Feasibility Study for Ellipsis Resolution in Dialogues by Machine-Learning Technique
Feasibility Study for Ellipsis Resolution in Dialogues by Machine-Learning Technique
复制标题
利用机器学习技术解决对话中省略号的可行性研究
DOI：
10.3115/980691.980802
复制
发表时间：
1998
期刊：
影响因子：
--
通讯作者：
E. Sumita
中科院分区：
文献类型：
--
作者：
Kazuhide Yamamoto;E. Sumita
提出了一种解决日语对话中出现的省略的方法。该方法不仅可以解决主语省略，还可以解决宾语和其他语法情况下的省略。在这种方法中，使用机器学习算法来选择分辨率所需的属性。建立一个决策树，并将其用作实际的省略号解析器。盲测结果表明，该方法对间接宾语的分辨准确率为91.7%，对带有动词谓语的主语的分辨准确率为78.7%。通过研究决策树，我们发现，主题相关的属性是必要的，以获得高性能的分辨率，和不可缺少的属性根据语法情况而变化。还讨论了与决策树训练相关的数据大小问题。
A method for resolving the ellipses that appear in Japanese dialogues is proposed. This method resolves not only the subject ellipsis, but also those in object and other grammatical cases. In this approach, a machine-learning algorithm is used to select the attributes necessary for a resolution. A decision tree is built, and used as the actual ellipsis resolver. The results of blind tests have shown that the proposed method was able to provide a resolution accuracy of 91.7% for indirect objects, and 78.7% for subjects with a verb predicate. By investigating the decision tree we found that topic-dependent attributes are necessary to obtain high performance resolution, and that indispensable attributes vary according to the grammatical case. The problem of data size relative to decision-tree training is also discussed.
使用决策树学习进行谓词省略解析
DOI：
--
发表时间：
2005
期刊：
Proceedings of the 67^<th> IPSJ Conference 1ZA-2
影响因子：
--
作者：
Akiko Kobayashi;Kanako Komiya;Nobuo Inui;Yoshiyuki Kotani
通讯作者：
Yoshiyuki Kotani
使用 Transformer 进行日语句子唇读
DOI：
--
发表时间：
2021
期刊：
影响因子：
--
作者：
Yoshida;S.;Yagi;H.;Kiminami;A. and Garrod;G.;盛満大生，伊藤一志;白方 達也，齊藤 剛史
通讯作者：
白方 達也，齊藤 剛史