Research on Joint Extraction Model of Financial Product Opinion and Entities Based on RoBERTa

Abstract

With the rapid development of the Internet, and its enormous impact on all aspects of life, traditional financial companies increasingly focus on the user’s online reviews, aiming to promote competitiveness and quality of service in the products of this enterprise. Due to the difficulty of extracting comment text compared with structured data itself, coupled with the fact that it is too colloquial, the traditional model insufficiently semantically represents sentences, resulting in unsatisfactory extraction results. Therefore, this paper selects RoBERTa, a pre-trained language model that has exhibited an excellent performance in recent years, and proposes a joint model of financial product opinion and entities extraction based on RoBERTa multi-layer fusion for the two tasks of opinion and entities extraction. The experimental results show that the performance of the proposed joint model on the financial reviews dataset is significantly better than that of the single model.

Extracting Entities and Relations in Analyst Stock Ratings News

“…There are numerous other applications of automatic information extraction from financial texts using NER (Farmakiotou et al, 2000;Wang et al, 2014;Alvarado et al, 2015;Liao and Shi, 2022), or NER & RE (Jabbari et al, 2020;Zhou and Zhang, 2018). In Repke and Krestel (2021), the reader can find an overview of NER and RE applications in financial texts as well as knowledge graphs construction and analysis.…”

“…In Jacobs and Hoste (2021), the authors have assembled and annotated a corpus of economic and financial news in English language and used it in the context of event extraction, while another study in Yang et al (2018), focused on event extraction from Chinese financial news using automated labeling. Another work in Liao and Shi (2022), solves a joint problem of opinion extraction and NER using a dataset of financial reviews.…”