New Fall 2012 Seminar: LING 506 (Topics in Computational Linguistics) – Discourse Processing, Argumentation, and Social Media
Instructor: Prof. Roxana Girju (Girju@illinois.edu)
Time & location: 9:30am – 10:45am, Tuesday and Thursday, in Foreign Language Bldg., room#1018 or Beckman Institute (to be decided)
This is a seminar on advanced topics in computational linguistics / natural language processing (NLP). An important yet challenging topic in NLP, and Artificial Intelligence, is the automatic detection and processing of discourse structure with application to argumentation and social media. There is a growing need of applications that rely on discourse analysis of different genres. Currently, there are many efforts to detect discourse structure at different levels of granularity and for different purposes. Discourse elements detected include the statement of facts, claims and hypotheses, explanations/justifications, or, in the medical domain, the identification of prescription and treatment guidelines, patient characteristics, and annotation of research data. The challenges derive from the combined requirements of a mapping process (text to a rich representation of relevant entities), representational framework (discourse relations), and reasoning capability (combining inference).
The purpose of this seminar is to expose students to the recent advances in the research on discourse processing and argumentation in social media and other genres through presentations and discussions of papers from the top conferences in NLP and its related areas. One goal of this seminar is to provide an environment for students to become familiar with current discourse representations and models and freely express opinions and criticize the state-of-the-art research work in a group setting.
Lecture presentations and guided discussions based on reading of prepared material (given by the instructor and the students). Case studies and examples will be used to illustrate the practical application of the main concepts, methods, and tools. In order to get the credit for the course, students are expected to participate in the discussions and choose among a midterm project, a research paper, or a survey paper.
The course is open to Linguistics, Computer Science, Computer Engineering, and Library and Information Science students, or to any students with interest and preparation in linguistics or computational linguistics/natural language processing, or artificial intelligence.
Questions should be addressed to the instructor at firstname.lastname@example.org.