14-day free trial
Create a full-featured search experience in no time.
Sorry, there is no results for this query
People and machines routinely exchange information via voice or text interface. But will machines ever be able to understand — and respond appropriately to — a person’s emotional state, nuanced tone, or understated intentions? More and more, the answer is yes. The science supporting this breakthrough capability is called natural-language understanding (NLU).
NLU is a subset of a broader field called natural-language processing (NLP), which is already altering how we interact with technology.
NLP involves processing natural spoken or textual language data by breaking it down into smaller elements that can be analyzed. Common NLP tasks include tokenization, part-of-speech tagging, lemmatization, and stemming. NLP focuses largely on converting text into structured data.
NLU is a subset of NLP that teaches computers what a piece of text or spoken speech means. NLU leverages AI to recognize language attributes such as sentiment, semantics, context, and intent. It enables computers to understand subtleties and variations in language. Using NLU, computers can recognize the many ways in which people are saying the same things.
Essentially, NLP processes what was said or entered, while NLU endeavors to understand what was meant. The intent of what people write or say can be distorted through misspelling, fractured sentences, and mispronunciation. NLU pushes through such errors to determine the user’s intent, even if their written or spoken language is flawed.
NLU thereby allows computer software and applications to be more accurate and useful in responding to written and spoken commands. It’s important for developers to consider the difference between NLP and NLU when designing conversational search functionality because it impacts the quality of interpretation of what users say and mean.
Examples of NLP and NLU commonly in use include:
NLU-powered chatbots work in real time, answering queries immediately based on user intent and fundamental conversational elements. Whether they’re directing users to a product, answering a support question, or assigning users to a human customer-support operator, NLU chatbots offer an effective, efficient, and affordable way to support customers in real time.
Voice-based intelligent personal assistants such as Siri, Cortana, and Alexa also benefit from advances in NLU that enable better understanding of user requests and provision of more-personalized responses.
Language translation — with its tantalizing prospect of letting users speak or enter text in one language and receive an instantaneous, accurate translation into another — has long been a holy grail for app developers. But the problems with achieving this goal are as complex and nuanced as any natural language is in and of itself. Although this field is far from perfect, the application of NLU has facilitated great strides in recent years. While translations are still seldom perfect, they’re often accurate enough to convey complex meaning with reasonable accuracy.
A growing number of companies are finding that NLU solutions provide strong benefits for analyzing metadata such as customer feedback and product reviews. In such cases, NLU proves to be more effective and accurate than traditional methods, such as hand coding.
NLP and NLU are commonly used to extract information from text using 5 techniques: named-entity recognition, sentiment analysis, text summarization, aspect mining, and topic modeling. Once information is extracted from unstructured text using these methods, it can be immediately used by machine-learning models to enhance their accuracy and performance.
Traditional search engines work well for keyword-based searches, but for more complex queries, an NLU search engine can make the process considerably more targeted and rewarding. Suppose that a shopper queries “Show me classy black dresses for under $500.” This query defines the product (dress), product type (black), price point (less than $500), and personal tastes and preferences (classy).
NLU-driven searches using tools such as Algolia Understand break down the important pieces of such requests to grasp exactly what the customer wants. By making sense of more-complex and delineated search requests, NLU more quickly moves customers from browsing to buying. For people who know exactly what they want, NLU is a tremendous time saver.
Chatbots are likely the best known and most widely used application of NLU and NLP technology, one that has paid off handsomely for many companies that deploy it. For example, clothing retailer Asos was able to increase orders by 300% using Facebook Messenger Chatbox, and it garnered a 250% ROI increase while reaching almost 4 times more user targets. Similarly, cosmetic giant Sephora increased its makeover appointments by 11% by using Facebook Messenger Chatbox.
NLU-enabled streaming and on-demand services can significantly improve customer satisfaction and loyalty by helping viewers find content, even when they’re unsure of exactly what they’re seeking. If a viewer says: “Show me some funny movies with the main actor from Apollo 13,” despite the vagueness, NLU can deduce and generate a list of movies that match all of these criteria. What might have been a tiresome and frustrating guessing-game search experience is instead a brief, fruitful experience that often leads to a purchase or rental sale.
NLU can greatly help journalists and publishers extract answers to complex questions from deep within content using natural language interaction with content archives.
Tools such as Algolia Answers allow for natural language interactions to quickly find existing content and reduce the amount of time journalists need in order to file stories. Readers can also benefit from NLU-driven content access that helps them draw connections across a range of sources and uncover answers to very specific questions in seconds.
Language-interfaced platforms such as Alexa and Siri already make extensive use of NLU technology to process an enormous range of user requests, from product searches to inquiries like “How do I return this product?” and “How long is my warranty good for?” Customer service and support applications are ideal for having NLU provide accurate answers with minimal hands-on involvement from manufacturers and resellers.
NLU is central to question-answering systems that enhance semantic search in the enterprise and connect employees to business data, charts, information, and resources. It’s also central to customer support applications that answer high-volume, low-complexity questions, reroute requests, direct users to manuals or products, and lower all-around customer service costs.
Online games have become fiendishly complex, so much so that players are continually referencing rule books and playing guides to find answers to specific questions. In addition, games are typically played at a breakneck pace, and players want immediate answers to such competition-focused questions as “How do I beat level 3 in this game?” and “Where can I find the magic potion in this game?”
In the midst of the action, rather than thumbing through a thick paper manual, players can turn to NLU-driven chatbots to get information they need, without missing a monster attack or ray-gun burst.
NLU and NLP already play a central role in the development and rollout of Algolia’s next-generation search tools. For example:
For more about the Algolia approach to NLU and NLP, see:
VP Corporate Marketing