- Upgrade to Microsoft Office Pro and Windows 11 Pro with this bundle for 87% off
- Get 3 months of Xbox Game Pass Ultimate for 28% off
- Buy a Microsoft Project Pro or Microsoft Visio Pro license for just $18 with this deal
- How I optimized the cheapest 98-inch TV available to look and sound incredible (and it's $1,000 off)
- The best blood pressure watches of 2024
The business value of NLP: 5 success stories
Data is now one of the most valuable enterprise commodities. According to CIO.com’s State of the CIO 2022 report, 35% of IT leaders say that data and business analytics will drive the most IT investment at their organization this year, and 58% say their involvement with data analysis will increase over the next year.
While data comes in many forms, perhaps the largest pool of untapped data consists of text. Patents, product specifications, academic publications, market research, news, not to mention social feeds, all have text as a primary component and the volume of text is constantly growing. According to Foundry’s Data and Analytics Study 2022, 36% of IT leaders consider managing this unstructured data to be one of their biggest challenges. That’s why research firm Lux Research says natural language processing (NLP) technologies, and specifically topic modeling, is becoming a key tool for unlocking the value of data.
NLP is the branch of artificial intelligence (AI) that deals with training a computer to understand, process, and generate language. Search engines, machine translation services, and voice assistants are all powered by NLP. Topic modeling, for example, is an NLP technique that breaks down an idea into subcategories of commonly occurring concepts defined by groupings of words. According to Lux Research, topic modeling enables organizations to associate documents with specific topics and then extract data such as the growth trend of a topic over time. Topic modeling can also be used to establish a “fingerprint” for a given document and then discover other documents with similar fingerprints.
As interest in AI rises in business, organizations are beginning to turn to NLP to unlock the value of unstructured data in text documents, and the like. Research firm MarketsandMarkets forecasts the NLP market will grow from $15.7 billion in 2022 to $49.4 billion by 2027, a compound annual growth rate (CAGR) of 25.7% over the period.
Here are five examples of how organizations are using natural language processing to generate business results.
Eli Lilly operates at global scale with NLP
Pharmaceutical multinational Eli Lilly is using natural language processing to help its more than 30,000 employees around the world share accurate and timely information internally and externally. The firm has developed Lilly Translate, a home-grown IT solution that uses NLP and deep learning to generate content translation via a validated API layer.
For years, Lilly relied on third-party human translation providers to translate everything from internal training materials to formal, technical communications to regulatory agencies. Now, the Lilly Translate service provides real-time translation of Word, Excel, PowerPoint, and text for users and systems, keeping document format in place. Deep learning language models trained with life sciences and Lilly content help improve translation accuracy, and Lilly is creating refined language models that recognize Lilly-specific terminology and industry-specific technical language, while maintaining the formatting of regulated documentation.
“Lilly Translate touches every area of the company from HR to Corporate Audit Services, to Ethics and Compliance Hotlines, Finance, Sales and Marketing, Regulatory Affairs, and many others,” says Timothy F. Coleman, vice president and information officer for information and digital solutions at Eli Lilly and Co. “The time savings is extensive. Translations are now taking seconds instead of weeks, providing key resources time to focus on other business-critical activities.”
Coleman’s advice: Support passion projects. Lilly Translate started as a passion project by a curious software engineer who had an idea for addressing a pain point of the Lilly Regulatory Affairs system portfolio: Business partners continually experienced delays and friction in translation services. Coleman shared the idea and technical vision with peers and managers, immediately garnering the project support from leadership at Eli Lilly Global Regulatory Affairs International, who advocated for investment in the tool.
“[The idea] married up well with an opportunity to explore and learn emerging technologies,” Coleman says. “It became a great opportunity that a Lilly software engineer picked up and ran with, initially as a great learning opportunity.”
Accenture analyzes contracts using NLP
Accenture is leveraging natural language processing for legal analytics. The company’s Accenture Legal Intelligent Contract Exploration (ALICE) project helps the global services firm’s legal organization of 2,800 professionals perform text searches across its million-plus contracts, including searches for contract clauses.
ALICE uses “word embedding,” an NLP method that facilitates comparisons between words based on semantic similarity. The model goes through contract documents paragraph by paragraph, looking for keywords to determine whether the paragraph relates to a particular contract clause type. For example, words like “flood,” “earthquake,” or “disaster” commonly occur with the clause “force majeure.”
“The use cases have grown as we continued to use this capability and to stretch it and enhance it as we see additional value opportunities,” says Mike Maresca, global managing director of digital business transformation, operations, and enterprise analytics at Accenture. “We’re finding new ways to harvest value from the data that we have.”
Accenture says the project has significantly reduced the amount of time attorneys have to spend manually reading through documents for specific information.
Maresca’s advice: Don’t be afraid to dive into NLP. “If innovation is part of your culture, you can’t be afraid to fail,” Maresca says. “Let’s experiment and iterate.”
NLP helps Verizon process customer requests
Verizon’s Business Service Assurance group is using natural language processing and deep learning to automate the processing of customer request comments. The group receives more than 100,000 inbound requests per month that had to be read and individually acted upon until Global Technology Solutions (GTS), Verizon’s IT group, created the AI-Enabled Digital Worker for Service Assurance.
Digital Worker integrates network-based deep learning techniques with NLP to read repair tickets that are primarily delivered via email and Verizon’s web portal. It automatically responds to the most common requests, such as reporting on current ticket status or repair progress updates. More complex issues are routed to human engineers.
“By automating responses to these requests, we respond within minutes as opposed to hours after the email was sent,” says Stefan Toth, executive director of systems engineering for Verizon Business Group’s Global Technology Solutions (GTS).
In February 2020, Verizon said Digital Worker had saved nearly 10,000 worker hours per month since the second quarter of the previous year.
Toth’s advice: Look to open source. “Look around and connect with your business partners and I’m sure you’ll find opportunities,” Toth says. “Look at open source and experiment before making large financial commitments to a platform. We found there’s a lot available now in open source.”
Great Wolf Lodge tracks customer sentiment with NLP-powered AI
Hospital and entertainment chain Great Wolf Lodge’s Artificial Intelligence Lexicographer (GAIL) sifts through comments in its monthly surveys and determines whether the writers are likely to be a net promoter, detractor, or neutral party.
The AI, which leverages natural language processing, was trained specifically for hospitality on more than 67,000 reviews. GAIL runs in the cloud and uses algorithms developed internally, then identifies the key elements that suggest why survey respondents feel the way they do about GWL. As of September 2019, GWL said GAIL can make determinations with 95 percent accuracy. GWL uses traditional text analytics on the small subset of information that GAIL can’t yet understand.
“We want to better engage with guests at all points,” says Edward Malinowski, CIO of GWL.
GWL’s business operations team uses the insights generated by GAIL to fine-tune services. The company is now looking into chatbots that answer guests’ frequently asked questions about GWL services.
Malinowski’s advice: Avoid tech for tech’s sake. Pick tools that strike the right balance of tech and practical utility — and that are aligned with business objectives. “You have to be careful of what’s gimmicky and what’s a solution in search of a problem,” Malinowski says.
Aetna resolves claims rapidly with NLP
Health insurer Aetna has created the Auto-adjudication of Complex Provider Contracts application to automate the process of reading notes about payment, deductible, and extraneous fee explanations in each contract, then calculate pricing and update the claim.
The application blends natural language processing and special database software to identify payment attributes and construct additional data that can be automatically read by systems. As a result, many claims can be resolved overnight.
The application has enabled Aetna to refocus 50 claims adjudication staffers to contracts and claims that require higher-level thinking and more coordination among care providers.
“It really comes down to providing a better experience for end users,” says Aetna CTO Claus Jensen, adding that the software will help the company be a better partner in the healthcare ecosystem for providers and patients. “We have to do more than just pay the bills and answer questions on the phone.”
As of July 2019, Aetna was projecting an annual savings of $6 million in processing and rework costs as a result of the application.
Jensen’s advice: Narrow your focus and take your time. In an ideal world, companies would implement AI that tackles narrow-band problems. Broad-based solutions are murky and will ultimately fail, Jensen says, adding that if Aetna tried to apply general AI to its business it wouldn’t work. Also, Aetna spent several months instrumenting the process, codifying the rules and testing the app. Jensen says many people don’t have the patience to slow down and do things the right way.