Semantic Web Technology in Watson

Half day tutorial

Open domain Question Answering (QA) is a long standing research problem. Recently, IBM took on this challenge in the context of Jeopardy!, a well-known TV quiz show that has been airing on television in the United States for more than 25 years. It pits three human contestants against one another in a competition that requires answering rich natural language questions over a very broad domain of topics. The development of a system able to compete with grand champions in the Jeopardy! challenge led to the design of the DeepQA architecture and the implementation of Watson.

The DeepQA project shapes a grand challenge in Computer Science that aims to illustrate how the wide and growing accessibility of natural language content and the integration and advancement of Natural Language Processing, Information Retrieval, Machine Learning, Knowledge Representation and Reasoning, and massively parallel computation can drive open-domain automatic Question Answering technology to a point where it clearly and consistently rivals the best human performance.

Semantic Web Technology, enhanced by a massive use of open linked data, plays a crucial role in the overall Deep QA architecture. For example, linked data such as DBpedia and Geonames and triple stores such as Sesame have been used to generate candidate answers and to score them under multiple points of view such as type coercion and geographic proximity.  In addition the connection between linked data and natural language text offered by Wikipedia has been very useful to generate open domain training data for relation detection and entity recognition systems, improving substantially the NLP capabilities of the system and therefore allowing the development of a truly open domain QA system. That’s why we decided to focus this tutorial on the Semantic Web Technology adopted by Watson and on how it fits in the general Deep QA architecture. The course is structured in two parts, described below.

Lesson 1 An overview of the Deep QA project

This lesson provides a general introduction to the Deep QA project, addressing the following topics: the Jeopardy! Grand challenge, the Deep QA architecture, the machine learning framework for answer scoring, experimental settings and evaluation in the Jeopardy! task, and the system development lifecycle of Watson.

Lesson 2 Semantic Web Technology in Watson
This lesson focuses on the Semantic Web technology implemented in Watson, highlighting the advancements with respect to state of the art techniques in Question Answering. Finally we present the next step of the Deep QA project focusing on adapting the Deep QA technology to the healthcare domain.


Organizing Committee