To enable natural language interfaces to databases more efficient and robust,two kinds of techniques,language paraphrasing and result analyzing,are widely used to help users to understand the system's intermediate...To enable natural language interfaces to databases more efficient and robust,two kinds of techniques,language paraphrasing and result analyzing,are widely used to help users to understand the system's intermediate language,and the query result meaning in some times. For the limitation of intermediate language adopted in some NLIDBs ,they could not give efficient and practical paraphrasing algorithms. Based on semantic dependency tree in NChiql,we present a completed paraphrasing algorithm which is suitable to Chinese languages.展开更多
The performance and reliability of converting natural language into structured query language can be problematic in handling nuances that are prevalent in natural language. Relational databases are not designed to und...The performance and reliability of converting natural language into structured query language can be problematic in handling nuances that are prevalent in natural language. Relational databases are not designed to understand language nuance, therefore the question why we must handle nuance has to be asked. This paper is looking at an alternative solution for the conversion of a Natural Language Query into a Structured Query Language (SQL) capable of being used to search a relational database. The process uses the natural language concept, Part of Speech to identify words that can be used to identify database tables and table columns. The use of Open NLP based grammar files, as well as additional configuration files, assist in the translation from natural language to query language. Having identified which tables and which columns contain the pertinent data the next step is to create the SQL statement.展开更多
文摘To enable natural language interfaces to databases more efficient and robust,two kinds of techniques,language paraphrasing and result analyzing,are widely used to help users to understand the system's intermediate language,and the query result meaning in some times. For the limitation of intermediate language adopted in some NLIDBs ,they could not give efficient and practical paraphrasing algorithms. Based on semantic dependency tree in NChiql,we present a completed paraphrasing algorithm which is suitable to Chinese languages.
文摘The performance and reliability of converting natural language into structured query language can be problematic in handling nuances that are prevalent in natural language. Relational databases are not designed to understand language nuance, therefore the question why we must handle nuance has to be asked. This paper is looking at an alternative solution for the conversion of a Natural Language Query into a Structured Query Language (SQL) capable of being used to search a relational database. The process uses the natural language concept, Part of Speech to identify words that can be used to identify database tables and table columns. The use of Open NLP based grammar files, as well as additional configuration files, assist in the translation from natural language to query language. Having identified which tables and which columns contain the pertinent data the next step is to create the SQL statement.
