Machine Learning: Emerging use cases of NLP

AI Solutions Development: Emerging use cases of NLP

First thing to know: This isn’t futuristic stuff. Natural language processing is happening right under your nose. Sports broadcasters do it all the time, using machines to generate narrative based on scores and statistics. Many universities routinely turn to NLP to screen for plagiarism in student work.

The healthcare industry is eager to leverage this emerging capability, with NLP playing a prominent role in the “10 Promising AI Applications Development in Health Care” recently identified by Accenture. For example, virtual nurse assistants could save $20 billion annually by taking on some of the first line responsibilities for interviewing and assessing patients.

Furthermore, a 2016 poll by analytics firm HealthMine found that while 60 percent of patients could access their electronic medical data, 15 percent had trouble understanding it and just 22 percent used it to make medical decisions. Some see NLP as a means to bridge the language gap between doctors and patients.

Researchers from Yale University, the University of Massachusetts and Bedford VA Medical Center have addressed this point. In a recent study they applied an NLP algorithm to clinical documents, tracking medical terms to their lay-language equivalents and making it easier for patients to understand their doctors’ instructions.

As a business tool, some say NLP could help drive better decision making by applying computer intelligence to insights harvested from news, social media, financial influencers and blogs. NLP could identify hot topics of discussion, chart consumer interest and potentially aid in business decision-making. For example, marketers are increasingly using sentiment analysis to mine social media for consumer insights regarding brand favorability and preference.

Others see in NLP the ability to streamline business processes. JPMorgan Chase, for instance, has developed a proprietary algorithm called COiN to analyze legal documents. The bank says this could save countless hours of manual labor and significantly reduce errors in loan servicing.

On the federal side, NLP offers a range potential benefits across diverse use cases.

Government use cases

In a recent study, researchers from Duke Law, the University of Southern California and Stanford Law School pitted an AI contract review platform against a team of lawyers. The computers achieved an average 94 percent accuracy rate at surfacing risks in Non-Disclosure Agreements (NDAs), one of the most common legal agreements used in business, versus an average of 85 percent for experienced lawyers.

Better still: It took the machines an average of 26 seconds to complete the task, compared to an average of 92 minutes for the lawyers. This shows that AI can hold its own in performing human tasks and suggests that the pairing of AI and humans together could deliver even more powerful results.

This has big implications for government at a time when agency headcount continues to decline, while the sheer volume of data increases exponentially. Citizens deserve an AI-empowered government, one that can process requests in a timely way and can cut down on the backlog that plagues so many citizen-facing agencies. NLP can do this by handily summarizing and prioritizing information.

The NLP-equipped computers achieved an average 94 percent accuracy rate at surfacing risks in NDAs, versus an average of 85 percent for experienced lawyers.

The Department of Health and Human Services (HHS) has piloted the use of NLP to process public comments on new regulations, which can require over 1,000 hours just to categorize for a single proposed rule. The tool was able to meet quality requirements and improve staff satisfaction, allowing one agency to demonstrate millions in cost savings.

The low-hanging fruit here may well lie with the agency help desk, where AI can be trained on the FAQs. NLP could route calls effectively, easing the burden on help desk staff, and could even help to resolve queries that are purely informational. In mature contact centers, Accenture has found that costs can be reduced by 30 percent with higher customer satisfaction through expanded use of more intelligent virtual assistants.

Some agencies already are moving in this direction. U.S. Citizenship and Immigration Services (USCIS) for instance has introduced Emma, a voice-powered personal assistant that can understand and speak both Spanish and English. Other agencies are looking to Emma as a model for what may be possible on the citizen-service side, with natural language enabling organic conversations and helping to fulfill routine requests with little to no human intervention.

As our population continues to age, finding new ways to enable the elderly to lead productive, independent lives will grow in importance. An Accenture pilot in the United Kingdom used Amazon Echo devices to empower caregivers to provide more virtual care and support. And working with the UK’s National Theatre, we developed a device using NLP for real-time audio captioning for those with loss of hearing.

While these use cases focus on the spoken word, government also may have much to gain from the ability to both analyze and generate text.

For example, Accenture is working with government agencies responsible for processing benefits claims for citizens. A key challenge is the inordinate volume of documentation requiring manual review to ensure information is correct and consistent. NLP can do that, “reading” documents at computer speed to ensure citizens are eligible for services or benefits. The machines won’t make the final call—no one likes to think of AI rejecting a health care claim!—but they can flag suspicious entries, inconsistencies or apparent discrepancies. Rather than wade through 100 pages of detail, a human reviewer can skip to the two pages where things look sticky, or the computer can automatically confirm that claims are supported by the text.

NLP is also a core technology for link analysis, which allows analysts and researchers to make network correlations across data, whether it be medical research, search engine optimization or criminal investigations. In this context, NLP technologies like latent semantic indexing can play an important role in concept matching, eDiscovery and disambiguation, allowing conceptual relationships to be identified even when not readily apparent.

In the near future, some expect NLP will become adept not just at reading government documents, but at writing them, too. Many agencies are tasked with generating reports, typically based on tables of data. 

What if the machines could read the data and formulate human-sounding sentences and paragraphs?

Another scenario that’s easy to envision centers upon document retention. Various agencies are charged with keeping documents for certain lengths of time, in response to Freedom of Information Act requirements and other regulations. Typically, documents are marked for retention by a manual process: That’s time consuming, tedious and error prone. A better idea would be to have the machine read and classify documents, automatically filing them according to authorized release dates.

In each case, the sweet spot for NLP lies somewhere at the intersection of simplicity and repeatability. AI shines brightest when it helps to automate routine tasks, where the level of complexity is fairly low and where the high frequency gives the AI the opportunity to learn from many repeated instances.

How exactly could government put NLP to work, and who would be in charge of that? It’s worth a deeper dive.

Article source: https://www.accenture.com/us-en/insights/us-federal-government/nlp-emerging-uses