COOL: A framework for conversational OLAP

作者：

Highlights：

• COOL interprets and translates a natural language dialog into an OLAP query.

• COOL handles both full queries and OLAP operators.

• The interpretation relies on a formal grammar and on a knowledge base storing metadata.

• Ambiguities are solved either through automatic inference or through interactions with the user.

• COOL achieves state-of-the-art accuracy in the interpretation of GPSJ queries.

摘要

•COOL interprets and translates a natural language dialog into an OLAP query.•COOL handles both full queries and OLAP operators.•The interpretation relies on a formal grammar and on a knowledge base storing metadata.•Ambiguities are solved either through automatic inference or through interactions with the user.•COOL achieves state-of-the-art accuracy in the interpretation of GPSJ queries.

论文关键词：Natural language processing,OLAP

论文评审过程：Received 4 June 2020, Revised 12 January 2021, Accepted 17 February 2021, Available online 23 February 2021, Version of Record 23 November 2021.

论文官网地址：https://doi.org/10.1016/j.is.2021.101752