Institutional Repository

Improvements to the complex question answering models

DSpace/Manakin Repository

Show simple item record

dc.contributor.advisor Chali, Yllias
dc.contributor.author Imam, Md. Kaisar
dc.date.accessioned 2012-11-02T22:02:29Z
dc.date.available 2012-11-02T22:02:29Z
dc.date.issued 2011
dc.identifier.uri http://hdl.handle.net/10133/3214
dc.description x, 128 leaves : ill. ; 29 cm en_US
dc.description.abstract In recent years the amount of information on the web has increased dramatically. As a result, it has become a challenge for the researchers to find effective ways that can help us query and extract meaning from these large repositories. Standard document search engines try to address the problem by presenting the users a ranked list of relevant documents. In most cases, this is not enough as the end-user has to go through the entire document to find out the answer he is looking for. Question answering, which is the retrieving of answers to natural language questions from a document collection, tries to remove the onus on the end-user by providing direct access to relevant information. This thesis is concerned with open-domain complex question answering. Unlike simple questions, complex questions cannot be answered easily as they often require inferencing and synthesizing information from multiple documents. Hence, we considered the task of complex question answering as query-focused multi-document summarization. In this thesis, to improve complex question answering we experimented with both empirical and machine learning approaches. We extracted several features of different types (i.e. lexical, lexical semantic, syntactic and semantic) for each of the sentences in the document collection in order to measure its relevancy to the user query. We have formulated the task of complex question answering using reinforcement framework, which to our best knowledge has not been applied for this task before and has the potential to improve itself by fine-tuning the feature weights from user feedback. We have also used unsupervised machine learning techniques (random walk, manifold ranking) and augmented semantic and syntactic information to improve them. Finally we experimented with question decomposition where instead of trying to find the answer of the complex question directly, we decomposed the complex question into a set of simple questions and synthesized the answers to get our final result. en_US
dc.language.iso en_US en_US
dc.publisher Lethbridge, Alta. : University of Lethbridge, c2011 en_US
dc.relation.ispartofseries Thesis (University of Lethbridge. Faculty of Arts and Science) en_US
dc.subject Question-answering systems -- Research en_US
dc.subject Database searching en_US
dc.subject Querying (Computer science) -- Research en_US
dc.subject Natural language processing (Computer science) -- Research en_US
dc.subject Information retrieval -- Research en_US
dc.subject Dissertations, Academic en_US
dc.title Improvements to the complex question answering models en_US
dc.type Thesis en_US
dc.publisher.faculty Arts and Science en_US
dc.publisher.department Department of Mathematics and Computer Science en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record

Related Items

Search DSpace


Advanced Search

Browse

My Account

Statistics