Speech act identification using an ontology-based partial pattern tree
نویسندگان
چکیده
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.
منابع مشابه
Ontology-based speech act identification in a bilingual dialog system using partial pattern trees
متن کامل
A Pragmatic Study of Requestive Speech Act by Iranian EFL Learners and Canadian Native Speakers in Hotels
This study was an attempt to shed light on the use of requestive speech act by Iranian nonnative speakers (NNSs) of English and Canadian native speakers (NSs) of English to find out the (possible) similarities and/or differences between the request realizations, and to investigate the influence of the situational variables of power, distance, context familiarity, and L1’s (possible) influence. ...
متن کاملDevelopment of a Combined System Based on Data Mining and Semantic Web for the Diagnosis of Autism
Introduction: Autism is a nervous system disorder, and since there is no direct diagnosis for it, data mining can help diagnose the disease. Ontology as a backbone of the semantic web, a knowledge database with shareability and reusability, can be a confirmation of the correctness of disease diagnosis systems. This study aimed to provide a system for diagnosing autistic children with a combinat...
متن کاملDevelopment of a Combined System Based on Data Mining and Semantic Web for the Diagnosis of Autism
Introduction: Autism is a nervous system disorder, and since there is no direct diagnosis for it, data mining can help diagnose the disease. Ontology as a backbone of the semantic web, a knowledge database with shareability and reusability, can be a confirmation of the correctness of disease diagnosis systems. This study aimed to provide a system for diagnosing autistic children with a combinat...
متن کاملDialogue act detection in error-prone spoken dialogue systems using partial sentence tree and latent dialogue act matrix
In a goal-oriented spoken dialogue system, the major aim of spoken language understanding is to detect the dialogue acts (DAs) embedded in a speaker’s utterance. However, errorprone speech recognition often degrades the performance of the SLU component. In this work, a DA detection approach using partial sentence trees (PSTs) and a latent dialogue act matrix (LDAM) is presented for spoken langu...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2004