Fact Check: Analyzing Financial Events from Multilingual News Sources
This addresses the problem of information overload for investment analysts by providing a tool to analyze financial events from multilingual sources, though it appears incremental as it builds on existing deep learning and fact-checking methods.
The paper tackles the challenge of extracting insights from complex multilingual financial news by proposing FactCheck, a web-based aggregator with deep learning models that extracts events using unsupervised clustering and includes a transformer-based fact-checker. The fact-checker outperforms strong baselines on a merger and acquisition dataset.
The explosion in the sheer magnitude and complexity of financial news data in recent years makes it increasingly challenging for investment analysts to extract valuable insights and perform analysis. We propose FactCheck in finance, a web-based news aggregator with deep learning models, to provide analysts with a holistic view of important financial events from multilingual news sources and extract events using an unsupervised clustering method. A web interface is provided to examine the credibility of news articles using a transformer-based fact-checker. The performance of the fact checker is evaluated using a dataset related to merger and acquisition (M\&A) events and is shown to outperform several strong baselines.