2017-2018 Senior Project - WikiQA
Extracting structured information from unstructured text has been a long-standing problem in the field of Natural Language Processing (NLP). However, effective approaches for text comprehension are still in the nascent stage. Question answering is one of the important applications of text comprehension. Although answering complicated questions posed by the users is a challenging task, we are investigating a system to automatically answer questions about relationships using the knowledge contained in Wikipedia. The WikiQA system utilizes an existing knowledge base with entities and relations extracted from Wikipedia articles. Text evidence is produced on-demand for relations between entities specified by users.
