A trainable generator for recommendations in multimodal dialog

INTERSPEECH(2003)

引用 39|浏览14
暂无评分
摘要
As the complexity of spoken dialogue systems has increased, there has been increasing interest spoken language generation (SLG). SLG promises portability across application domains and dialogue situations through the development of application- independent linguistic modules. However in practice, rule- based SLGs often have to be tuned to the application. Recently, a number of research groups have been developing hybrid meth- ods for spoken language generation, combining general linguis- tic modules with methods for training parameters for particular applications. This paper describes the use of boosting to train a sentence planner to generate recommendations for restaurants in MATCH, a multimodal dialogue system providing entertain- ment information for New York.
更多
查看译文
关键词
rule based
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要