Question Answering System

Created on Feb. 14, 2013, 2:30 p.m. by Hevok & updated by Hevok on May 2, 2013, 4:38 p.m.

By complementing classic knowledge-based approaches with recent advances in Natural Language Processing, Information Retrieval, and Machine Learning to interpret and reason over huge volumes of widely accessible naturally encoded knowledge (or "unstructured knowledge") we can build effective and adaptable open-domain question answer systems. While they may not be able to formally prove an answer is correct in purely logical terms, they can build confidence based on a combination of reasoning methods that operate directly on a combination of the raw natural language, automatically extracted Entities, Relations and available structured and semi-structured knowledge available from the Semantic Web.

watson.jpg

Tags: answers, questions, language, ai
Parent: Acceleration Technology

Update entry (Admin) | See changes

Comment on This Data Unit