Speech act identification using an ontology-based partial pattern tree

Chung Hsien Wu, Jui Feng Yeh, Ming Jun Chen

研究成果: Paper同行評審

2 引文 斯高帕斯(Scopus)

摘要

This paper presents an ontology-based partial pattern tree to identify the speech act in a spoken dialogue system. This study first extracts the key words/concepts in an application domain using latent semantic analysis (LSA). A partial pattern tree is used to deal with the ill-formed sentence problem in a spoken dialogue system. Concept expansion based on domain ontology is adopted to improve system performance. For performance evaluation, a medical dialogue system with multiple services, including registration information, clinic information and FAQ information, is implemented. Four performance measures were separately used for evaluation. The speech act identification rate achieves 86.2%. A Task Success Rate of 77% is obtained. The contextual appropriateness of the system response is 78.5%. Finally, the correct rate for FAQ retrieval is 82% with an improvement of 15% in comparison with the keyword-based vector space model. The results show the proposed ontology-based partial pattern tree is effective for dialogue management.

原文English
頁面2157-2160
頁數4
出版狀態Published - 2004 1月 1
事件8th International Conference on Spoken Language Processing, ICSLP 2004 - Jeju, Jeju Island, Korea, Republic of
持續時間: 2004 10月 42004 10月 8

Other

Other8th International Conference on Spoken Language Processing, ICSLP 2004
國家/地區Korea, Republic of
城市Jeju, Jeju Island
期間04-10-0404-10-08

All Science Journal Classification (ASJC) codes

  • 語言與語言學
  • 語言和語言學

指紋

深入研究「Speech act identification using an ontology-based partial pattern tree」主題。共同形成了獨特的指紋。

引用此