NTU Computational Linguistics Lab Courses
This page lists courses relevant to Computational Linguistics from the Division of Linguistics and Multilingual Studies (plus some courses from other places in the Unviersity), Nanyang Technological University, Singapore. Not all courses are offered in all years.
|AY16/17 Sem 1: (this semester)|
Semantics and Pragmatics (LMS core course)
A general introduction to semantics and pragmatics, illustrated with humorous video clips.
Language and the Computer (LMS)
Traditionally linguistic analysis was done largely by hand, but computer-based methods and tools are becoming increasingly widely used in contemporary research. This course provides an introduction to skills and resources that can assist the linguist in performing fast, flexible and accurate quantitative analyses. Students will learn a scripting language (Python) and use it and the Natural Language Tool Kit (NLTK) to analyse linguistic phenomena. No previous programming experience is required: we will teach you the basics of programming, with an emphasis on useful techniques for processing languages.
Language, Technology and the Internet (LMS)
Like so many other aspects of life, language communicate has been revolutionised by the introduction of the Internet. This course explores how the structure and use of English have been shaped by the popularity of new modes of communication made available by the Internet: SMS, e-mail, chatrooms, Internet Relay Chat, Usenet newsgroups, World Wide Web pages, and virtual worlds. The implications of these changes for our thinking and understanding of language will also be discussed.
This course introduces computer modeling for the social sciences, with a focus on linguistic phenomena. It will provide an overview of:
- The rationale for modeling: How modeling can be applied to various linguistic levels of analysis, from reading to understanding meaning, to collective linguistic behavior.
- We will cover principles of distributional models (n-gram; connectionist, vector spaces); structured models; graph-based models; agent-based models.
- What type of model is best suited for what phenomenon.
- The strengths and weaknesses of different models.
- How to evaluate models.
Corpus Linguistics (LMS)
This course is an introduction to the fast growing field of corpus linguistics. It aims to familiarise students with key concepts and common methods used in the construction of language corpora, as well as tools that have been developed for searching and using major corpora such as the British National Corpus. Students will be given hands-on experience in pre-editing, annotating, and searching corpora. Criteria and methods used for evaluating corpora and analytical tools will also be discussed.
Machine Translation (LMS)
This course introduces students to the field of Machine Translation (MT). It will begin with an overview of the history of MT, from early attempts to contemporary approaches including rule-based MT, statistics-based MT and knowledge-based MT. Key concepts relating to representation and processing, dictionary building and annotation, and principles and components in the construction of MT engines will be illustrated and discussed. Major MT resources, particularly on-line ones, will also be reviewed.
Grammar Engineering (LMS)
The course gives an introduction to the Linguistics Knowledge Building (LKB) system, and how to develop a grammar with the help of the Matrix Grammar. On the one hand, the course will focus on technical aspects, like the installation of the tools needed for the grammar development, how to run the tools, and how to do the actual implementation. On the other hand, the course will focus on certain grammatical phenomena, like modification, agreement, valence, and long-distance dependencies, as well as the semantic representation used: Minimal Recursion Semantics (MRS).
Chinese Lexicology (Chinese)
The course provides a comprehensive knowledge for students to understand lexicon construction in Chinese and its connection with syntactic and phonological environment, issues in new word formation since ancient times, differentiation of synonyms and given that word sense is a function of its parts, students will also be guided to examine the semantics in Chinese lexicons as well as variation across time and geographical boundaries.
Natural Language Processing (CSC)
Use models: Document search, document clustering, automatic topic hierarchy generation, document classification. Performance evaluation: Precision versus recall, experiment design. Vector Space Model. Latent Semantic Indexing. Features: Word stemming, case folding, stop words, thesauri, N-grams. Relevance ranking: Cosine, IDF, link-based scoring. Implementation issues: Inverted indexes, dictionaries, parsing, compression.
Information Retrieval (CSC)
Overview: introduction, definitions, fundamental concepts, applications. Parsing methods:deterministic and stochastic grammars. Statistical NLP: parsing, term extraction, word sense disambiguation; Information extraction: rule-based approach, learning-based approach. Ontology: WordNet, XML, semantic web. Machine translation.
Computational Lexical Semantics
In this course students will become familiar with how to represent word meanings computationally and a variety of methods for automatically determining the meaning of words. These include dictionary based methods, such as LESK, graph based methods such a UKB, supervised methods such as sequence classification and best paths as well as vector space methods. We will finish with a discussion of how to provide feedback from word sense disambiguation to meaning representation. The course includes a strong computational component, students will experiment with implementing systems and algorithms, in addition to learning about them. By the end of this course, graduate students will have an advance knowledge of current computational approaches to lexical meaning. Students should be able to evaluate lexical resources for coverage and quality as well as to design and implement systems for determining meaning in text.
Grammar Engineering (LMS)
The course gives students the skills to implement a computational grammar of a language. On the one hand, the course will focus on technical aspects, like the installation of the tools needed for the grammar development, how to run the tools, and how to do the actual implementation. On the other hand, the course will focus on certain grammatical phenomena, like modification, agreement, valence, and long-distance dependencies, as well as formal syntactic and semantic representations (Head-driven Phrase Structure Grammar and Minimal Recursion Semantics) The students will develop their own grammars, which can be used for both parsing and generation. Parallel to the development of the grammar, a test suite will be made in order to test the accuracy of the grammar. At the end of the course, it will be demonstrated how the grammars can be used in Machine Translation.
- HG7030 Natural Language Processing for Linguists
Computer-based methods and tools are becoming increasingly more widely used in contemporary research. This course provides an introduction to the key instruments and resources available on the personal computer that can assist the linguist in performing fast, flexible and accurate quantitative analyses. Students will learn a scripting language (Python) and use it and the Natural Language Tool Kit (NLTK) to analyse linguistic phenomena. We will show examples of both symbolic and statistical processing.
- HG7032 Topics in Corpus Linguistics
This course aims to provide graduate students with key concepts and common methods used in the construction of language corpora. On completion of this module, graduate students should be able to understand the uses of text corpora in language research and be able to manipulate program to extract data from a corpus. Students should be able to design and build a corpus for specific task.
(Conflicts with HG2052)
In this elective you will get a chance to see how technology affects how we use language (from the effects of encoding to the rise of chatspeak), and also how technology has enabled us to study and process language in new ways. Students will gain understanding of the problems of representing, transmitting and transforming language electronically. Specific topics will include automatic parsing and generation of language, text mining (extracting knowledge from text) and machine translation.
Detecting Meaning with Sherlock Holmes
(Conflicts with HG2002)
In this elective we will detect how language conveys meaning, using examples taken from Sir Arthur Conan Doyle's Sherlock Holmes stories. The course considers meaning from the smallest levels of words and morphemes, up through sentences to the stories as a whole. Finally, we consider how Sherlock Holmes stories have entered into popular culture, both through translation into other languages and into other media, such as films and TV.
In the first half of the course, we will look at how words convey meanings and how they can be combined to express richer meaning (semantics). We will show that meaning does not only come from the words themselves, but also from our own understanding of them, and that words can convey much more than simple truth-conditional meanings (pragmatics).
In the second half of the course, we will show how the stories (and other works adapted from them) convey meaning to the reader, as well as how the meaning becomes part of our cultural heritage.
|AY15/16 Sem 2:|
|AY15/16 Sem 2: (next semester)|
|AY14/15 Sem 2:|
|AY14/15 Sem 1:|