Probabilistic dialogue act extraction for concept based multilingual translation systems
Probabilistic dialogue act extraction for concept based multilingual translation systems
复制标题
基于概念的多语言翻译系统的概率对话行为提取
DOI：
10.21437/icslp.1998-579
复制
发表时间：
1998
期刊：
影响因子：
--
通讯作者：
Koichi Tanigaki
中科院分区：
文献类型：
--
作者：
Toshiaki Fukada;D. Koll;A. Waibel;Koichi Tanigaki
本文描述了一种基于概念的多语言翻译系统中对话行为的概率提取方法。话语分析是语义中间语言的一个单位，它由说话人信息、言语行为、概念和语言四部分组成。用于提取言语行为或概念的概率模型被训练为言语行为或依赖于概念的单词n元语法模型。该方法在带DA标注的英语和日语数据库上进行了评估。实验结果表明，与传统的基于文法的方法相比，该方法具有更好的性能。此外，对于作为语音识别输出的错误输入，所提出的方法具有更强的鲁棒性。
This paper describes a probabilistic methodfor dialogue act (DA) extraction for concept-based multilingual translation systems. A DA is a unit of a semantic interlingua and it consists of speaker information, speech act, concept and argu-ment. Probabilistic models for the extraction of speech acts or concepts are trained as speech act or concept dependent word n-gram models. The proposed method is evaluated on DA-annotated English and Japanese databases. The experimental results show that the proposed method gives a better performance compared to the conventioanl grammar-based approach. In addition, the proposed method is much more robust for erroneous inputs obtained as speech recognition outputs.