Capturing negation in question answering systems

摘要

This masters thesis will present my research on the world of Negation, as welludas my attempt to apply the Negation Algorithm on a new Question Answeringudsystem which is able to accept negative input in natural language. The aim ofudthis project is to focus on the uses of negation in natural language, and onudthe importance of including negative constructions in Information Retrievaludprocesses, which for the moment treat negation as a nonexisting phenomenonudin natural language.udThe new restricted-domain question answering system is called NotFilms, andudaccepts subject and object questions regarding Movies of 2005. NotFilms readsudthe input in natural language, produces its semantic representation, appliesudthe IR algorithm on the semantic reading, and provides the user with the exactudanswer. It allows the existence of the negative particle ’not’ in the input,udand as long as the input can be semantically represented by the linguistic processesudof the system, it answers both affirmative and negative questions withudthe same efficiency. Results have shown that the linguistic and IR processes ofudthe system can give relevant answers for 75% of the users’ questions.