Natural Language Processing: Examples, Techniques, and More

Previously Google Translate used a Phrase-Based Machine Translation, which scrutinized a passage for similar phrases between dissimilar languages. Presently, Google Translate uses the Google Neural Machine Translation instead, which uses machine learning and natural language processing algorithms to search for language patterns. Your software can take a statistical sample of recorded calls and perform speech recognition after transcribing the calls to text using machine translation. The NLU-based text analysis can link specific speech patterns to negative emotions and high effort levels. Using predictive modeling algorithms, you can identify these speech patterns automatically in forthcoming calls and recommend a response from your customer service representatives as they are on the call to the customer.

• Natural language processing (NLP) is a subfield of computer science and artificial intelligence (AI) that uses machine learning to enable computers to understand and communicate with human language.
• The misspelled word is then added to a Machine Learning algorithm that conducts calculations and adds, removes, or replaces letters from the word, before matching it to a word that fits the overall sentence meaning.
• It can be hard to understand the consensus and overall reaction to your posts without spending hours analyzing the comment section one by one.

And in business, NLP applications will provide more realistic, more helpful customer service as well as more efficiency in day-to-day computer interactions. The growth of virtual assistants is based largely on system ease of use and as well as accuracy of results — all of which depends on NLP. NLP powers intelligent chatbots and virtual assistants—like Siri, Alexa, and Google Assistant—which can understand and respond to user commands in natural language. They rely on a combination of advanced NLP and natural language understanding (NLU) techniques to process the input, determine the user intent, and generate or retrieve appropriate answers. The recent emergence of GPT and large language models (LLMs) has ignited a new golden age in artificial intelligence (AI) and machine learning (ML) research, bringing Natural Language Processing (NLP) back to the forefront of the field. ChatGPT is the fastest growing application in history, amassing 100 million active users in less than 3 months.

The semantic step in NLP starts to look at the meaning of a sentence, instead of individual words. The easiest way to explain it is, syntactic analysis is the grammatical structure of the language, whereas the semantic is the actual meaning of the sentence.Semantic analysis is a structure for assigning meanings of words. That means that the syntactic analyzer will always have assigned meanings to the words. Natural language processing brings together linguistics and algorithmic models to analyze written and spoken human language. Based on the content, speaker sentiment and possible intentions, NLP generates an appropriate response. In machine translation done by deep learning algorithms, language is translated by starting with a sentence and generating vector representations that represent it.

This kind of model, which takes sentences or documents as inputs and returns a label for that input, is called a document classification model. Document classifiers can also be used to classify documents by the topics they mention (for example, as sports, finance, politics, etc.). Three open source tools commonly used for natural language processing include Natural Language Toolkit (NLTK), Gensim and NLP Architect by Intel.

Interested in Our Online MBA?

NLP can generate human-like text for applications—like writing articles, creating social media posts, or generating product descriptions. A number of content creation co-pilots have appeared since the release of GPT, such as Jasper.ai, that automate much of the copywriting process. Topic modeling is an unsupervised learning technique that uncovers the hidden thematic structure in large collections of documents. It organizes, summarizes, and visualizes textual data, making it easier to discover patterns and trends. Although topic modeling isn’t directly applicable to our example sentence, it is an essential technique for analyzing larger text corpora. Part-of-speech (POS) tagging identifies the grammatical category of each word in a text, such as noun, verb, adjective, or adverb.

NLP business applications come in different forms and are so common these days. For example, spell checkers, online search, translators, voice assistants, spam filters, and autocorrect are all NLP applications. A chatbot system uses AI technology to engage with a user in natural language—the way a person would communicate if speaking or writing—via messaging applications, websites or mobile apps. The goal of a chatbot is to provide users with the information they need, when they need it, while reducing the need for live, human intervention. Syntax and semantic analysis are two main techniques used in natural language processing. NLP is special in that it has the capability to make sense of these reams of unstructured information.

Processing all those data can take lifetimes if you’re using an insufficiently powered PC. However, with a distributed deep learning model and multiple GPUs working in coordination, you can trim down that training time to just a few hours. Of course, you’ll also need to factor in time to develop the product from scratch—unless you’re using NLP tools that already exist. The Natural Language Toolkit is a platform for building Python projects popular for its massive corpora, an abundance of libraries, and detailed documentation. Whether you’re a researcher, a linguist, a student, or an ML engineer, NLTK is likely the first tool you will encounter to play and work with text analysis.

Compared to chatbots, smart assistants in their current form are more task- and command-oriented. Too many results of little relevance is almost as unhelpful as no results at all. As a Gartner survey pointed out, workers who are unaware of important information can make the wrong decisions. However, as you are most which of the following is an example of natural language processing? likely to be dealing with humans your technology needs to be speaking the same language as them. Predictive text has become so ingrained in our day-to-day lives that we don’t often think about what is going on behind the scenes. As the name suggests, predictive text works by predicting what you are about to write.

If you want to learn more about this technology, there are various online courses you can refer to. For example, a user can ask Siri about the weather, command Alexa to play a song, or instruct Google Assistant to set an alarm, all with their voice. These systems use NLP to understand the command, extract the necessary information, and execute the action, making technology more interactive and user-friendly. Furthermore, smart assistants can also engage in two-way communication, providing responses to user inquiries in a conversational manner. This capability to understand, respond to, and learn from human language is made possible by the integration of NLP, solidifying its role in enhancing human-computer interaction.

Big data and the integration of big data with machine learning allow developers to create and train a chatbot. Deep semantic understanding remains a challenge in NLP, as it requires not just the recognition of words and their relationships, but also the comprehension of underlying concepts, implicit information, and real-world knowledge. LLMs have demonstrated remarkable progress in this area, but there is still room for improvement in tasks that require complex reasoning, common sense, or domain-specific expertise. GPT, short for Generative Pre-Trained Transformer, builds upon this novel architecture to create a powerful generative model, which predicts the most probable subsequent word in a given context or question.

Why Natural Language Processing Is Difficult

The solution here is to develop an NLP system that can recognize its own limitations, and use questions or prompts to clear up the ambiguity. In this example, the word “king”, appears once in the first sentence, twice in the second, once in the third, and none in the fourth. So it needs to look at the sentence before it and understand that carbon offsetting is a “green (environmentally friendly)” idea. For example, the stem for the word “touched” is “touch.” “Touch” is also the stem of “touching,” and so on.

If a marketing team leveraged findings from their sentiment analysis to create more user-centered campaigns, they could filter positive customer opinions to know which advantages are worth focussing on in any upcoming ad campaigns. An NLP customer service-oriented example would be using semantic search to improve customer experience. Semantic search is a search method that understands the context of a search query and suggests appropriate responses. While NLP is concerned with enabling computers to understand the content of messages or the meanings behind spoken or written language, speech recognition focuses on converting spoken language into text. Think of tokenization as the meticulous librarian of NLP, organizing a chaotic array of words and sentences into neat, manageable sections. This technique breaks down text into units such as sentences, phrases, or individual words, making it easier for machines to process.

Equipped with natural language processing, a sentiment classifier can understand the nuance of each opinion and automatically tag the first review as Negative and the second one as Positive. Imagine there’s a spike in negative comments about your brand on social media; sentiment analysis tools would be able to detect this immediately so you can take action before a bigger problem arises. There is now an entire ecosystem of providers delivering pretrained deep learning models that are trained on different combinations of languages, datasets, and pretraining tasks. These pretrained models can be downloaded and fine-tuned for a wide variety of different target tasks.

Using this data, they can perform upgrades to certain steps within the supply chain process or make logistical modifications to optimize efficiencies. No language is perfect, and most languages have words that have multiple meanings. For example, a user who asks, “how are you” has a totally different goal than a user who asks something like “how do I add a new credit card?

This task is crucial for understanding the opinion or emotion conveyed in user reviews, social media posts, or customer feedback. Natural language processing is one of the most powerful tools for business analytics. Professionals can use this ground-breaking technology to analyze documents, understand how Chat GPT consumers respond to products, and much more. By knowing the structure of sentences, we can start trying to understand the meaning of sentences. We start off with the meaning of words being vectors but we can also do this with whole phrases and sentences, where the meaning is also represented as vectors.

Leveraged by businesses across the globe, chatbots streamline customer service, facilitating real-time, 24/7 communication with clients. They are capable of understanding customer queries, providing immediate responses, and even resolving common issues, thereby boosting the efficiency of customer service operations. Moreover, chatbots can be tailored to reflect a brand’s tone and style, creating personalized customer experiences. While they continue to evolve, the integration of NLP in chatbots is a testament to the significant advancements in human-computer interaction.

NLP combines rule-based modeling of human language called computational linguistics, with other models such as statistical models, Machine Learning, and deep learning. When integrated, these technological models allow computers to process human language through either text or spoken words. As a result, they can ‘understand’ the full meaning – including the speaker’s or writer’s intention and feelings. In practical applications, NLP uses sentiment analysis to identify sentiment in social data, customer reviews, and surveys, among other sources. For instance, businesses can use sentiment analysis to understand customer sentiment towards products, branding, or services based on online reviews or social media conversations.

Just take a look at the following newspaper headline “The Pope’s baby steps on gays.” This sentence clearly has two very different interpretations, which is a pretty good example of the challenges in natural language processing. NLP uses various analyses (lexical, syntactic, semantic, and pragmatic) to make it possible for computers to read, hear, and analyze language-based data. As a result, technologies such as chatbots are able to mimic human speech, and search engines are able to deliver more accurate results to users’ queries.

Except for entire document as the feature, rest all can be used as features of text classification learning model. A right text classification model contains – cleaning of text to remove noise, annotation to create more features, converting text-based features into predictors, learning a model using gradient descent and finally tuning a model. Since, you are given only the data of tweets and no other information, which means there is no target variable present. One cannot train a supervised learning model, both svm and naive bayes are supervised learning techniques. If a user opens an online business chat to troubleshoot or ask a question, a computer responds in a manner that mimics a human. Though natural language processing tasks are closely intertwined, they can be subdivided into categories for convenience.

Smart assistants such as Google’s Alexa use voice recognition to understand everyday phrases and inquiries. NPL cross-checks text to a list of words in the dictionary (used as a training set) and then identifies any spelling errors. The misspelled word is then added to a Machine Learning algorithm that conducts calculations and adds, removes, or replaces letters from the word, before matching it to a word that fits the overall sentence meaning. Then, the user has the option to correct the word automatically, or manually through spell check. Sentiment analysis (also known as opinion mining) is an NLP strategy that can determine whether the meaning behind data is positive, negative, or neutral. For instance, if an unhappy client sends an email which mentions the terms “error” and “not worth the price”, then their opinion would be automatically tagged as one with negative sentiment.

Human language data does not resemble the orderly rows and columns you might find in a time series, for example. For those who don’t know me, I’m the Chief Scientist at Lexalytics, an InMoment company. We sell text analytics and NLP solutions, but at our core we’re a machine learning company. We maintain hundreds of supervised and unsupervised machine learning models that augment and improve our systems.

From predictive text to data analysis, NLP’s applications in our everyday lives are far-ranging. However, nowadays, AI-powered chatbots are developed to manage more complicated consumer requests making conversational experiences somewhat intuitive. For example, chatbots within healthcare systems can collect personal patient data, help patients evaluate their symptoms, and determine the appropriate next steps to take. Additionally, these healthcare chatbots can arrange prompt medical appointments with the most suitable medical practitioners, and even suggest worthwhile treatments to partake. Financial markets are sensitive domains heavily influenced by human sentiment and emotion.

In conclusion, Natural Language Processing (NLP) encompasses essential techniques such as tokenization, part-of-speech tagging, named entity recognition, sentiment analysis, and language generation. These fundamental elements enable machines to understand, interpret, and generate human language, opening up a world of possibilities for applications ranging from language translation to chatbots and sentiment analysis. By harnessing the power of NLP, we can bridge the gap between humans and machines, revolutionizing the way we communicate and interact with technology. Chatbots epitomize one of the most prevalent applications of natural language processing. These AI-driven entities employ NLP to understand and respond to human language in a conversational manner, primarily via text-based interfaces, but voice-activated chatbots are also gaining traction.

Make sure your NLU solution is able to parse, process and develop insights at scale and at speed. Depending on your business, you may need to process data in a number of languages. Having support for many languages other than English https://chat.openai.com/ will help you be more effective at meeting customer expectations. In our research, we’ve found that more than 60% of consumers think that businesses need to care more about them, and would buy more if they felt the company cared.

Part of this care is not only being able to adequately meet expectations for customer experience, but to provide a personalized experience. Accenture reports that 91% of consumers say they are more likely to shop with companies that provide offers and recommendations that are relevant to them specifically. Natural Language Understanding (NLU) is a field of computer science which analyzes what human language means, rather than simply what individual words say.

That’s great news for businesses since NLP can have a dramatic effect on how you run your day-to-day operations. It can speed up your processes, reduce monotonous tasks for your employees, and even improve relationships with your customers. Using emotive NLP/ ML analysis, financial institutions can analyze larger amounts of meaningful market research and data, thereby ultimately leveraging real-time market insight to make informed investment decisions. Natural language processing and its subsets have numerous practical applications within today’s world, like healthcare diagnoses or online customer service. Sometimes it’s hard even for another human being to parse out what someone means when they say something ambiguous.

For example, “the thief” is a noun phrase, “robbed the apartment” is a verb phrase and when put together the two phrases form a sentence, which is marked one level higher. Part of this difficulty is attributed to the complicated nature of languages—possible slang, lexical items borrowed from other languages, emerging dialects, archaic wording, or even metaphors typical to a certain culture. If perceiving changes in the tone and context is tough enough even for humans, imagine what it takes an AI model to spot a sarcastic remark. Albeit limited in number, semantic approaches are equally significant to natural language processing. In order for NLP to function, it must perform a variety of tasks to understand the text in questions, or text classification, and how to process it. These tasks are similar to the way the human brain understands and interprets language.

natural language processing (NLP)

Sentiment analysis, also known as opinion mining, is an influential application of natural language processing. It involves determining the emotional tone behind words to gain an understanding of the attitudes, opinions, and emotions expressed within an online mention. By leveraging machine learning, text analysis, and computational linguistics, NLP enables the extraction of subjective information from source materials. Language translation is a striking demonstration of the power of natural language processing.

Integrating insights from psychology, neuroscience, and cognitive science will make NLP tools more intuitive, adapting responses based on the user’s emotional state or cognitive load. This interdisciplinary approach will enhance the responsiveness and sensitivity of AI systems. NLP tools process data in real time, 24/7, and apply the same criteria to all your data, so you can ensure the results you receive are accurate – and not riddled with inconsistencies. Automated Essay Scoring (AES) is an innovative application of NLP that has revolutionized educational assessment. AES systems utilize NLP to evaluate, and grade written essays based on various parameters like grammar, vocabulary, coherence, and argument structure. By analyzing these components, AES can provide instant, objective scoring, reducing the workload of educators and providing students with immediate feedback.

Whether analyzing a novel or sifting through tweets, tokenization is the first step in structuring the unstructured text. Natural language processing is one of the most promising fields within Artificial Intelligence, and it’s already present in many applications we use on a daily basis, from chatbots to search engines. Once you get the hang of these tools, you can build a customized machine learning model, which you can train with your own criteria to get more accurate results. This example of natural language processing finds relevant topics in a text by grouping texts with similar words and expressions.

To summarize, natural language processing in combination with deep learning, is all about vectors that represent words, phrases, etc. and to some degree their meanings. Natural Language Processing (NLP) is a field of data science and artificial intelligence that studies how computers and languages interact. The goal of NLP is to program a computer to understand human speech as it is spoken. Ties with cognitive linguistics are part of the historical heritage of NLP, but they have been less frequently addressed since the statistical turn during the 1990s. Future NLP aims to achieve deeper comprehension of human language nuances, including context, irony, and emotional subtleties.

The NLU field is dedicated to developing strategies and techniques for understanding context in individual records and at scale. NLU systems empower analysts to distill large volumes of unstructured text into coherent groups without reading them one by one. This allows us to resolve tasks such as content analysis, topic modeling, machine translation, and question answering at volumes that would be impossible to achieve using human effort alone.

Challenges and limitations of NLP

As a result, many businesses now look to NLP and text analytics to help them turn their unstructured data into insights. Core NLP features, such as named entity extraction, give users the power to identify key elements like names, dates, currency values, and even phone numbers in text. First, the capability of interacting with an AI using human language—the way we would naturally speak or write—isn’t new. Smart assistants and chatbots have been around for years (more on this below). And while applications like ChatGPT are built for interaction and text generation, their very nature as an LLM-based app imposes some serious limitations in their ability to ensure accurate, sourced information. Where a search engine returns results that are sourced and verifiable, ChatGPT does not cite sources and may even return information that is made up—i.e., hallucinations.

• By analyzing customer opinion and their emotions towards their brands, retail companies can initiate informed decisions right across their business operations.
• Covering techniques as diverse as tokenization (dividing the text into smaller sections) to part-of-speech-tagging (we’ll cover later on), data pre-processing is a crucial step to kick-off algorithm development.
• Selection of the number of topics is directly proportional to the size of the data, while number of topic terms is not directly proportional to the size of the data.
• Autocorrect can even change words based on typos so that the overall sentence’s meaning makes sense.
• NLP/ ML helps banks and other financial security institutions to identify money laundering activities or other fraudulent circumstances.

From early machine translation projects like IBM’s Automatic Language Translator to modern, sophisticated algorithms used in AI chatbots, NLP has grown exponentially alongside advancements in computing power and machine learning. Although sometimes tedious, this allows corporations to filter customer information and quickly get you to the right representative. These machines also provide data for future conversations and improvements, so don’t be surprised if answering machines suddenly begin to answer all of your questions with a more human-like voice.

In our example, POS tagging might label “walking” as a verb and “Apple” as a proper noun. Most recently, transformers and the GPT models by Open AI have emerged as the key breakthroughs in NLP, raising the bar in language understanding and generation for the field. In a 2017 paper titled “Attention is all you need,” researchers at Google introduced transformers, the foundational neural network architecture that powers GPT. Transformers revolutionized NLP by addressing the limitations of earlier models such as recurrent neural networks (RNNs) and long short-term memory (LSTM).

For example, swivlStudio allows you to visualize all of the utterances (what people say or ask) in one inbox. These are either tagged as Handled (your model was successful at generating a next step) or Unhandled (the model scored below a certain confidence threshold) so that you have a full visual as to how your model is performing. Machines are still pretty primitive – you provide an input and they provide an output. Although they might say one set of words, their diction does not tell the whole story. However, trying to track down these countless threads and pull them together to form some kind of meaningful insights can be a challenge. IBM’s Global Adoption Index cited that almost half of businesses surveyed globally are using some kind of application powered by NLP.

TextBlob is a more intuitive and easy to use version of NLTK, which makes it more practical in real-life applications. Its strong suit is a language translation feature powered by Google Translate. Unfortunately, it’s also too slow for production and doesn’t have some handy features like word vectors. You can be sure about one common feature — all of these tools have active discussion boards where most of your problems will be addressed and answered.

This technique is particularly popular in social media monitoring, marketing analysis, and customer service, as it provides insights into public sentiment and customer satisfaction. These models showcase the breadth and depth of techniques in the field of NLP, from the rigid but reliable rule-based systems to the highly sophisticated and contextually aware transformers. As we continue to develop these technologies, the potential for even more nuanced and effective communication between humans and machines is vast and exciting. Analyzing customer feedback is essential to know what clients think about your product.

The saviors for students and professionals alike – autocomplete and autocorrect – are prime NLP application examples. Autocomplete (or sentence completion) integrates NLP with specific Machine learning algorithms to predict what words or sentences will come next, in an effort to complete the meaning of the text. Oftentimes, when businesses need help understanding their customer needs, they turn to sentiment analysis. There are many eCommerce websites and online retailers that leverage NLP-powered semantic search engines. They aim to understand the shopper’s intent when searching for long-tail keywords (e.g. women’s straight leg denim size 4) and improve product visibility.

NLP can be applied to many languages, although the quality and depth of the tools and models available can vary widely between languages. Advances in machine learning and data availability are helping to improve NLP tools across a broader range of languages. These NLP techniques illustrate just how machines can be taught to understand not only the structure of language but also its meaning and emotional tone. By leveraging these methods, businesses and developers can create richer, more interactive experiences that feel both personal and efficient. As we continue to refine these techniques, the potential for creating systems that truly understand and interact with us on a human level becomes more and more tangible. It detects the mood or subjective opinions expressed in text, classifying them as positive, negative, or neutral.

For many businesses, the chatbot is a primary communication channel on the company website or app. It’s a way to provide always-on customer support, especially for frequently asked questions. Now, thanks to AI and NLP, algorithms can be trained on text in different languages, making it possible to produce the equivalent meaning in another language.

NLP can help you leverage qualitative data from online surveys, product reviews, or social media posts, and get insights to improve your business. Read on to learn what natural language processing is, how NLP can make businesses more effective, and discover popular natural language processing techniques and examples. While it’s not exactly 100% accurate, it is still a great tool to convert text from one language to another. Google Translate and other translation tools as well as use Sequence to sequence modeling that is a technique in Natural Language Processing. It allows the algorithm to convert a sequence of words from one language to another which is translation.

People go to social media to communicate, be it to read and listen or to speak and be heard. As a company or brand you can learn a lot about how your customer feels by what they comment, post about or listen to. However, it has come a long way, and without it many things, such as large-scale efficient analysis, wouldn’t be possible.

Examples include first and last names, age, geographic locations, addresses, product type, email addresses, company name, etc. Text classification has broad applicability such as social media analysis, sentiment analysis, spam filtering, and spam detection. In addition, there’s a significant difference between the rule-based chatbots and the more sophisticated Conversational AI. There are different natural language processing tasks that have direct real-world applications while some are used as subtasks to help solve larger problems.

Sentiment analysis determines the sentiment or emotion expressed in a text, such as positive, negative, or neutral. While our example sentence doesn’t express a clear sentiment, this technique is widely used for brand monitoring, product reviews, and social media analysis. Social media monitoring uses NLP to filter the overwhelming number of comments and queries that companies might receive under a given post, or even across all social channels. These monitoring tools leverage the previously discussed sentiment analysis and spot emotions like irritation, frustration, happiness, or satisfaction.

And despite volatility of the technology sector, investors have deployed $4.5 billion into 262 generative AI startups. Natural language processing is one of the most complex fields within artificial intelligence. But, trying your hand at NLP tasks like sentiment analysis or keyword extraction needn’t be so difficult.

While natural language processing (NLP), natural language understanding (NLU), and natural language generation (NLG) are all related topics, they are distinct ones. Given how they intersect, they are commonly confused within conversation, but in this post, we’ll define each term individually and summarize their differences to clarify any ambiguities. To be sufficiently trained, an AI must typically review millions of data points.

For years, trying to translate a sentence from one language to another would consistently return confusing and/or offensively incorrect results. This was so prevalent that many questioned if it would ever be possible to accurately translate text. Plus, tools like MonkeyLearn’s interactive Studio dashboard (see below) then allow you to see your analysis in one place – click the link above to play with our live public demo. This function predicts what you might be searching for, so you can simply click on it and save yourself the hassle of typing it out. Watch IBM Data and AI GM, Rob Thomas as he hosts NLP experts and clients, showcasing how NLP technologies are optimizing businesses across industries.

Also, some of the technologies out there only make you think they understand the meaning of a text. NLP has its roots in the 1950s with the development of machine translation systems. The field has since expanded, driven by advancements in linguistics, computer science, and artificial intelligence. Milestones like Noam Chomsky’s transformational grammar theory, the invention of rule-based systems, and the rise of statistical and neural approaches, such as deep learning, have all contributed to the current state of NLP. One of the main reasons natural language processing is so critical to businesses is that it can be used to analyze large volumes of text data, like social media comments, customer support tickets, online reviews, news reports, and more.

You can foun additiona information about ai customer service and artificial intelligence and NLP. Take sentiment analysis, for example, which uses natural language processing to detect emotions in text. This classification task is one of the most popular tasks of NLP, often used by businesses to automatically detect brand sentiment on social media. Analyzing these interactions can help brands detect urgent customer issues that they need to respond to right away, or monitor overall customer satisfaction.

For instance, when a user types ‘how’, the system might suggest ‘are’, ‘do’, ‘to’ as the following word, based on the frequency of these combinations in prior usage. This application of NLP not only enhances efficiency in communication but also adds an element of personalization to our digital experiences. Another kind of model is used to recognize and classify entities in documents.

As computer systems cannot explicitly understand grammar, they require a specific program to dismantle a sentence, then reassemble using another language in a manner that makes sense to humans. Based on some data or query, an NLG system would fill in the blank, like a game of Mad Libs. But over time, natural language generation systems have evolved with the application of hidden Markov chains, recurrent neural networks, and transformers, enabling more dynamic text generation in real time. Essentially, NLP systems attempt to analyze, and in many cases, “understand” human language. When we feed machines input data, we represent it numerically, because that’s how computers read data. This representation must contain not only the word’s meaning, but also its context and semantic connections to other words.