IBM’s Watson Developer CloudBy Tanay Pant
IBM made its debut in the artificial intelligence field several years ago with Watson, an artificial intelligence computer system that can answer questions posed in natural language.
Watson now includes a collection of Web APIs that enable web developers to leverage Watson's cognitive capabilities in their web applications. These REST APIs are publicly available through IBM's Bluemix cloud services platform, dubbed the Watson Developer Cloud.
IBM’s CTO for Watson, Rob High, has been quoted as saying that developers can utilize these APIs without needing to understand anything about machine learning.
Demo Apps at the Developer Cloud
Personality Insights Demonstration
The IBM Watson Personality Insights service provides an API that enables applications to derive insights from social media, enterprise data or from digital communications.
Watson gives the personality insights in the form of percentages of what's known as the "Big Five". These are the human characteristics of Openness, Conscientiousness, Extraversion, Emotional Range, and Agreeableness. Other than the Big Five, it also gives some insights into the Needs and Values of a person's personality.
Their website suggests that –
These insights help businesses to understand their clients' preferences and improve customer satisfaction by anticipating customer needs and recommending future actions. This allows businesses to improve client acquisition, retention, and engagement, and to strengthen relations with their clients.
It also provides a beautiful visualization of its results in the form of a chart, created with the help of D3.js:
Question and Answer
The Watson Question and Answer service interprets and answers questions related to the Travel and Health industries by obtaining meaningful information based on primary data sources (brochures, web pages, manuals, records, and so on).
Each answer has an associated confidence level, and it links to supporting evidence for the answer. This application is currently in Beta, since it hasn't been trained currently through machine learning.
The IBM Watson Visual Recognition service provides an API that enables a user to analyze images or video frames to understand their contents.
We decided to test the application, and provided an image from Wikipedia as input in the landmarks category:
And Watson gave the following output in less than 8 seconds!
13 Services Currently Offered by IBM
- Personality Insights
enables deeper understanding of people's personality characteristics, needs, and values to help engage users on their own terms.
- Concept Insights
explores information based on the concepts behind your input, rather than limiting investigation to findings based on traditional text matching.
- Concept Expansion
maps euphemisms or colloquial terms to more commonly understood phrases.
- Language Identification
identifies the language in which text is written.
- Machine Translation
converts text input in one language into a destination language for the end user.
- Message Resonance
facilitates communication with people in a style and in words that suit them.
- Question and Answer
interprets and answers user questions directly, based on primary data sources.
- Relationship Extraction
intelligently finds relationships between sentence components (nouns, verbs, subjects, objects, etc.).
- Speech to Text
transcribes English speech to text with low latency.
- Text to Speech
synthesizes natural-sounding speech from English or Spanish text.
- Tradeoff Analytics
helps people optimize their decisions, while striking a balance between multiple – often conflicting – objectives.
- Visual Recognition
analyzes the visual content of images and video frames to understand the content directly, without the need for a textual description.
- Visualization Rendering
provides graphical representations of data analysis for easier understanding.
IBM has taken a pleasing step by making Watson's APIs freely available to developers, enabling them to make their applications cognitive and smarter. Hopefully, over time, more machine learning and natural language processing services like this will become freely available for developers. If they could be open-source, too, that would be icing on the cake!
Various individuals and organizations are currently developing natural language processing solutions such as Siri, Google Now, Cortana, Jasper and Sirius. The ability to integrate such services with web applications would be an extra bonus, ushering in a new era of speech interaction with web services, and freeing us a little more from the mouse and keyboard!
So, what do you think of Watson's new APIs? Have you tried them yet? If not, can you envisage what you might be using them for one day?