IBM Debating Technologies - overview
Deep Blue showed the world that a computer can beat a human world champion in chess. Watson used big data analytics to defeat top human contestants in question and answering. Now, IBM Debating Technologies are ushering in a new era of Cognitive Computing. The goal of this project is to develop technologies that can assist humans to reason, make decisions, or persuade others. When it comes to decisions, opinions or points of view, there are no "right" or "wrong" answers. Successful arguments are based on evidence, constructed with perspective, and delivered persuasively. These abilities have always been considered exclusive to humans - until now.
This multi-year cognitive computing project explores scenarios where there isn't only one answer (for example as a Jeopardy! clue). We have demonstrated the ability to generate pro and con arguments and speeches for controversial topics and will show other elements over time.
The distinctive debating technologies developed in this project can have great practical use in industries such as government, legal, finance, healthcare, and sales, to name just a few. For example, automatic argument construction could serve to dramatically enhance business processes and decision making – whether by providing assisted reasoning for which treatment will work best on a patient, or by helping salespeople develop persuasive arguments when working with clients in deal negotiations, or by presenting pro and con arguments in support of or against government policies.
The science and technology used in this project includes NLP, Machine Learning, IR, Knowledge Graphs, Expressive Text to Speech (ETTS), and more. On the academic front, our researchers play a key role in establishing the rapidly evolving field of Computational Argumentation (see Publications tab). Researchers are welcome to use our publically available datasets.
IBM Research - Haifa along with IBM Research labs in India, Dublin and Watson are working on this effort; collaborating with teams from the Watson group. More information and a demo about this effort can be found in this video (starting around 45 mins).
Contact: Ranit Aharonov, IBM Research - Haifa, email@example.com