Please use this identifier to cite or link to this item:
|Title: ||機率式建模技術與自然語言的標記、認知和教學 (I)|
|Other Titles: ||Probability-Based Techniques for Model Construction and Tagging, Cogintion, and Education of Natural Languages|
|Issue Date: ||2012-11-12 11:03:02 (UTC+8)|
Can we apply computational methods to help the study of human mind, after researchers have shown that computers are helpful for bioinformatics and medical informatics? In fact, applying computational methods to assist us to learn about human mind is not a wild imagination, and had been proposed a long while ago. It is just that this research topic has been receiving more and more attention in recent years, partially due to the tremendous improvement in computational powers of modern computers and partially due to the success achieved in bioinformatics. In the past few years, we have applied probabilistic methods and other machine learning techniques to study the learning process of how students learn complex concepts. We assumed the availability of students’ responses to test items, and attempted to find the best model of learning process based on students’ item responses. We have also applied techniques for natural language processing (NLP) to process judicial documents in Chinese, and have applied NLP techniques to facilitate the preparation of test items for learners and teachers for English and Chinese. At the time of writing, we have implemented usable prototypes for legal informatics and for computer-assisted item writing. Based on the research experience that we gathered in the past years and based on our observation about the trend of research and about the needs in realistic applications, we propose this research plan which attempts to integrate the research work in artificial intelligence and cognitive science. We hope and believe that we can contribute not only to computer and cognitive sciences but also to their applications in language learning. We would like to achieve multiple goals in this three-year project. For the research on computational methods, we will extend our current study on Bayesian networks, probabilistic reasoning, and other relevant machine learning methods. We will also integrate as many machine learning techniques, including those that we will and have developed, in an environment so that people can build models of interest in a more efficient way. For the research on cognitive science, we will employ the eye tracker, which will be offered by the laboratory led by Professor Tsai of National Chengchi University, to study how human subjects of different backgrounds process Chinese text with their eyes. The understanding of how human subjects process text is a very interesting topic itself; it also sheds light on the rationale of the techniques discussed in computational linguistics and natural language processing. The main participants of this research project include Chao-Lin Liu of the Department of Computer Science, Professor Jie-Li Tsai of the Department of Psychology of the National Chengchi University, and Professor Zhao-Ming Gao of the Department of Foreign Languages and Literatures of the National Taiwan University. As a team, we have covered the domain knowledge in computer science, cognitive science, and computational linguistics. We believe that we are prepared to execute this research work in a good manner, and produce appropriate results in the years to come.
In the first half of this project, we continued what we have been doing in the past few years. We worked on the construction of student models using a probability-based approach, and continued to publish research papers. We have also applied the techniques for natural language processing to computer assisted language learning. In the past several months, we have focused on research issues regarding incorrect Chinese words and regarding the reconstruction of scrambled sentences. In addition, in order to offer better assistance in learning languages, we worked with Professor Tsai of the Department of Psychology (National Chengchi University) to study how native speakers of Chinese move their eyes while they read Chinese. Overall, we published 11 papers in the past 10 months. Two of them are journal articles, three are international conference papers, and six are domestic conference papers. Two other submitted papers are still under review.
|Data Type: ||report|
|Appears in Collections:||[資訊科學系] 國科會研究計畫|
Files in This Item:
All items in 政大典藏 are protected by copyright, with all rights reserved.