Did you know, that several years ago, NLP was heavily an academic discipline?
Today, natural language processing or NLP has become critical to business applications. This can partly be attributed to the growth of big data, consisting heavily of unstructured text data. The need for intelligent techniques to make sense of all this text-heavy data has helped put NLP on the map.
So what’s this NLP?
In a strict academic definition, NLP is about helping computers understand human language. It’s a branch of study within artificial intelligence.
But the industry definition of NLP is much broader. It refers to any method that does the processing, analysis, and retrieval of textual data—even if it’s not natural language.
So how can you leverage NLP in your business? That’s what this article is about. While there are many applications of NLP (as seen in the figure below), we’ll explore seven that are well-suited for business applications.
Ten application areas of NLP
7 NLP Applications in Business
1: Text Classification
Text classification or document categorization is the automatic labeling of documents and text units into known categories. For example, automatically labeling your company’s presentation documents into one or two of ten categories is an example of text classification in action.
In business applications, categorizing documents and content is useful for discovering, efficiently managing documents, and extracting insights.
LinkedIn, for example, uses text classification techniques to flag profiles that contain inappropriate content, which can range from profanity to advertisements for illegal services. Facebook, on the other hand, uses text classification methods to detect hate speech on its platform.
Text classification is one of the most common applications of NLP in business. But for text classification to work for your company, it’s critical to ensure that you’re collecting and storing the right data.
Further reading: AI Document Classification: 5 Real-World Examples
2: Conversational Agents
Conversational agents communicate with users in natural language with text, speech, or both. Conversational agents fall into two categories.
- Virtual assistants
Virtual assistants also referred to as digital assistants, or AI assistants, are designed to complete specific tasks and are set up to have reasonably short conversations with users.
Siri, Alexa, and Google Assistant are examples of AI assistants. These agents understand human commands and can complete tasks like setting an appointment in your calendar, calling a friend, finding restaurants, giving driving directions, and switching on your TV. Companies also use such agents on their websites to answer customer questions or resolve simple customer issues.
Chatbots, on the other hand, are designed to have extended conversations with people. It mimics chats in human-to-human conversations rather than focusing on a particular task.
Quick Tip: In the commercial world, AI assistants are often referred to as chatbots.
When it comes to conversational agents, what’s most relevant to businesses is AI assistants that can work on tasks without needing human intervention.
In a banking example, simple customer support requests such as resetting passwords, checking account balance, and finding your account routing number can all be handled by AI assistants. With this, call-center volumes and operating costs can be significantly reduced, as observed by the Australian Tax Office (ATO), a revenue collection agency.
The ATO faces high call center volume during the start of the Australian financial year. To provide consistent service to customers even during peak periods, in 2016, the ATO deployed Alex, an AI virtual assistant. Within three months of deploying Alex, she has held over 270,000 conversations, with a first contact resolution rate (FCR) of 75 percent. Meaning, the AI virtual assistant could resolve customer issues on the first try 75 percent of the time. This number further improved in the following years after deployment.
The beauty of virtual assistants is that they can work 24-hours a day, and your customers will not be turned down because employees called in sick.
3: Machine Translation
Machine translation is the automatic software translation of text from one language to another. For example, English sentences can be automatically translated into German sentences with reasonable accuracy.
Research in machine translation dates back to the 1950s. While there have been major advancements in the field, translation systems today still have a hard time translating long sentences, ambiguous words, and idioms. The example below shows you what I mean by a translation system not understanding things like idioms.
French idiom to English translation using Google Translate. The input is an idiom: “He’s getting on my nerves.” Notice that the output has nothing to do with getting on someone’s nerves.
But the good news is that machine translation is handy for simple translation tasks in business applications. It can be used to:
- Render Web content in a different language depending on the visitor’s language settings.
- Translate customer support requests that are in a different language from the support agent’s native language.
- Standardize datasets that are in a different language before they’re used for downstream analysis.
4: Sentiment Analysis
Sentiment analysis is the automatic interpretation and summarization of emotions within text data. For example, in predicting emotions in Tweets, emotions can be “positive,” “negative,” or “neutral.” It can also be more granular where you detect elements such as “anger,” “joy,” “sadness,” and “disgust.”
Sentiment analysis enables businesses to analyze customer sentiment towards brands, products, and services using online conversations or direct feedback. With this, companies can better understand customers’ likes and dislikes and find opportunities for innovation.
TasNetworks, a Tasmanian supplier of power, used sentiment analysis to understand problems in their service. They applied sentiment analysis on survey responses collected monthly from customers. These responses document the customer’s most recent experience with the supplier. With sentiment analysis, they discovered general customer sentiments and discussion themes within each sentiment category. With this, they were able to pinpoint issues in their service.
5: Text Summarization
Text summarization involves automatically reading some textual content and generating a summary. The goal of text summarization is to inform users without them reading every single detail, thus improving user productivity.
The summary can be a paragraph of text much shorter than the original content, a single line summary, or a set of summary phrases. For example, automatically generating a headline for a news article is an example of text summarization in action. Although news summarization has been heavily researched in the academic world, text summarization is helpful beyond that.
In my Ph.D. thesis, for example, I researched an approach that sifts through thousands of consumer reviews for a given product to generate a set of phrases that summarized what people were saying. With such a summary, you’ll get a gist of what’s being said without reading through every comment.
Example of text summarization of user reviews for Acura 2007.
This idea is beneficial for summarizing free-text survey comments, Tweets, Facebook comments, and other user-generated content where the gist of what’s being said at scale is important. The closest to this idea that I know is Amazon’s “read reviews that mention…” as shown below.
Example of browsable topics within reviews on Amazon.com. Source: Amazon
While this is not text summarization in a strict sense, the goal is to help you browse commonly discussed topics to help you make an informed decision. Even if you didn’t read every single review, reading about the topics of interest can help you decide if a product is worth your precious dollars.
Similarly, you can use text summarization to summarize audio-visual meetings such as Zoom and WebEx meetings. With the growth of online meetings due to the COVID-19 pandemic, this can become extremely powerful. The audio from the meetings can be converted to text, and this text can be summarized to highlight the main discussion points. And there are many such application opportunities.
6: Information Retrieval (IR)
Information retrieval or IR is about finding documents that satisfy a users’ need from a large pool of documents. Google Search is a classic example of an IR system. It gets you the information that you need from the entire Web. Your Gmail email search is another example.
While in academia, IR is considered a separate field of study, in the business world, IR is considered a subarea of NLP. That’s because IR deals with the retrieval of text data. Plus, understanding a user’s keyword query requires NLP.
Although most business websites have search functionality, these search engines are often not optimized. Businesses tend to rely on Web search engines. But the reality is that Web search engines only get visitors to your website. From there on, a good search engine on your website coupled with a content recommendation engine can keep visitors on your site longer and more engaged.
There is a huge opportunity for improving search systems with machine learning and NLP techniques customized for your audience and content.
7: Information Extraction
Information extraction is the process of pulling out specific content from text. Information extraction is extremely powerful when you want precise content buried within large blocks of text and images.
For example, by extracting appointment information from your emails, you automate the process of adding appointments to your calendar. Google does this by reading emails about a flight confirmation or a concert and offers to add those events to your calendar. Another example is having a credit card company extract information from your travel itinerary. Traditionally, you’d have to call them to inform them about your upcoming travel. Now, with the extracted information, they’ll know where you are off to and automatically authorize transactions at that location.
Which NLP Applications Would You Consider?
Now that you’ve seen seven different NLP applications, do any seem relevant for your company? Consider some of these questions:
- Do you need to better manage and organize content? Then perhaps you can benefit from text classification, information retrieval, or information extraction.
- Do you need to have hundreds of separate conversations with customers to help them solve specific tasks? Consider virtual AI assistants.
- Are you trying to make sense of customer feedback from surveys, Twitter, and support tickets? You could benefit from sentiment analysis.
- Do you have piles of documents waiting to be read? Then perhaps text summarization can be of help.
While some of these ideas would have to be custom developed, you can use existing tools and off-the-shelf solutions for some. But which ones should be developed from scratch and which ones can benefit from off-the-shelf tools is a separate topic of discussion. See the figure below to get an idea of which NLP applications can be easily implemented by a team of data scientists
NLP application areas summarized by the difficulty of implementation and how commonly they’re used in business applications.
The post 7 Natural Language Processing Applications for Business Problems appeared first on Opinosis Analytics.