的一个显著改进。不同子集的结果差异很大,汇总数据的性能达到峰值。我们得出的结论是,规范化的对齐对于检测文本继承是有用的,但是一个健壮的方法可能需要包括额外的信息源。
课程简介: In this paper, we investigate the usefulness of normalized alignment of dependency trees for entailment prediction. Overall, our approach yields an accuracy of 60% on the RTE2 test set, which is a significant improvement over the baseline. Results vary substantially across the different subsets, with a peak performance on the summarization data. We conclude that normalized alignment is useful for detecting textual entailment, but a robust approach will probably need to include additional sources of information.
关 键 词: 计算机科学; 自然语言处理; 文本蕴涵
课程来源: 视频讲座网
最后编审: 2020-07-06:heyf
阅读次数: 18