Use this URL to cite or link to this record in EThOS:
Title: Information fusion for automated question answering
Author: Dalmas, Tiphaine
Awarding Body: University of Edinburgh
Current Institution: University of Edinburgh
Date of Award: 2007
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
Until recently, research efforts in automated Question Answering (QA) have mainly focused on getting a good understanding of questions to retrieve correct answers. I focus on the analysis of the relationships between answer candidates as provided in open domain QA on multiple documents. I argue that such candidates have intrinsic properties, partly regardless of the question, and those properties can be exploited to provide better quality and more user-oriented answers in QA. Information fusion refers to the technique of merging pieces of information from different sources. While frequency has proved to be a significant characteristic of a correct answer, I evaluate the value of other relationships characterizing answer variability and redundancy. Partially inspired by recent developments in multi-document summarization, I redefine the concept of “answer” within an engineering approach to QA based on the Model-View-Controller (MVC) pattern of user interface design. An “answer model” is a directed graph in which nodes correspond to entities projected from extractions and edges convey relationships between such nodes. I describe shallow techniques to compare entities and enrich the model by discovering four broad categories of relationships between entities in the model: equivalence, inclusion, aggregation and alternative. Quantitatively, answer candidate modelling improves answer extraction accuracy. It also proves to be more robust to incorrect answer candidates than traditional techniques. Qualitatively, models provide meta-information encoded by relationships that allow shallow reasoning to help organize and generate the final output. Coupling this fusion-based reasoning with the MVC approach, I report experiments on mixed-media answering involving generation of illustrated summaries, and discuss the application of web-based answer modelling to improve non web QA tasks. Finally, I discuss issues related to the computation of answer models (candidate selection for fusion, relationship transitivity), and address the difficulty of assessing fusion-based answers with the current evolution methods in QA.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available