Complex question answering : minimizing the gaps and beyond

Simple item page
dc.contributor.authorSadid-Al-Hasan, Sheikh
dc.contributor.supervisorChali, Yllias
dc.date.accessioned2014-06-04T15:34:24Z
dc.date.available2014-06-04T15:34:24Z
dc.date.issued2013
dc.degree.levelPh.Den_US
dc.degree.levelPhD
dc.descriptionxi, 192 leaves : ill. ; 29 cmen_US
dc.description.abstractCurrent Question Answering (QA) systems have been significantly advanced in demonstrating finer abilities to answer simple factoid and list questions. Such questions are easier to process as they require small snippets of texts as the answers. However, there is a category of questions that represents a more complex information need, which cannot be satisfied easily by simply extracting a single entity or a single sentence. For example, the question: “How was Japan affected by the earthquake?” suggests that the inquirer is looking for information in the context of a wider perspective. We call these “complex questions” and focus on the task of answering them with the intention to minimize the existing gaps in the literature. The major limitation of the available search and QA systems is that they lack a way of measuring whether a user is satisfied with the information provided. This was our motivation to propose a reinforcement learning formulation to the complex question answering problem. Next, we presented an integer linear programming formulation where sentence compression models were applied for the query-focused multi-document summarization task in order to investigate if sentence compression improves the overall performance. Both compression and summarization were considered as global optimization problems. We also investigated the impact of syntactic and semantic information in a graph-based random walk method for answering complex questions. Decomposing a complex question into a series of simple questions and then reusing the techniques developed for answering simple questions is an effective means of answering complex questions. We proposed a supervised approach for automatically learning good decompositions of complex questions in this work. A complex question often asks about a topic of user’s interest. Therefore, the problem of complex question decomposition closely relates to the problem of topic to question generation. We addressed this challenge and proposed a topic to question generation approach to enhance the scope of our problem domain.en_US
dc.identifier.urihttps://hdl.handle.net/10133/3436
dc.language.isoen_CAen_US
dc.proquestyesNoen_US
dc.publisherLethbridge, Alta. : University of Lethbridge, Dept. of Mathematics and Computer Scienceen_US
dc.publisher.departmentDepartment of Mathematics and Computer Scienceen_US
dc.publisher.facultyArts and Scienceen_US
dc.relation.ispartofseriesThesis (University of Lethbridge. Faculty of Arts and Science)en_US
dc.subjectQuestion-answering systemsen_US
dc.subjectReinforcement learningen_US
dc.subjectInteger programmingen_US
dc.subjectLinear programmingen_US
dc.subjectRandom walks (Mathematics)en_US
dc.subjectDecomposition methoden_US
dc.subjectDissertations, Academicen_US
dc.titleComplex question answering : minimizing the gaps and beyonden_US
dc.typeThesisen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
SADIDALHASAN_SHEIKH_PHD_2013.pdf
Size:
887.92 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Arts and Science, Faculty of
University of Lethbridge Theses