Understand all organizations, people, Start Your Free Trial
places and things in text
Making sense of text requires understanding the who, what and where. While humans do this naturally, machines struggle. Enter NERD. NERD identifies the entities in text – the companies, people, organizations, events, places etc. – and connects them to data and other information in S&P Capital IQ and Wikimedia, unlocking new understanding and insights.
No other solution offers NERD’s combination of accuracy, general breadth and business and financial depth. See for yourself!
…entities recogizable by NERD!
Quick NERD Overview
Kensho NERD Use Cases
NERD is a valuable tool for anyone dealing with high volumes of text, documents, or unstructured data. For large enterprises, academics, financial or professional service providers, government bodies and more, NERD makes your text intelligible and searchable in a snap.
Frequently Asked Questions (FAQs)
Kensho combines the latest advances in machine learning with S&P Global’s unparalleled data universe to train the models that make up NERD.
NERD has learned from the patterns in millions of documents, with a special focus on financial and business-related text, from news articles to earnings call transcripts. Many of these documents are hand-labeled by Kensho’s domain experts in the financial and business worlds, so as to teach NERD to extract accurate information from such text.
NERD is designed to extract entities out of standard English text documents comprising complete sentences. While NERD is by no means limited to formal, lengthy texts, it will function optimally on documents written with conventional grammatical structure.
One of NERD’s most powerful features is its context-awareness. For example, references to ‘the Supreme Court’ in news stories, where the context provided by the story tells you which Supreme Court this refers to (e.g., the Supreme Court of Kenya vs. the Supreme Court of the United States). Documents whose entities make sense from the text’s surrounding context are ideally situated to take advantage of contextual extraction. NERD achieves excellent performance on a diverse array of document types, from emails to research reports.
NERD is not a keyword or fuzzy matching product. Such products suffer from low accuracy and highly unstable results, even on simple examples. For instance, a text matching engine would struggle to determine whether “TSLA“ refers to a Task Service Level Agreement or to the ticker symbol for Tesla, Inc.
Instead, NERD uses a bespoke combination of fine-tuned, domain-specific neural networks and ensembled tree-based learning algorithms, along with granular heuristics informed by human subject-matter experts, to extract and link the entities in a document consistently and accurately.
NERD is designed to recognize companies at the appropriate levels of their corporate hierarchies. Parent companies and their subsidiaries are both distinguished and represented according to the relationships contained in Capital IQ. NERD reports the most up-to-date information for these relationships -- even if the corporate hierarchies or names have changed.
NERD is accessed via REST API. Simply input your text, specify to which knowledge base(s) you would like to link, and get your results. NERD’s results are returned as a list of JSON annotations, each corresponding to a mention of an entity in your document. Each annotation will include: Location of the entity in the text, Entity Name, Entity ID in either Capital IQ or Wikidata, Entity Type and other relevant metadata.
Kensho takes your privacy and security seriously. Data submitted to NERD is only temporarily stored in order to perform the service and is secured from being accessed by others. Contact us to learn more.
Why Kensho NERD?
Unstructured data represents 90% of all data in existence, but only 18% of organizations report using it effectively. Unstructured data presents organizations with an opportunity to turn cost into intelligence and competitive differentiation.
Text is ubiquitous in unstructured data, whether emails, articles, documents, audio and/or video transcripts, reports, log files, presentations, social media posts, or any one of many other formats.
Like many organizations, S&P Global is awash with unstructured text data, with millions of documents, articles, transcripts, etc. generated each year. Effectively processing such data was a strategic imperative to find operational efficiencies, new revenue streams and business intelligence.
Kensho developed NERD to help S&P address this challenge. S&P Global has used NERD to great success. NERD has enriched 55M+ docs and has made 600M+ new connections to S&P Global’s company databases. NERD can do the same for your organization; we are eager to help!