IBM adds Watson tools for reading comprehension, FAQ extraction

EY is using Watson to streamline its merger and acquisition due diligence.

special feature

Managing AI and ML in the Enterprise

The AI and ML deployments are well underway, but for CXOs the biggest issue will be managing these initiatives, and figuring out where the data science team fits in and what algorithms to buy versus build.

Read More

IBM said it is adding reading comprehension, the ability to extract information from FAQ documents, support for new languages and intent classification models to Watson.

The new features outlined by IBM are designed to advance natural language processing and make it a bigger part of automation workflows. IBM has been looking to distinguish Watson with its natural language processing research efforts. For instance, IBM recently said it is commercializing its Project Debater technology that enables artificial intelligence to debate humans and handle complex topics.

Among the core additions:

  • Reading Comprehension, based on technology from IBM Research, is in beta in Watson Discovery. 
  • FAQ Extraction is in beta in IBM Watson Assistant's search. Using natural language processing, IBM Watson Assistant can keep virtual assistants up to date with latest answers.
  • A new intent classification model in Watson Assistant to improve user interaction with assistants.
  • Support for 10 new languages in Watson Discovery.

Primers: What is AI? | What is machine learning? | What is deep learning? | What is artificial general intelligence?    

Here's a look at Reading Comprehension. 

ibm-reading-comprehension.png

EY's Tony Qui, chief innovation officer, said the firm is using Watson in its diligence process for mergers and acquisitions. Watson ingests and scans 100s of thousands of documents in the diligence process so anything affecting valuations is surfaced in data clean rooms.

The capabilities are part of EY's Digital Edge, a natural language processing engine that's trained on EY's M&A techniques and approaches. 

"With Watson looking for things like product recalls and cyber breaches and how it affects our M&A model, we can spend more time on diligence and analysis instead of opening and closing documents," said Qui.

IBM also said that it will commercialize IBM Research's AI Factsheets in Watson Studio in Cloud Pak for Data throughout 2021. AI Factsheets are designed to provide information about a product's characteristics.

Seth Dobrin, IBM's chief data officer, said the AI Factsheets are like a nutrition label "for AI to understand what AI did."

IBM also said it will offer new services for scaling AI.