Foundations – Basic Linguistic Concepts and Computational Methods/Resources (5 Half-Days)
Basic Linguistic Concepts and Computational Methods/Resources: This course presents two sides of the same coin. One part of the course is geared more towards natural language engineers, the other part towards linguists. Linguists are in possession of a great deal of knowledge about particular languages and typological patterns that have been observed across languages. However, leveraging and organizing this knowledge so that it is immediately useful for computational purposes is often difficult for linguists because of a lack of basic knowledge about computational approaches and resources. On the other hand, natural language engineers possess a great deal of knowledge about computational methods and applications, but tend to have difficulty leveraging these towards developing natural language processing applications because of a lack of basic knowledge about language structure. This course therefore seeks to convey basics of language structure that is relevant for computational efforts and to provide information on basic resources and methods within natural language processing. It addresses both language technologists (natural language engineers) and linguists in providing a basic understanding of the required knowledge to build successful natural language processing applications.
Grammar Engineering for South Asian Languages (5 Half-Days)
This course teaches participants how to build rule-based computational grammars using powerful state-of-the-art grammar development software that includes interfacing with a finite-state morphological analyzer, the integration of large scale lexica and statistically-based disambiguation methods. The first half of the course introduces participants to basic grammar writing techniques based on the grammar development platform XLE, which assumes the syntactic framework of Lexical-Functional Grammar (LFG; Bresnan and Kaplan 1982, Butt et al. 1999, Dalrymple 2001, Butt et al. 2006). The second half of the course focuses on the specific needs of South Asian languages and presents existing grammar engineering solutions that can address these needs (free word order, complex morphology, complex predication, pronoun ommission, etc.)
Argumentation and Computation (5 Half-Days)
This course offers an interdisciplinary view on argumentation and its computation, spanning the fiels of philosophy, linguistics, computer science and artificial intelligence. The first half of the course introduces students to basic concepts in argumentation theory and provides hands-on experience with state-of-the-art frameworks, in particular Inference Anchoring Theory (Budzynska et al. 2016), that facilitate the identification and extraction of argumentative structures in real data. The second half of the course focuses on argument mining and gives an overview of the techniques, methodologies and tools for processing argumentation in natural language texts, as well as of the solved issues and open challenges the new research area of argument mining is facing.
Computational Corpus Linguistics (5 Half-Days)
This course introduces the methodological and computational foundations of corpus-based research, with applications in linguistics, digital humanities and language processing. On a theoretical level, the course discusses the principle of corpus design, statistical techniques for the quantitative analysis of corpus data, and natural language processing techniques for the automatic annotation and indexing of large corpora. On a practical level, participants will learn how to combine available off-the-shelf tools with command-line processing and Python/R scripts in order to collect, annotate and analyze their own corpora. Students will have the opportunity to work on their own research projects with support from the course instructor.
Deep Learning for NLP (5 Half-Days)
In this lecture series, we cover the basics of machine learning, neural networks and deep neural networks. We look at several deep neural network architectures from the perspective of applying them to various classification tasks, such as sequence prediction and generation. Each concept is backed and presented in a framework of an objective, loss and optimization lifecycle. We will also learn to peek into these neuron systems and analyze what they learn about the intricacies of a language like morphology and syntax, without ever explicitly seeing these details in the training data. Lastly, we cover several practical aspects of how to design a model given the size of the data, nature of the task, and how to debug a trained model to improve its performance.
Workshops on language and teaching (4 Days)
This is a series of workshops on language acquisition, Bilingualism, Language policy and language acquisition planning, and Second language teaching. Click here for more details about each workshop.
Subscribe to the calendar here to get updates.
| || || |
|Venue: University of Moratuwa | 11 – 15 March 2019|
|11-15 March 2019 (Monday-Friday)||Morning||Foundations – Basic Linguistic Concepts and Computational Methods/Resources||Prof. Miriam Butt|
Mr. Tharanga Weerasooriya
|Evening||Option 1 – Grammar Engineering for South Asian Languages||Prof. Miriam Butt |
|Evening||Option 2 – Argumentation and Computation||Dr. Annett Hautli-Janisz|
| 16 March 2019 |
|Venue: University of Moratuwa | 17 – 21 March 2019|
| 17 – 21 March 2019 |
(Sunday – Thursday)
|Morning||Deep Learning for NLP||Dr. Hassan Sajjad and Fahim Dalvi|
|Evening||Computational Corpus Linguistics||Prof. Dr. Stefan Evert|
|Venue: University of Sri Jayewardenepura | 18 – 21 March 2019|
| 18 – 21 March 2019 |
(Monday – Thursday)
|Whole Day (6 hours)||Workshops on Language and Teaching||Prof. Tanja Kupisch and |
Ms. P. Nagasundaram
| 22 – 23 March 2019
(Friday – Saturday)
| Symposium on National Languages Processing |