When Watson goes to work in a particular field it learns the language, the jargon and the mode of thought of that domain. Take the term ‘cancer’ for instance, there are many different types of cancer and each type has different symptoms and treatments. However, those symptoms can also be associated with diseases other than cancer. Treatments can have side effects and affect people differently depending on many factors. Watson evaluates standard-of-care practices and thousands of pages of literature that capture the best science in the field. And From all of that, Watson identifies the therapies that offer the best choices for the doctor to consider in their treatment of the patient.
With the guidance of human experts, Watson collects the knowledge required to have literacy in a particular domain, what’s called a Corpus of Knowledge. Collecting a Corpus starts off with loading a relevant body of literature into Watson. Building the Corpus also requires some human intervention to cull through the information and discard anything that is out of date, poorly regarded or immaterial to the problem domain. We refer to this as curating the content.
Next the data is pre-processed by Watson, building indices and other meta data that make working with that content more efficient. This is known as ingestion. At this time Watson may also create a knowledge graph to assist and answer more precise questions.
Now that Watson has ingested the Corpus, it needs to be trained by a human expert to learn how to interpret the information, to learn the best possible responses and acquire the ability to find ptterns. Watson partners with experts, who train it in using an approach called Machine Learning. An expert will upload training data into Watson in the form of question-answer pairs that serve as ground truth. This doesn’t give explicit answers for every question it receives, but rather teaches it the linguistic patterns of meaning in the domain.
Once Watson has been Trained on Q/A pairs it continues to learn through ongoing interaction. Interactions between users and watson are periodically reviewed by experts and fed back into the system to help Watson better interpret information. Likewise, as new information is published, Watson is updated so that it’s constantly adapting to shifts in knowledge and linguistic interpretation in any given field.
Watson is now ready to respond to questions about highly complex situations and quickly provide a range of potential responses and recommendations that are backed by evidence. It’s also prepared to identify new insights or patterns locked away in information.
From Metallurgists looking for new alloys, to researchers looking to develop more effective drugs, human experts are using Watson to uncover new possibilities in data and make better evidence-based decisions.
Across all of these different applications there is a common approach that Watson follows. After identifying parts of speech in a question or inquiry, it generates hypothesis. Watson then looks for evidence to support or refute the hypothesis. It scores each passage based on statistical modelling for each piece of evidence, known as weighted-evidence scores. Watson estimates its confidence based on how high the response is rated during evidence scoring and ranking. In essence, Watson is able to run analytics against a body of data to glean insights which Watson can turn into inspirations, allowing human experts to make better and more informed decisions.
Across an organization, Watson scales and democratizes expertise by surfacing accurate responses and answers to an inquiry or question. Watson also accelerates expertise by surfacing a set of possibilities from a large body of data, saving valuable time.
Today Watson is revolutionizing the way we make decisions, become experts, and share expertise in fields as diverse as Law, medicine and even cooking. Further, Watson is discovering and offering answers in patterns we hadn’t known existed, faster than any known person or group of people ever could, in ways that make a material difference every day.
Most important of all, Watson learns, adapts and keeps getting smarter. It actually gains value with age by learning from its interactions with us and from its own successes and failures just like we do.