[4Rin1] インタラクティブセッション２

[4Rin1-25] Extraction of Business Contents from Financial Reports Using Recurrent Neural Network Model

〇Tomoki Ito¹, Hiroki Sakaji¹, Kiyoshi Izumi¹ (1. The University of Tokyo)

キーワード：Financial Text Mining, Information Ritrieval, Application

To extract business contents automatically from financial reports is an important problem in the financial industry.
Especially, segment names and their explanations are important contents to be extracted.
However, the methods for extracting these types of information from financial reports have not been established.
In this study, we aim to develop a practical solution for extracting these types of information.
To solve this problem, we developed a manually annotated dataset for the task of extracting the segment names and their explanations of each company from financial reports and then developed a recurrent neural network model to solve this task.
Our developed method using the manually annotated dataset outperformed the baseline methods without the dataset in the task of extracting segment names and their explanations of each company.
This results demonstrated that our approach is useful for extracting the business contents of each company.
This work is the first work for applying a machine learning method to the task of extracting segment names and their explanations.
Insights from this work should be useful in the industrial area.