设计并实现了一个基于FAQ(Frequently Asked Question)的OTC(Over The Counter)问答系统。描述了该系统的工作流程、系统结构;详细阐述了系统实现的关键技术,包括基于倒排索引的查找算法、根据用户问题建立候选问题集和基于知网的语义...设计并实现了一个基于FAQ(Frequently Asked Question)的OTC(Over The Counter)问答系统。描述了该系统的工作流程、系统结构;详细阐述了系统实现的关键技术,包括基于倒排索引的查找算法、根据用户问题建立候选问题集和基于知网的语义相似度计算方法等。运行结果表明,对于常问问题和普遍性的问题,系统有很高的准确率。展开更多
Purpose: The purpose of this study is to develop an automated frequently asked question(FAQ) answering system for farmers. This paper presents an approach for calculating the similarity between Chinese sentences based...Purpose: The purpose of this study is to develop an automated frequently asked question(FAQ) answering system for farmers. This paper presents an approach for calculating the similarity between Chinese sentences based on hybrid strategies.Design/methodology/approach: We analyzed the factors influencing the successful matching between a user's question and a question-answer(QA) pair in the FAQ database. Our approach is based on a combination of multiple factors. Experiments were conducted to test the performance of our method.Findings: Experiments show that this proposed method has higher accuracy. Compared with similarity calculation based on TF-IDF,the sentence surface forms and the semantic relations,the proposed method based on hybrid strategies has a superior performance in precision,recall and F-measure value.Research limitations: The FAQ answering system is only capable of meeting users' demand for text retrieval at present. In the future,the system needs to be improved to meet users' demand for retrieving images and videos.Practical implications: This FAQ answering system will help farmers utilize agricultural information resources more efficiently.Originality/value: We design the algorithms for calculating similarity of Chinese sentences based on hybrid strategies,which integrate the question surface similarity,the question semantic similarity and the question-answer similarity based on latent semantic analysis(LSA) to find answers to a user's question.展开更多
文摘设计并实现了一个基于FAQ(Frequently Asked Question)的OTC(Over The Counter)问答系统。描述了该系统的工作流程、系统结构;详细阐述了系统实现的关键技术,包括基于倒排索引的查找算法、根据用户问题建立候选问题集和基于知网的语义相似度计算方法等。运行结果表明,对于常问问题和普遍性的问题,系统有很高的准确率。
基金jointly supported by the National Social Science Foundation of China(Grant Nos.:08ATQ003 and 10&ZD134)
文摘Purpose: The purpose of this study is to develop an automated frequently asked question(FAQ) answering system for farmers. This paper presents an approach for calculating the similarity between Chinese sentences based on hybrid strategies.Design/methodology/approach: We analyzed the factors influencing the successful matching between a user's question and a question-answer(QA) pair in the FAQ database. Our approach is based on a combination of multiple factors. Experiments were conducted to test the performance of our method.Findings: Experiments show that this proposed method has higher accuracy. Compared with similarity calculation based on TF-IDF,the sentence surface forms and the semantic relations,the proposed method based on hybrid strategies has a superior performance in precision,recall and F-measure value.Research limitations: The FAQ answering system is only capable of meeting users' demand for text retrieval at present. In the future,the system needs to be improved to meet users' demand for retrieving images and videos.Practical implications: This FAQ answering system will help farmers utilize agricultural information resources more efficiently.Originality/value: We design the algorithms for calculating similarity of Chinese sentences based on hybrid strategies,which integrate the question surface similarity,the question semantic similarity and the question-answer similarity based on latent semantic analysis(LSA) to find answers to a user's question.
