Ranking Multiple Dialogue States by Corpus Statistics to Improve Discourse Understanding in Spoken Dialogue Systems
Ranking Multiple Dialogue States by Corpus Statistics to Improve Discourse Understanding in Spoken Dialogue Systems
复制标题
通过语料库统计对多个对话状态进行排名，以提高口语对话系统中的话语理解
DOI：
10.1587/transinf.e92.d.1771
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
Mikio Nakano
中科院分区：
文献类型：
--
作者：
Ryuichiro Higashinaka;Mikio Nakano
本文讨论了口语对话系统中的话语理解过程。该过程使得系统能够从对话的上下文理解用户话语。由多个语音识别假设和解析结果引起的用户话语中的歧义有时使得系统难以决定对用户意图的单个解释。作为一种解决方案，已经提出了将可能的解释保留为多个对话状态并使用后续用户话语来解决歧义的想法。尽管这种方法已被证明可以提高话语理解的准确性，但为了准确地对对话状态进行排名，精心创建的手工规则是必要的。本文提出了自动排序多个对话状态使用从对话语料库中获得的统计信息。在火车票预订和天气信息服务领域的实验结果表明，统计信息可以显著提高对话状态的排序精度，以及排序靠前的对话状态的时隙精度和概念错误率。
This paper discusses the discourse understanding process in spoken dialogue systems. This process enables a system to understand user utterances from the context of a dialogue. Ambiguity in user utterances caused by multiple speech recognition hypotheses and parsing results sometimes makes it difficult for a system to decide on a single interpretation of a user intention. As a solution, the idea of retaining possible interpretations as multiple dialogue states and resolving the ambiguity using succeeding user utterances has been proposed. Although this approach has proven to improve discourse understanding accuracy, carefully created hand-crafted rules are necessary in order to accurately rank the dialogue states. This paper proposes automatically ranking multiple dialogue states using statistical information obtained from dialogue corpora. The experimental results in the train ticket reservation and weather information service domains show that the statistical information can significantly improve the ranking accuracy of dialogue states as well as the slot accuracy and the concept error rate of the top-ranked dialogue states.
使用置信度测量和对话历史的口语理解方法
DOI：
--
发表时间：
2007
期刊：
Systems and Computers in Japan 38
影响因子：
--
作者：
N.Fujiwara;T.Itoh;K.Araki;A.Kai;T.Konishi and Y.Itoh
通讯作者：
T.Konishi and Y.Itoh
DOI：
10.21437/eurospeech.2001-396
发表时间：
2001-09
期刊：
--
影响因子：
--
作者：
Akinobu Lee;Tatsuya Kawahara;K. Shikano
通讯作者：
Akinobu Lee;Tatsuya Kawahara;K. Shikano
口语对话系统数据库搜索任务中基于对话模型的语境约束
DOI：
--
发表时间：
2005
期刊：
Proceedings of the Nineth European Conference on Speech Communication and Technology (Interspeech-2005)
影响因子：
--
作者：
T.Kondoh;M.Bannai;H.Nishino;K.Torii;Kazunori Komatani
通讯作者：
Kazunori Komatani