Rapid Prototyping of Robust Language Understanding Modules for Spoken Dialogue Systems
Rapid Prototyping of Robust Language Understanding Modules for Spoken Dialogue Systems
复制标题
DOI：
--
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
Yuichiro Fukubayashi;Kazunori Komatani;Mikio Nakano;Kotaro Funakoshi;H. Tsujino;T. Ogata;HIroshi G. Okuno
中科院分区：
文献类型：
--
作者：
Yuichiro Fukubayashi;Kazunori Komatani;Mikio Nakano;Kotaro Funakoshi;H. Tsujino;T. Ogata;HIroshi G. Okuno
口语对话系统的语言理解（LU）模块在其开发的早期阶段需要（i）易于构建和（ii）对各种表达的鲁棒性。传统的LU方法不适用于新的领域，因为它们需要花费大量的精力来制定规则或转录和注释足够的语料库进行训练。在我们的方法中，加权有限状态传感器（WFST）的权重设计在两个层次上，比传统的WFST为基础的方法简单。因此，我们的方法需要更少的训练数据，这使得LU模块的快速原型化成为可能。我们在两个不同的领域评估了我们的方法。结果表明，我们的方法优于基线方法，少于一百个话语作为训练数据，这可以合理地准备新的领域。这表明，我们的方法是适当的LU模块的快速原型。
Language understanding (LU) modules for spoken dialogue systems in the early phases of their development need to be (i) easy to construct and (ii) robust against various expressions. Conventional methods of LU are not suitable for new domains, because they take a great deal of effort to make rules or transcribe and annotate a sufficient corpus for training. In our method, the weightings of the Weighted Finite State Transducer (WFST) are designed on two levels and simpler than those for conventional WFST-based methods. Therefore, our method needs much fewer training data, which enables rapid prototyping of LU modules. We evaluated our method in two different domains. The results revealed that our method outperformed baseline methods with less than one hundred utterances as training data, which can be reasonably prepared for new domains. This shows that our method is appropriate for rapid prototyping of LU modules.