Natural language processing shapes intelligent automation
Hear from CIOs, CTOs, and other executives and senior executives on data and AI strategies at the Future of Work Summit on January 12, 2022. Learn more
This article was written by Pascal Bornet and Rachael Churchill. The content of this article is inspired by Pascal Intelligent Automation’s book.
Natural language processing is the name generally given to the ability of computers to perform linguistic tasks – although in practice it includes more than language processing (understanding text and speech), but also includes generation. language (creation of text and speech).
Natural Language Processing (NLP) is a component of intelligent automation, a set of related technologies that allow computers to automate the work of knowledge and increase the productivity of people who work with their minds. The other components of intelligent automation are computer vision (interpretation of images and videos, as in self-driving cars or medical diagnostics), thinking and learning (for example, evolving strategies and data-driven decision making) and execution (interacting with the physical world or with existing software, and chaining other capabilities together in automated pipelines).
Below are some natural language processing applications that are being deployed today and how they can help your business.
Natural language processing technologies
Chatbots and cognitive agents
Chatbots and cognitive agents are used to answer questions, search for information, or schedule appointments, without the need for a human agent in the loop.
Simple chatbots can be programmed with a set of basic rules (âif the user says X, you say Yâ); more advanced chatbots or “cognitive agents” use deep learning to learn conversations and improve, and can be mistaken for humans.
Many chatbots are text-based and interact with users through instant messaging or texting, but some use voice and even video. Notable examples are ANZ Bank’s chatbot “Jamie”, which guides customers through the bank’s services, and Google Duplex, which can make phone calls to book barber appointments or restaurant tables. , even talking to unsuspecting receptionists who don’t know it’s a bot.
Unstructured information management
Unstructured Information Management (UIM) platforms are used to process large amounts of unstructured data and extract meaning from it without the need for many manual keyword research queries, which are time consuming and prone to errors. They are an essential part of natural language processing and process unstructured documents such as journal articles, patents, contracts and medical records, and create a structured and searchable knowledge base. They can also categorize data and find clusters and trends within it.
Sentiment Analysis uses natural language processing to extract feelings, such as approval or disapproval of a brand, from unstructured text such as tweets.
Speech analysis is a component of natural language processing that combines UIM with sentiment analysis. It is used by call centers to turn text chats and transcripts of phone conversations into structured data and analyze them using sentiment analysis. All of this can be done in real time, giving call center agents live feedback and suggestions during a call, and alerting a manager if the customer is unhappy.
Machine Translation is an extremely powerful NLP application. Currently, it’s usually not powerful enough to produce fully grammatical and idiomatic translations, but it can give you the gist of a webpage or email in a language you don’t speak. Every day, 500 million people use Google Translate to help them understand text in over 100 languages.
Classification of information
The classification or categorization of information is used, among other things, for spam filtering. It works by using the same type of machine learning model that is used to classify x-rays and other medical images into healthy and sick, or used by self-driving cars to decide if something is a stop sign. Rather than being programmed with explicit rules, the computer receives a large amount of training data in the form of known spam e-mails and known legitimate e-mails, and it extracts its own based rules. on evidence to classify new emails.
Components of natural language processing that can help your business
Chatbots and cognitive agents
Chatbots and cognitive agents can improve your bottom line by replacing call center staff for simple customer queries and increasing human call center agents for more complex queries, allowing you to expand your customer base and your market share and improve customer satisfaction without the need to employ and train more agents.
Unstructured information management
Unstructured information management platforms allow you to automate a lot of research: for example, lawyers can use them to execute intelligent queries on existing patents or case law, and medical researchers can use them in drug discovery or search for relevant genetic interactions in the literature. . Rather than spending time going through tons of documents, a human researcher can quickly examine the suggestions and information provided by the UIM platform, making them overall more productive and freeing up their time and mental energy for the most important aspects. creative and high-level work.
You can use sentiment analysis to perform real-time automatic monitoring of consumer reactions to your brand, especially in response to a new product launch or ad campaign, which will help you tailor future products and services accordingly. It can also automatically alert you to any eruption of criticism or negativity about your brand on social media, without the need for human staff to actively monitor channels 24/7, so you can react in time to avoid a public relations crisis.
Speech analysis can increase the skills of your call center staff, improving customer satisfaction without the expense and opportunity cost of additional training. You can also use voice analysis to detect conversation patterns that lead to successful sales, or cross-sell or up-sell opportunities based on customer behavior. This can help elevate mediocre telesales agents to star salespeople, allowing them to share and deploy the talents of their more qualified colleagues, which has a significant impact on your bottom line without any expense of recruiting or staffing. training.
Machine translation can allow you to read relevant articles that your competitors might not have seen if they were published in a minority language, share knowledge internationally in your company, and communicate with colleagues. or international vendors without the overhead of a human translator (although when communicating with clients it may still be advisable to employ one in order to make a good impression).
Classification of information
The classification of information has a variety of useful applications. In addition to saving you time and time by filtering spam, this technology can be used to automate domain-specific classification tasks. For example, he could categorize and label products in a catalog, which makes it easier for customers to browse and purchase them; or it could filter social media posts for hate speech, mitigating legal and reputational risks without the need for a large team of human moderators; or it can categorize support tickets and automatically forward them to the right person, saving manual effort and improving overall response times.
Automatic Natural Language Processing: A Case Study
This is an example from my own experience of the benefits of using cognitive agents to improve customer satisfaction and reduce staff turnover.
One hotel chain employed a team of 240 customer service agents to handle more than 20,000 guest interactions per day, including phone calls, emails and social media. Team morale was low due to the high pressure and workload, and staff turnover was 40%. This had a ripple effect on the quality of customer service, which was rated less than five out of 10.
The company deployed an omnichannel cognitive agent to engage with customers via email, social media, and voice calls. Cognitive Agent was designed to look and behave the same as human agents, and used machine learning to improve and learn from previous conversations. It could also recognize users based on biometric information, such as voice or facial recognition, and it could autonomously process changes in systems.
After three months, the customer satisfaction rate had dropped from five in 10 to nine in 10, staff turnover had dropped by over 70%, and members of the human team were under less pressure and could focus on values. more complex and higher. -Add interactions requiring greater relational skills.
Language is the way humans communicate naturally, so computer interfaces that can understand natural language are more powerful and easier to use than those that require clicking buttons, typing commands, or learning to program, and it is important to understand the components of natural language processing. Natural language interfaces are the next step in the evolution of human-machine interaction, from simple tools to machines capable of event-driven and automated processes, potentially even leading to a kind of symbiosis between humans and machines.
This article was written by Pascal Bornet and Rachael Churchill. The content of this article is inspired by Pascal’s book on Amazon, Intelligent Automation.
Welcome to the VentureBeat community!
DataDecisionMakers is the place where experts, including data technicians, can share data-related ideas and innovations.
If you’re interested in learning more about cutting-edge ideas and up-to-date information, best practices, and the future of data and data technology, join us at DataDecisionMakers.
You might even consider contributing your own article!
Read more about DataDecisionMakers
Comments are closed.