Natural Language Processing Applications for State Governments


“When you start to contemplate the hundreds and thousands and tens of thousands of hours of media that are recorded, it’s literally impossible for individual humans to sit there and listen to it all,” says Morper. “Technology like NLP can process this media so that it can create a transcript of what that conversation was or what was said in that video. Then you can apply keyword research to that transcript, and you can start eliminating massive amounts of audio and video quickly so you can start building a compelling case to pursue.

In Texas, state officials use NLP for chatbots and to read emails to send them to the appropriate departments to facilitate the workflow. For example, during the pandemic, an agency was receiving 2,000 service tickets per day, 80% of which were requests for help with resetting passwords, says Krishna Edathil, director of the Texas Artificial Intelligence Center of Excellence (AI- CoE).

Thanks to NLP, password requests have been isolated from the main help desk inbox so that the appropriate teams can resolve the most pressing issues.

Edathil says the biggest benefits of NLP have been the efficiency and productivity it has brought to his office.

“It’s becoming a great digital assistant that helps manage growing cases and requests for IT support,” he says, especially when every state agency has full-time employee caps that ‘she cannot overtake.

Other use cases in the era of the pandemic have also emerged.

IBM’s NLP technology helps state and local governments care for their constituents and deliver their messages. The Rhode Island Department of Health has a virtual assistant called Rhoda who has helped residents locate COVID-19 testing sites and manage vaccine eligibility and travel restrictions, Dobrin says.

RELATED: How is the use of artificial intelligence accelerating in state government?

Best Natural Language Processing Techniques and Steps

Some of the most common ways to use NLP are in text-to-speech and text-to-speech applications; in sentiment analysis to extract meaning from a text such as emotions, tone or sarcasm; for word meaning disambiguation to select the meaning of a word which may have multiple meanings; and for natural language generation to transform structured data into human language, says Dobrin.

Edathil’s center uses it primarily for sentiment analysis, where a bot could help prioritize emails by understanding the content of customer complaints and concerns.

“This is not limited to email; this is for any form of text. The responses on social media and conversations with chatbots are prime examples, ”he says.

The steps to using NLP begin with lexical analysis, then parsing, semantic analysis, speech integration, and pragmatic analysis, she says. While some models require users to do it themselves, Texas AI-CoE relies on major cloud providers, such as Microsoft, Google, and Amazon, who have already implemented this technology through Platform as a Service. .

MORE FROM STATETECH: Find out why states are deploying computer vision technology.

The future of natural language processing in government operations

For government entities that want to start using NLP, Edathil’s best advice is to start with simple use cases, such as prioritizing an email queue. Pick “a task that will not raise concerns that this technology could take jobs away from humans,” he says. “Instead, it may show that NLP can help them do their jobs much more efficiently and quickly.”

Governments can also look to companies that frequently use NLP to gain insight and conduct analysis with techniques such as advanced sentiment analysis to elicit insights for a range of “increasingly popular” uses. that would translate well in the government sector, explains Dobrin.

“With NLP, a municipal agency can ask an AI, ‘Which bus stop gets the most complaints? Or “Where are noise complaints a problem?” “And the AI ​​can retrieve that information,” he said. “It’s all part of the general trend to improve the personalization of AI so that it can eliminate repetitive work and research time and help unleash greater human potential. “


Comments are closed.