數據科學 理學碩士 計算語言學專業

與FAH合作

所有課程都是必修課：

AHGC7315 語言與語言學

3 學分

This course introduces key concepts and approaches to the study of language and linguistics. It provides an overview, with basic terminology, of the major subfields of linguistics, investigating the nature, history, and structure of language and how language relates to the mind, society, and education. It provides the basis of investigation in subsequent courses in the Computational Linguistics program. Students are encouraged to reflect on their own language experience and apply the theories covered in the course to their own linguistic context.

AHGC7398 項目報告

6 學分

A “Project Report” addresses a particular issue in a specific context and may incorporate elements of data collection, data processing, data analysis and data solution. Students demonstrate their ability to reflectively examine a particular context, identify and define an issue in that context, access, summarize, and synthesize current literature relevant to the issue, and develop a justified approach to address that issue. Various linguistics and applied linguistics related topics are acceptable.

從以下選項中選擇3門必修課：

CISC7021 應用自然語言處理

3 學分

This course covers both the fundamental and advanced topics in Natural Language Processing(NLP), which deals with the application of computational models to text data. In this course, the core tasks in natural language processing will be examined, including minimum edit distance, language modelling, Nävie Bayes, Maximum Entropy, text classification, sequence labelling, POS tagging, syntax parsing and computational lexical semantics. Modern NLP applications will be explored such as information retrieval, and statistical machine translation. Students will learn how to formulate and investigate research questions on related topics.

ENGL7022 語料庫語言學

3 學分

This course will introduce students to the methods and issues involved in corpus linguistics. It aims to demonstrate the practical use of online corpora to explore questions asked by scholars of language, and to address some of the central issues raised by corpus design and analysis. Students will familiarize themselves with the research use of online corpora and the construction and analysis of original corpora using freeware concordance tools. At the same time, the classes will consider various aspects of language analysis concerning lexis and grammar, and questions of language variation and change.

AHGC7039 計算機輔助翻譯

3 學分

This course reviews state-of-the-art technology in translation. In addition to Translation Memory, which allows users to leverage existing data, deep learning technologies have allowed Machine Translation to achieve fully automatic translations for some genres of writing. The course will include an extensive practical component using these technologies in addition to exploring assessment of Machine Translation quality, emerging possibilities and issues. In addition to these, the use of the World Wide Web, Web-based translation aids and other applications for producing rapid, localized and high-quality translation are discussed.

AHGC7303 語言應用評估

3 學分

This course is an introduction to the field of language assessment. Topics covered in the course include purpose and context of testing, assessing skills and components of language ability, content analysis of test instruments, and statistical analysis of test performance data, and fairness and justice in language assessment.

CHLL7101 漢語語言學研究方法

3 學分

This course aims to systematically introduce the research ideas and methods of linguistics and some important linguistic theories, and guide students to use scientific tools and methods to conduct systematic synchronic or diachronic research on Chinese. The course includes general and special methods of linguistic research, instrumental concepts frequently used in linguistic research, analytical techniques adopted by various linguistic schools, and linguistic theories established by domestic scholars.

AHGC7308 應用語言學專題 I

3 學分

This course is designed to offer visiting scholars, existing or future staff, the opportunity to offer courses in their particular area of specialization. The topic and content of the courses will vary from year to year depending on the availability of expert staff. Examples of specialized topics that may be offered include: data-driven learning, computer-adaptive language testing, automated scoring, corpus-based EAP (English for academic purposes), etc.

PHIL7101 語義學專題

3 學分

This course is an introduction to the formal analysis of natural language semantics as situated within the larger domain of linguistics. Students will be introduced to the main goals and methods of formal semantics, with a special focus on some of its core empirical results, and to some mathematical concepts underlying semantic interpretation systems (sets, relations, functions). Topics include: predication, the semantics of quantificational determiners, indexicals, semantic binding, tense, and modality.