Postgraduate Course: Topics in Natural Language Processing (INFR11113)
|School||School of Informatics
||College||College of Science and Engineering
|Credit level (Normal year taken)||SCQF Level 11 (Year 4 Undergraduate)
||Availability||Available to all students
|Summary||The aim of this course is to expose students to a variety of advanced topics in computational linguistics and natural language processing (NLP). Most of these topics will be described through the introduction of the basic theory that underlies these topics. There is an important theoretical component in NLP and CL that students are not being normally exposed to - the goal of the class is to increase the exposure to these topics. The course will focus especially on learning-theoretic and formal language theoretic issues in NLP. Students will be expected to present and critique classic and recent research results articles from the NLP literature, chosen from a list provided by the instructor.
The syllabus consists of two parts. In the first part, the instructor will provide a basic overview of topics that will be covered in the class, and some of the fundamental ideas in NLP. She or he will also discuss methodologies to read and analyse scientific papers on topics in NLP. In the second part, students will give the presentations and brief paper responses. The papers will be chosen from a list provided by the instructor (or suggested by the students, subject to the instructor┐s approval).
Topics covered by the instructor will include:
*A refresher in probability and information theory.
*Basic introduction to formal language theoretic tools used in NLP such as finite state transducers, advanced grammar topics.
*Introduction and overview of advanced statistical modelling techniques in NLP such as structured prediction, log-linear models.
*Information about reading and analysing research papers in NLP.
Relevant QAA Computing Curriculum Sections:
Artificial intelligence; Natural language computing
Information for Visiting Students
Course Delivery Information
|Academic year 2014/15, Available to all students (SV1)
|Learning and Teaching activities (Further Info)
Lecture Hours 15,
Feedback/Feedforward Hours 2,
Summative Assessment Hours 3,
Programme Level Learning and Teaching Hours 2,
Directed Learning and Independent Learning Hours
|Assessment (Further Info)
|Additional Information (Assessment)
||The assessment for this course consists of the following components:
*Oral presentation (20%): students (in small groups perhaps, depending on enrollment) will choose 2┐3 papers on a speci┐c topic (topics can be repeated) from a list provided by the instructor. Freedom will be given to students to choose a topic, if they show they are able to grasp the material and present it well.
*Brief paper responses (25%): Students will choose 2┐3 additional papers (on the same topic as their presentation), and will write a short summary on the topic and these papers for all other students to read (1 page). This summary will also suggest ideas to further expand the research presented in these papers, or questions that students had during their readings.
*Essay (55%): This is the ┐nal piece of assessment, in which students could choose a potentially new topic (or stick to the old topic of their presentation and the brief paper responses), and create a literature review of this topic, or an essay based for this topic.
If delivered in semester 1, this course will have an option for semester 1 only visiting undergraduate students, providing assessment prior to the end of the calendar year.
|No Exam Information
| After completing this course successfully, students will be able to:
*Demonstrate understanding of classic and current articles on statistical modelling of language. Special emphasis on fundamental models such as probabilistic grammars, learning theory for structured prediction and linguistic structure prediction, formal language theory and latent-variable modelling.
*Demonstrate understanding of the relationship between NLP and machine learning and statistics, by being able to critically assess the validity and soundness of the techniques used in NLP papers.
*Synthesise information from the NLP literature on a specific topic, and create a coherent summary.
*Following the above, identifying shortcomings in the literature and suggest solutions for these shortcomings, or ideas for further exploration.
|There is no main textbook for the course. Readings will be chosen from classic and current research papers in NLP, learning theory and formal language theory.|
|Course organiser||Dr Shay Cohen
|Course secretary||Miss Claire Edminson
Tel: (0131 6)51 4164
© Copyright 2014 The University of Edinburgh - 12 January 2015 4:12 am