No results found

Your search did not match any results.

We suggest you try the following to help find what you’re looking for:

  • Check the spelling of your keyword search.
  • Use synonyms for the keyword you typed, for example, try “application” instead of “software.”
  • Try one of the popular searches shown below.
  • Start a new search.
Trending Questions
social discussion icon

Enrich Natural Language Processing and Generation for Better Conversation Analytics

Why Are We Building This?
People don’t speak like computers. Yet we turn to computers for quick answers to make the best possible decisions in our business and personal lives. Oracle aims to eliminate the need to translate your questions to accommodate how analytics systems work. With natural language processing, you’ll be able to get more accurate answers—faster and more efficiently.

What is natural language?

Oracle thinks of natural language in two ways:

  • Natural language processing (NLP). The ability to interrogate the data with text or voice. This is also called "language in." Oracle Analytics can currently process 28 languages on input.
  • Natural language generation (NLG). The ability to provide a verbal description of what has happened. This is also called "language out." Oracle Analytics summarizes meaningful information into text using a concept known as "grammar of graphics."

The natural language processing capabilities we plan to add to Oracle Analytics include the following:

  • Understanding plurals, synonyms, and misspellings. This is an integral capability of intelligent search.
  • Sharing global synonyms. A shared capability with intelligent search and augmented data preparation that lets you define common global synonyms. For example: “avg” can mean “average.”
  • Activating clarifying questions. For example: a question for content about Mary Smith when there is more than one Mary Smith, will prompt the system to ask “Did you mean Mary Smith, the employee, or Mary Smith, the customer?”
  • Adding conditions to the question incrementally. For example: you may start with “revenue by product,” and then add “for 2019,” and then “by region.”
  • Personalizing what’s important. The system learns what’s important from the previous questions asked by you, your coworkers, or a predetermined group.
  • Asking a question in a different language. For example: a question in Dutch can be interpreted and answered from English-based data.
  • Adding integration of more chatbot capabilities. Full API and specific chatbot integration within the system.

The natural language processing generation capabilities we plan to add to Oracle Analytics include the following:

  • Narrations out of the box with any Oracle Analytics visualization
  • Enhanced integration with chatbot for descriptive output
  • Integration to voice-on-output such as Amazon Echo and Apple’s Siri

How does this benefit you, the customer?

Natural language processing significantly expands your consumer community for analytics by making interaction with data as natural as asking a question. Additionally, the generation of narratives on output significantly improves productivity for many roles in the business (finance teams, in particular) by enabling users to customize narratives for a larger audience.

Safe Harbor

The preceding is intended to outline our general product direction. It is intended for informational purposes only, and may not be incorporated into any contract. It is not a commitment to deliver any material, code, or functionality, and should not be relied upon in making purchasing decisions. The development, release, timing, and pricing of any features or functionality described for Oracle’s products may change and remains at the sole discretion of Oracle Corporation.