tailieunhanh - Báo cáo khoa học: "Towards Web-Based Evaluation of Automatic Natural Language Phrase Generation"

This paper describes a novel approach for the automatic generation and evaluation of a trivial dialogue phrases database. A trivial dialogue phrase is defined as an expression used by a chatbot program as the answer of a user input. A transfer-like genetic algorithm (GA) method is used to generating the trivial dialogue phrases for the creation of a natural language generation (NLG) knowledge base. The automatic evaluation of a generated phrase is performed by producing n-grams and retrieving their frequencies from the World Wide Web (WWW). Preliminary experiments show very positive results. . | Is It Correct - Towards Web-Based Evaluation of Automatic Natural Language Phrase Generation Calkin S. Montero and Kenji Araki Graduate School of Information Science and Technology Hokkaido University Kita 14-jo Nishi 9-chome Kita-ku Sapporo 060-0814 Japan calkin araki @ Abstract This paper describes a novel approach for the automatic generation and evaluation of a trivial dialogue phrases database. A trivial dialogue phrase is dehned as an expression used by a chatbot program as the answer of a user input. A transfer-like genetic algorithm GA method is used to generating the trivial dialogue phrases for the creation of a natural language generation NLG knowledge base. The automatic evaluation of a generated phrase is performed by producing n-grams and retrieving their frequencies from the World Wide Web WWW . Preliminary experiments show very positive results. 1 Introduction Natural language generation has devoted itself to studying and simulating the production of written or spoken discourse. From the canned text approach in which the computer prints out a text given by a programmer to the template filling approach in which predetermined templates are hlled up to produce a desired output the applications and limitations of language generation have been widely studied. Well known applications of natural language generation can be found in human-computer conversation HCC systems. One of the most famous HCC systems ELIZA Weizenbaum 1966 uses the template hlling approach to generate the system s response to a user input. For a dialogue system the template hlling approach works well in certain situations however due to the templates limitations nonsense is produced easily. In recent research Inui et al. 2003 have used a corpus-based approach to language generation. Due to its flexibility and applicability to open domain such an approach might be considered as more robust than the template hlling approach when applied to dialogue systems. In .