Commentary generation for financial markets

作者：

Highlights：

• A methodology for generating market-wide commentary for financial time series data.

• Consideration of both informativeness and compliance to linguistic constraints.

• Ability to deliver high-quality results even when the number of reference commentaries is small.

• Explainable commentaries that can be traced back to interesting events in the underlying time series data.

摘要

•A methodology for generating market-wide commentary for financial time series data.•Consideration of both informativeness and compliance to linguistic constraints.•Ability to deliver high-quality results even when the number of reference commentaries is small.•Explainable commentaries that can be traced back to interesting events in the underlying time series data.

论文关键词：NLP,NLG,Text mining,Summarization,Financial markets

论文评审过程：Received 27 July 2021, Revised 13 July 2022, Accepted 1 August 2022, Available online 17 August 2022, Version of Record 26 August 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118364