https://hdl.handle.net/2149/2110 2026-04-17T21:54:10Z 2026-04-17T21:54:10Z Wen, Dunwei https://hdl.handle.net/2149/2310 2009-09-18T20:35:39Z 2009-09-18T20:32:54Z

Statistical and Semantic Question Analysis for Situated Question Answering Wen, Dunwei Natural Language Processing (NLP) aims to study techniques and systems for processing and eventually understanding natural language speech and text. Typical NLP tasks include speech recognition, natural language generation, machine translation, question answering (QA) and so on. As natural language is still the most natural and indispensable way to convey knowledge and exchange ideas in e-learning. It is very beneficial to use the state-of-the art NLP technology to support efficient and adaptive teaching and learning. This project concentrates on question answering, which aims to automatically extract answers from relevant resources to natural language questions. First of all, we apply deep analysis on questions, as question analysis is the first and key step in QA and can significantly affect the performance of QA systems. Both statistical and semantic techniques are explored in question analysis for supporting QA situated in specific educational environments. The questions are parsed and semantic roles in the questions are recognized by the help of VerbNet, a lexical semantics resource that incorporates both semantic and syntactic information about verbs and their semantic roles. The semantic frames of both questions and its possible answers are constructed and compared to filter out the most possible answers to the questions. We also defined a set of features that we think have strong influence on the semantic similarity of two sentences, and incorporate machine learning algorithm to learn the structure and weights of the features. The learned classifier is then used to decide the best answers to a question. A prototype experimental question answering system based on the proposed structure and methods has been built for demonstration and experiments. The experimental results have been presented in our paper and report. An online presentation/demo is also available for a short introduction of this research work. The first part shows the use of an NLP server for a deeper question analysis in a search engine like question answering application designed for facilitating students' access and retrieval of knowledge and information from the learning materials in the form of natural language text. The second part shows how NLP parsing tools analyze natural language sentences, and thus provide information for further understanding of the natural language questions and answers. In the third part, an interface of our NLP based QA system shows the main underlying processes of the system step by step, from a user query, syntactic parsing, to semantic analysis, searching and matching, and finally lead to the possible answer sets of the query. The last two parts are experiments on semantic analysis and feature learning for automated question answering respectively. They evaluate the performance of our methods for a set of test sentences against the test corpora, and serve as platforms for us to develop effective QA system of the research program. This research has provided the Primary Investigator (PI) with experience and several important outcomes such as a prototype system, experimental results and research report and paper. The PI's future research will surely along the same direction, with further theoretical research and feasible application, especially in distance education.

2009-09-18T20:32:54Z Conrad, Dianne https://hdl.handle.net/2149/2249 2009-07-22T21:44:23Z 2009-07-22T21:44:23Z

Exploring the Contribution of Mentoring to Knowledge Building in PLAR Practice Conrad, Dianne Through RPL’s process of intensive reflection, learners come to understand the nature of their past learning. In so doing, new knowledge – knowledge about their own learning histories and learning styles – is created. This is not an easy task, and mentoring is important to learners as they engage with and learn to take ownership of their own learning. This study, informed by the central research question – how best can mentoring be enacted in order to foster and elicit the high-level cognitive activity required for successful RPL? – gathered data from learners and mentors from four Canadian institutions. Major findings include the importance of learners' "finding their voices" – academically, linguistically, and emotionally. Learners' empowerment emerged as a major theme as did the the inability of both learners and mentors to speak fluently about their own learning process. Data reflecting input from both learners and mentors also reveal the complex nature of the RPL process, mentors' sensitivity to learners' work, learners' extreme dedication and commitment to the process, and their pride of completion. The project's research activities were completed as per the project description. Learners and mentors from 4 different Canadian institutions participated in providing data. Initial questionnaires were followed by telephone interviews (3), a face-to-face interview (1), and an on-site focus group (7).

2009-07-22T21:44:23Z Smith, Jay Chen, Peter J. https://hdl.handle.net/2149/2116 2015-03-12T21:03:33Z 2009-06-05T16:29:57Z

A Canadian E-lection 2008? New Media and Political Competition Smith, Jay; Chen, Peter J. The results of the research are an informative study of the specific use of new media in the Canadian national election of 2008 and provide comparative data for other national and provincial studies. This election may prove to be a transitional year for the use of new media in Canadian federal election campaigns as, with the exception of the Greens, the major nation wide parties - Conservatives, Liberals, and New Democratic Party - viewed and incorporated new media as an integrated part of their overall campaign strategy. Fundraising online proved to be a very important part of the process. The use of new media reflected a structural bias with those parties having more resources utilizing them more extensively. Analysis of the data is ongoing and Drs. Jay Smith and Peter J. Chen will presenting their findings at conferences in late May and November 2009.

2009-06-05T16:29:57Z