The economy of the twenty-first century has shaped the economic landscape and changed the way market stakeholders interact with one another in a global market where national borders have melted and trades have become more open and free, resulting in a more competitive business world. Indeed, rivalry has moved from the local market level to the multinational level, inciting companies and industries to strengthen their capacity for innovation in order to deliver competitive products and services, expand their economic growth, and improve economic performances. In this context, the available business and financial textual information on the internet (e.g., company announcements, industry research reports, online news articles, and policy statements) has become a major source of information for companies and professionals to keep track of their complex, rapidly changing, and competitive business environment. Furthermore, textual content is no longer limited to English; multilingual content has emerged to assist businesses in improving their customer experience and expanding their regional and global market presence. The primary goal of this dissertation is to develop a system capable of structuring these multilingual textual data and reconstructing the business network from them by identifying business interactions between the market's key players. We build a multilingual dataset for business relationship extraction, which is then used to train a variety of neural-based supervised models. Our findings are encouraging, and they represent the first step toward extracting multilingual business relationships from the web.