Abstract

Abstract: One and the same fact in natural language can be expressed in many different ways by using different words and/or a different syntax. This phenomenon, commonly called paraphrasing, is the main reason why Natural Language Processing (NLP) is such a challenging task. This becomes especially obvious in Question Answering (QA) where the task is to automatically answer a question posed in natural language, usually in a text collection also consisting of natural language texts. It cannot be assumed that an answer sentence to a question uses the same words as the question and that these words are combined in the same way by using the same syntactic rules.

In my thesis I describe methods that can help to address this problem. Firstly I explore how lexical resources, i.e. FrameNet, PropBank and VerbNet can be used to recognize a wide range of syntactic realizations that an answer sentence to a given question can have. Furthermore, I use a corpus of question and answer sentence pairs (QASPs) to develop an approach to QA based on matching dependency relations between answer candidates and question constituents in the answer sentences. In this talk, I will describe these two approaches in more detail and present evaluation results.