IBM has made a big bet on Watson and the cognitive era. Curiosity has been mounting. We’ve all know Watson as a Jeopardy champion. Now he’s the friendly cog in a support grouphosted by Carrie Fisher. Beyond all the marketing, fun and games, executives want to know:
Who is the real Watson? What can he do for me and my company…today?
For example, a client sent me very brief email recently.
“Have you met Watson?” she asked. “What do you think?”
As a long-time student and proponent of the Semantic Web, I’ve kept a close, but skeptical eye on Watson. Just recently, I finally got the chance to meet him face-to-interface on IBM Bluemix. In what will probably amount to a series of posts, I’ll provide a summary of what I’ve learned and what I think.
Bottom line: Watson is real and ready to serve.
One of the quickest and easiest ways for you to get personally acquainted with Watson is on IBM Bluemix where a host of Watson services are available now, so we’ll start this series there. Bluemix is IBM’s cloud platform for building, running, and managing applications and services. Bluemix starts you up in a trial mode, which gives you some elbow room to hack around before incurring fees, but you don’t even need an account to explore many of the Watson services. From the Bluemix Catalog, you can look under Services > Watson to find the available services. You can then click on each service icon to view more information and find a link to the documentation. Many of the documentation pages link to a demo, which allows you to try the service using a ready-made example. This is a great way to get a quick idea of what’s capable and to get those creative juices flowing. In this post, I’m going to try to save you a little time by giving you a concise summary of each of the available Watson services, along with some relevant links.
Watson services on IBM Bluemix
Analyzes unstructured text and image content
The AlchemyAPI is actually comprised of three services that help you understand the content and context within text and images. For example, you can use it to extract the people, places, companies, and other entities mentioned in a news article or analyze an image to understand the contents of the photo.
Text analysis through natural language processing. Process text to understand its sentiment, emotions, keywords, entities, high-level concepts and more.
Provides news and blog content enriched with natural language processing to allow for highly targeted search and trend analysis. Query the world’s news sources and blogs like a database.
Understands and analyzes complex visual scenes without needing textual clues. Recognize images, scenes, and understand the objects within images.
Maps euphemisms or colloquial terms to more commonly understood phrases
Analyzes text and learns similar terms (words or phrases) based on context. Rapidly create a lexicon (a set of related terms) from a data set of text fragments. The output can be used to provide further understanding of data and improve text analytics pipelines.
Explore the concepts behind your input, identifying associations beyond traditional text matching
Links documents that you provide with a pre-existing graph of concepts based on Wikipedia (e.g. ‘The New York Times’, ‘Machine learning’, etc.). Two types of links are identified: explicit links when a document directly mentions a concept, and implicit links which connect your documents to relevant concepts that are not directly mentioned in them.
Search for documents that are relevant to a concept or collection of concepts by exploring the explicit and implicit links.
Enable your application to use natural language to converse with users
Use natural language to automatically respond to user questions, cross-sell and up-sell, walk users through processes or applications, or even hand-hold users through difficult tasks. Track and store user profile information to learn more about end users, guide them through processes based on their unique situation, or pass their information to a back-end system to help them take action and get the help they need.
Converts a HTML, PDF, or Microsoft Word™ document into a normalized HTML, plain text, or a set of JSON-formatted Answer units. This service also takes documents and ‘chunks them up” into smaller answer units to return as passages.
Translates text from one language to another for specific documents
Dynamically translates news, patents, or conversational documents. Instantly publish content in multiple languages. Allow your French-speaking staff to instantly send emails in English.
Natural Language Classifier
Performs natural language classification on question texts. A user would be able to train their data and the predict the appropriate class for an input question.
Applies cognitive computing techniques to return the best matching classes for a sentence or phrase. For example, you submit a question and the service returns keys to the best matching answers or next actions for your application. You create a classifier instance by providing a set of representative strings and a set of one or more correct classes for each training. After training, the new classifier can accept new questions or phrases and return the top matches with a probability value for each match.
- Natural Language Classifier Overview
- Natural Language Classifier Documentation
- Natural Language Classifier Demo
Derives insights from transactional and social media data to identify psychological traits
Derives insights from transactional and social media data to identify psychological traits which determine purchase decisions, intent and behavioral traits; utilized to improve conversion rates.
Intelligently finds relationships between sentence components (nouns, verbs, subjects, objects, etc.)
Parses sentences into their various components and detects relationships between the components. It can process new terms (like people’s names in a news feed) it has never analyzed before through contextual analysis. Sentence components include parts of speech (noun, verb, adjective, conjunction, etc.) and functions (subjects, objects, predicates, etc.). The service maps the relationships between the components so that users or analytics engines can more easily understand the meaning of individual sentences and documents.
Retrieve and Rank
Add machine learning enhanced search capabilities to your application
Helps users find the most relevant information for their query by using a combination of search and machine learning algorithms to detect “signals” in the data. Built on top of Apache Solr, developers load their data into the service, train a machine learning model based on known relevant results, then leverage this model to provide improved results to their end users based on their question or query.
Speech to Text
Low-latency, streaming transcription
Converts the human voice into the written word.
Bridge the gap between the spoken word and the written form, including voice control of embedded systems, transcription of meetings and conference calls, and dictation of email and notes. Uses machine intelligence to combine information about grammar and language structure with knowledge of the composition of the audio signal to generate an accurate transcription.
Text to Speech
Synthesizes natural-sounding speech from text
Processes text and natural language to generate synthesized audio output complete with appropriate cadence and intonation.
Helps detect, understand and revise the language tones of emotions, social propensities and writing styles
Analyze various language tones, such as joy, sadness, anger, and agreeableness, in daily written communications. Such tones can impact the effectiveness of communication in different contexts. Tone Analyzer leverages cognitive linguistic analysis to identify such tones for better communication. It detects three types of tones, including emotion (anger, disgust, fear, joy and sadness), social propensities (openness, conscientiousness, extraversion, agreeableness, and emotional range), and writing styles (analytical, confident and tentative) from text.
Helps make better choices under multiple conflicting goals. Combines smart visualization and recommendations for tradeoff exploration
Helps people make better choices while taking into account multiple, often conflicting, goals that matter when making that choice. The service can be used to help make complex decisions like what mortgage to take, and also for helping with more everyday ones like which laptop to purchase. Tradeoff Analytics uses Pareto filtering techniques in order to identify the optimal alternatives across multiple criteria. It then uses various analytical and visual approaches to help the decision maker explore the tradeoffs within the optimal set of alternatives. This insures that the chosen option will adhere to the goals and criteria that matter for the decision maker.
Analyzes the visual content of images and videos to understand their content without requiring a textual description
Enables you to analyze the visual appearance of images or video frames to understand what’s happening in a scene. Using machine learning technology, semantic classifiers recognize many visual entities, such as settings, objects, and events. The service applies these pre-learned models to imagery that you have uploaded to the service and returns a score for each image for each model, indicating the likelihood of that visual element being present in the image.
A third-party service provided by Cognitive Scale.
Cognitive insights and advice fuel personalized and contextual commerce opportunities for consumers and businesses and provide more relevant and actionable recommendations. Cognitive Commerce™ provides the next level of fulfillment and helps drive commercial transactions.
A third-party service provided by Cognitive Scale.
Cognitive Graphs are an encapsulation of knowledge, sourced from 3rd party, internal, and private data sources, using domain specific models, into a query-able graph representation. Sourcing Agents pull, enrich, transform, and map, multi-structured and dark data, using machine learning techniques. The Cognitive Graph can be projected in multiple ways to be applied to different problem sets.
A third-party service provided by Cognitive Scale.
Cognitive Insights are contextually relevant and personalized observations or predictions, presented with a recommendation, with the purpose of invoking user action. An insight serves to augment the knowledge, perception, and awareness of the end user, with the goal of improving their efficiency, decisions, and ability to quickly react to emerging scenarios. This service, when used in conjunction with a basis of knowledge and real-time data provided by the cognitive graph, can be used to power end-user applications.
In this post, I’ve summarized the Watson services that are available for your use on IBM Bluemix. I’ve provided some links to documentation and demos, so you can jump quickly to spots of interest. With Watson, there’s really a lot of fascinating ground to cover. I have much more to share, so stay tuned.
Since posting about the Watson services on IBM Bluemix (above), I've learned that there are other services and applications now falling within IBM's Watson brand. As I learn about each, I am now adding those as an addendum below.
IBM Watson Workspace is a way to message your teams and coworkers from anywhere. It helps you keep your work conversations in one place, and easily find information in previous conversations. With its cognitive features and ability to interact with other apps, you can work more easily and work the way you want.
Watson Work Services
IBM Watson Work Services provide you with a set of APIs that are designed to help people get work done. You can make use of these services to build out your own application.
We also have an application built on our platform, called Watson Workspace. You can integrate and connect your application to Watson Workspace through our services.
Watson Knowledge Studio
IBM Watson Knowledge Studio is a cloud-based application that enables developers and domain experts to collaborate and create custom annotator components for unique industries. These annotators can identify mentions and relationships in unstructured data and be easily administered throughout their lifecycle using one common tool. Annotator components can be deployed directly to IBM Watson Explorer and Alchemy Language on IBM Watson Developer Cloud.
Watson Question and Answer Service
NO LONGER AVAILABLE
This service is gone as of Nov 20, 2015. For more information on replacement services and how to use them for similar results, see:
Watson Virtual Agent
Watson Virtual Agent is a new way to provide automated services to your customers. It offers a cognitive, conversational self-service experience that can provide answers and take action. You can easily customize your Watson Virtual Agent to fit your specific business needs, provide custom content and match your business brand. Additionally, deep analytics provide insights on your customer's engagement with the Watson Virtual Agent and help with the understanding of your constantly changing customer's needs.