HPE enters natural language question answering fray

Hewlett Packard Enterprise is offering a series of core services designed to offer natural language question answering.
Written by Larry Dignan, Contributor

Hewlett Packard Enterprise has added natural language question answering to its unstructured data analytics engine.

The engine, HPE IDOL, uses machine learning to boost the accuracy of human interactions with computers.

HPE IDOL's natural question answering capability joins a crowded field as Nuance and IBM via Watson all have similar plays on natural language processing.

One big wild card with HPE's effort is cloud providers. For instance, Amazon Web Services announced a service called Amazon Polly, which turns text into lifelike speech in 24 languages. Amazon Lex, which powers Alexa, provides cloud-based conversational experiences. AWS rolled out those systems last week as part of a broader artificial intelligence push. Meanwhile, Google and Microsoft have natural languages cloud services.

According to HPE, the edge for IDOL will be allowing developers to leverage its technology to answer user questions without complicated interfaces or a lot of training.

HPE's Natural Language Question Answering aims to figure out intent and use everything from public data sources to structured and unstructured corporate information. HPE added that its natural language question answering system can integrate with dialogue flow systems to be conversational.

The natural language system is included in HPE's IDOL 11.2 software. The capabilities include:

  • IDOL Answer Bank, which includes curated responses to predetermined reference questions.
  • IDOL Fact Bank, which handles structured and unstructured queries, to answer questions such as the price of a stock or details from a financial report.
  • IDOL Passage Extract, a text overview based on a variety of data.
  • IDOL Answer Server, which uses all of the capabilities to provide an optimal answer.

Quest Diagnostics has integrated HPE IDOL's Natural Language Question Answering system.

Editorial standards