13 IBM Services That Simplify the Building of Cognitive Watson Apps

by Darryl K. Taft

This service maps euphemisms or colloquial terms to more commonly understood phrases. The Concept Expansion service analyzes text and interprets its meaning based on usage in other similar contexts. For example, it could interpret “The Big Apple” as meaning “New York City.” It can be used to create a dictionary of related words and concepts so that euphemisms, colloquialisms or otherwise unclear phrases can be better understood and analyzed.

The Concept Insights service maps user-input words to the underlying concepts of those words based on training on English Wikipedia data. Doing so can broaden the user’s investigation beyond the actual words used in an inquiry. Two types of associations are identified: explicit links when an input document directly mentions a concept and implicit links that connect the input documents to relevant concepts that are not directly mentioned in them. Users of this service can also search for documents that are relevant to a concept or collection of concepts by exploring the explicit and implicit links.

This service identifies the language in which text is written. This helps inform next steps such as translation, voice to text or direct analysis. The service can be used in tandem with the Machine Translation service. Today, the service can identify many languages: Arabic, Chinese (Simplified), Chinese (Traditional), Cyrillic, Danish, Dutch, English, Farsi, Finnish, French, German, Greek, Hebrew; Hind,; Icelandic, Italian, Japanese, Korean, Norwegian (Bokmal), Norwegian (Nynorsk), Portuguese; Spanish, Swedish; Turkish and Urdu.

The Machine Translation service converts text input in one language into a destination language for the end user. Translation is available among English, Brazilian Portuguese, Spanish, French and Arabic.

The Message Resonance service analyzes draft content and scores how well it is likely to be received by a specific target audience. This analysis is based on content that has been written by the target audience itself, such as fans of a specific sports team or new parents. Today, analysis can be done against datasets from people active in cloud computing or related discussions, but future versions will let users provide their own community data.

This service interprets and answers user questions directly based on primary data sources (brochures, Web pages, manuals, records, etc.) that have been selected and gathered into a body of data, or “corpus.” The service returns candidate responses with associated confidence levels and links to supporting evidence. The current corpora that are available in Bluemix focus on the travel and health care industries. Cognitive services learn and improve through training. This beta-level service has no training but shows representative (if not always highly accurate) output. The service is shared to demonstrate how it works. Training the models can improve the results through machine learning.

This service intelligently finds relationships between sentence components (nouns, verbs, subjects, objects, etc.). From unstructured text, Relationship Extraction can extract entities (such as people, locations, organizations and events), and the relationships between these entities (such as person employed-by organization or person resides-in location).

This service transcribes English speech to text with low latency. The Speech to Text service converts the human voice into the written word. This easy-to-use service uses machine intelligence to combine information about grammar and language structure with knowledge of the composition of the audio signal to generate a more accurate transcription. The transcription is continuously sent back to the client and retroactively updated as more speech is heard. Recognition models can be trained for different languages, as well as for specific domains.

This service synthesizes natural-sounding speech from English or Spanish text. The Text to Speech service understands text and natural language to generate synthesized audio output complete with appropriate cadence and intonation. It is available in three voices—two U.S. English voices, including the voice used by Watson in the 2011 Jeopardy match, and one Spanish voice.

This service helps users make better choices to best meet multiple conflicting goals, combining smart visualization and recommendations for trade-off exploration. The Tradeoff Analytics service helps people optimize their decisions while striking a balance between multiple, often conflicting, objectives. The service can be used to help make such complex decisions as what mortgage to take or which laptop to purchase. Tradeoff Analytics uses Pareto filtering techniques to identify the optimal alternatives across multiple criteria. It then uses various analytical and visual approaches to help the decision maker explore the pros and cons of the alternatives.

This service improves understanding of people’s preferences to help engage users on their own terms. The IBM Watson User Modeling service uses linguistic analytics to extract cognitive and social characteristics, including Big Five, Values and Needs, from communications that the user makes available, such as email, text messages, tweets, forum posts and more. By deriving cognitive and social preferences, the service helps users understand, connect to and communicate with other people on a more personalized level.

This service analyzes the visual content of images and video frames to understand the content directly without the need for a textual description. Using machine learning technology, semantic classifiers recognize many visual entities, such as settings, objects and events. The service applies these models to identify imagery and returns candidate responses with confidence levels.

This service provides graphical representations of data analysis for easier understanding. It offers interactive data visualizations that can range from common business charts to more advanced layouts. Visualizations can be easily modified to match user needs, visual styling and types of data being analyzed.