IBM has announced several new IBM Watson technologies that the company hopes will advance the Natural Language Processing (NLP) capabilities within Watson APIs. These new features, which had previously been developed as part of the company’s Project Debater program, include advanced sentiment analysis, advanced topic clustering, and summarization tools.
Project Debater is IBM’s AI system that serves as a testing ground for the company’s most advanced NLP systems. Among the new features to be brought forward from Project Debater is an advanced sentiment analysis feature that is designed to tackle the difficult task of interpreting common idioms and colloquialisms. “Hardly helpful” and “hot under the collar”, are key examples of such phrases that this technology is designed to help process.
Additionally, Watson APIs gain a new summarization feature that does exactly what the name implies, scours various sources to create a brief summary of relevant data corresponding to what is being discussed. The technology was most notably used by the GRAMMYS to provide summaries of hundreds of artists.
Advanced Topic Clustering capabilities will also be moved over to Watson. Clustering conversation data into topics streamlines processing by allowing for information to be group analyzed. Additionally, companies will be able to fine-tune the process to their specific industry.
In the announcement Rob Thomas, General Manager, IBM Data and AI, spoke to the value that these features provide to end-users:
"Language is a tool for expressing thought and opinion, as much as it is a tool for information… This is why we're harvesting technology from Project Debater and integrating it into Watson – to enable businesses to capture, analyze, and understand more from human language and start to transform how they utilize intellectual capital that's codified in data."