Bloomberg terminal features11/13/2022 We also have built automatic answering capabilities that can detect and answer frequently occurring client inquiries.įrom a staffing perspective, we have multiple natural language processing and machine learning experts, including former professors and graduates from the best programs. For our internal help system, we have automatic routing systems that direct incoming queries to the appropriate internal experts. This search functionality is deployed across many document collections, but our news search and ranking (NSE) gets significant attention in particular. Furthermore, we’ve built a natural language query interface (e.g., ‘What is IBM’s market cap’) where people can ask questions in plain English and get precise answers. Our search system (HL) is very sophisticated, with state-of-the-art ranking and query understanding. We have a robustly deployed related stories function that highlights additional relevant information to people when they are reading stories.įinally, we have invested heavily in tools that simplify client interaction. Our market moving news indicators (MMN) automatically detect news headlines that are crucially important and tag them. We have also built tools for our reporters that allow them to create self-service topic streams to find pieces of news about the companies or sectors they are responsible for covering.Īll of these core NLP tools stay strictly within the domain of text, but we have also built out significant functionality that connects text to other artifacts – either people or stock tickers. Additionally, we have built research systems for figure understanding that extract the underlying data from scatter plots. One piece of these are table detection and segmentation tools that enable our analysts to increase their scope of ingested data. We have also built out a large suite of tools for structured data. In the law domain, we have built a legal principles engine that enables lawyers to uncover the underlying case law argumentation that supports a particular decision.īeyond these core functions, we have built sophisticated fact extractors (or relationship extractors), that pick out specific information from documents in order to ease our ingestion flow. Beyond that, our topic classification engine (e.g., NI OIL) automatically tags documents with normalized topics to make retrieval and monitoring straight-forward. These named entity extractors are crucial for enabling our sentiment analysis (BSV and TREN) derived indicators that estimate how positive a piece of news is for a particular company. On top of this core tool set, we have built named entity extractors that detect people, companies, tickers and organizations in natural text, which is deployed across our news and social text databases. At the core of this program is a proprietary, robust real-time NLP library that performs low-level text resolution tasks such as tokenization, chunking and parsing. Our engineering teams have built state-of-the-art NLP technology for core document understanding, recommendation, and customer-facing systems.Īt the heart of our NLP program is technology that extracts structured information from documents - sometimes known as digitization or normalization. Over the past decade, we have increased our investment in statistical natural language processing (NLP) techniques that extend our capabilities. Personal information may include your IP address, digital identifiers, and your interactions with digital properties.Throughout the life of the company, Bloomberg has always relied on text as a key underlying source of data for our clients. We and our advertising partners use electronic technologies to collect certain types of personal information through our digital properties in order to provide you with relevant advertisements. They collect information in a way that does not directly identify individuals. These cookies allow us to analyze site usage so we can measure and improve performance. These cookies are required to enable core site functionality. Your choice regarding cookies on this website: Required You may also submit a request via this Do Not Sell My Personal Info link. To opt out of sharing your information for advertising purposes you can choose below under “ Advertising” to opt-out of all or adjust your specific choices. By clicking "Save Settings", you agree to the use of these tools. For more information, please read our Privacy Policy. We, and third parties, use cookies and other electronic tools to enhance your experience, analyze site usage, and deliver advertisements tailored to your interests.
0 Comments
Leave a Reply.AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |