In an attempt to democratise the natural language processing (NLP) capabilities within organisations, IBM announced to integrate Project Debater technologies into Watson throughout the year. The idea is to help organisations begin identifying, understanding and analysing some of the most challenging aspects of the English language with greater clarity, for more significant insights.

This will assist companies in identifying and analysing idioms and colloquialisms for the first time. Phrases, like ‘hardly helpful,’ or ‘hot under the collar,’ have been challenging for AI systems because they are difficult for algorithms to spot. With advanced sentiment analysis, businesses can begin analysing such language data with Watson APIs for a more holistic understanding of their operation. Further, IBM is bringing technology from IBM Research for understanding business documents, such as PDF’s and contracts, to also add to their AI models. 

“IBM Research has been developing and advancing NLP capabilities for years to create intuitive AI systems that can offer deeper business insights, explain decisions, and are less labour-intensive to deploy and maintain. With these new capabilities infused in Watson, Indian organisations have the potential to enhance everything from customer care and transportation, to finance and education,” said Gargi Dasgupta, Director, IBM Research India and CTO, IBM India South Asia 

The key benefits for organisations:

Analysis – Advanced Sentiment Analysis. A new classification technology that will enable clients to create AI models that can more easily classify clauses that occur in business documents, like procurement contracts. Based on Project Debater’s deep learning-based classification technology, the new capability can learn from as few as several hundred samples to do new classifications quickly and easily. It will be added to Watson Discovery later this year.

Briefs – Summarisation. This technology pulls textual data from a variety of sources to provide users with a summary of what is being said and written about a particular topic. An early version of summarisation was leveraged at The GRAMMYS this year to analyse over 18 million articles, blogs and bios to produce bite-sized insights on hundreds of GRAMMY artists and celebrities. 

Clustering – Advanced Topic Clustering. Building on insights gained from Project Debater, new topic clustering techniques will enable users to “cluster” incoming data to create meaningful “topics” of related information, which can then be analysed. The technique, which will be integrated into Watson Discovery later this year, will also allow subject matter experts to customise and fine-tune the topics to reflect the language of specific businesses or industries, like insurance, healthcare and manufacturing.

The post IBM Announced To Integrate Project Debater Into Watson appeared first on Analytics India Magazine.