Plexi NLP – language heuristics engine

web-scale language analysis

Consume, summarize, implement and automate with Plexi NLP

Plexi NLP is the core of all Stremor's products. A language processing system that uses heuristic models to extract information from text, Plexi NLP is the most feature rich language heuristics engine ever built. Plexi NLP extracts information about sentence and paragraph structure, word usage, parts of speech, grammar, writing style, punctuation, and author bias. This information provides insight into unstructured data and can be used in conjunction with Big Data system to unlock information, which was previously only minable through human data entry.

fits any platform or application

Plexi NLP offers all language analytics features through its API. It has the ability to summarize content to any length and at any level of detail. Extracting sentiment, bias, reading level, technical level, formality, urgency, and whether or not content is editorial in nature, are just a few examples of the language scores returned. Plexi NLP can also detect action items in the text. For example, if the author was looking for a follow up, the people mentioned, the time, the phone numbers, and the places.

Plexi NLP contains rules that range in the millions. Rules to determine if the writing style is formal or casual. Rules to determine if the author is for or against the subject matter. Rules to determine if the author is making an argument and if points made support the argument. It can even make inferences about the credibility of those points. This is possible through the vast amounts of data poured into its database about how words can typically be used and what they mean. 

Plexi NLP works on content for any device

language analysis

Whether data mining or developing a knowledge base for internal use, organizations need to convert unstructured data from text, email, marketing materials, and support communications. The problem is, Big Data is turning the information from millions of new web pages, blogs, tweets, news articles, and comments, into actionable items for business decision making. However, Big Data only works for structured, normalized data. Creating structured, minable, and actionable data at web-scale is well beyond human capacity and requires automation. Plexi NLP delivers the core foundation of that automation.

Examples of the types of extraction to structured data and content tagging that can be performed by Plexi NLP include: 

Action Items: Extraction of action items from communications reader or external event handler. Finds appointment requests in emails and discovers completed tasks in support tickets.

People & Places: Identification of people and/or places mentioned in a document enables prioritization of emails, link generation, and categorization.

Keywords: Determination of keywords that define a document's subject matter.

Facts: Detection of key facts, statistics, quantities, and other verifiable data.

Reading Level: Determination of the reading level of a document based on vocabulary, sentence complexity, and other factors.

Date & Time: Extraction of time and date data from a document body or identification about relative temporal information (e.g. "last Tuesday" or "next Friday").

Plexi NLP F.A.Q.

What does the Plexi NLP API do?
The Plexi NLP API provides access to the core features that demonstrate Stremor’s consumer applications. It summarizes, analyzes, suggests improvements, finds related keywords, and detects sentiment and bias. It can also extract phone numbers, people, places, and price labels from text.
How is Plexi NLP different from previous sentiment detection?
Sentiment detection is not new, but the way that Plexi NLP does it is. Sentiment detection in the past has been binary, likes or dislikes. That is not how people write, nor is it how people think. An author more often will like some features of a product and dislike others. They might compare a product to another product, which causes false positives or negatives in other technologies. An author might even use sarcasm, which may reverse the sentiment from the written text. Plexi NLP addresses these issues and more.
What is “language heuristics?”
Language heuristics is the application of math and psychology to language. Words have meaning, but they also have connotation. “Small,” “compact,” and “puny” are synonyms, but do not have the same connotation to readers. For example, a consumer may be in the market for a “compact car” or something in the “small car” class, but would be insulted if someone referred to their car as “puny.” “Minuscule” is an insult when used in reference to intelligence, but neutral when describing particles in a scientific work. Language heuristics is the science of constructing these types of rules so that the intent, meaning, and psychographic of the author can be extracted.
What kind of scores does it return?
Language is deeply complex. As a result, so are the scores Plexi NLP returns. Some of these scores are very straightforward, such as the "sentence importance." Others, like “implied formality” is harder to use directly. Plexi NLP returns scores for how much emotion is expressed, if the author makes conclusions or absolutisms, the technical level of the content, the subjectivity, the amount of description used, and much more.
Can the length of summaries be specified?
There is no need. Each sentence is returned with a score for its importance, so developers can simply pick however many of the top sentences they need. The technology also considers that if an important sentence requires the sentence before it, it will return scores that will reflect this.
Why does the world need a language heuristics engine?
Combine the content from the web, email communications, and support tickets, it is easy to see that the “Information Age” long ago crossed a tipping point where the overwhelming amount of content is no longer able to be indexed merely by keywords and phrases alone. Plexi NLP provides a means to sort content by a wide range of language indicators from something as simple as temporal relevance to more complex factors, such as the target audience, meaning, or author integrity.
What advantage does the API offer content publishers?
The full answer would require much more than one sheet. In short, Plexi NLP API can be a simple panacea for mobile efforts by converting articles to lengths optimized for mobile screens, freeing publishers from maintaining multiple versions. It can be a tightly integrated part of an editorial process that helps writers maintain style standards along with a long list of author-time optimization features. This accelerates speed to publication by reducing the time it takes to approve new content.
What can it do for enterprise CRM applications?
There is an untapped treasure trove of valuable information locked away in all the communications, support, and consumer feedback archives. Converting language to factors for big data analysis unlocks that treasure for insights achievable no other way.

More questions?

Want to learn more about the full capabilities of Plexi NLP and related applications? Drop us an email.

Technology Questions

Just send an email sales(at sign), indicate you have technology questions in your subject line, and our mad scientist CTO, Brandon Wirtz, will do his best to explain how Plexi NLP can fit into your current deployments.

Sales Questions

For all sales enquiries, please send an email to sales(more at signs) and our Director of Business Development, Russ Hedgpeth, will get in touch with you as quickly as possible to discuss your needs.