Natural Language Processing 2

Course manual 2017/2018

Course content

The amount of language data that is available to us electronically is increasing with the day. With this eminent increase, a question arises as to the possibility of inducing latent structure in this data that can be useful for further tasks such as machine translation. The different kinds of latent structure that is possible depends on the data and the task, and will usually demand suitable statistical models and learners. The course will teach methods for inducing a variety of latent structure for tasks such as language modeling, machine translation and adaptation across domains. The course covers the following topics

• Statistical Machine Translation and Paraphrasing
• Domain adaptation
• Statistical models of lexical semantics
• Latent, hierarchical or linguistic structure in natural language data 

Study materials

Literature

• 'Statistical Machine Translation'. Philipp Koehn. Cambridge University Press.

Other

• Articles will be provided.

Objectives

In this advanced course in NLP the student will 

• Acquire knowledge of advanced NLP techniques, particularly in statistical machine translation
• Acquire awareness of ongoing research and challenges in NLP in general
• Practice reading and presenting scientific articles in NLP
• Develop, program and report basic solutions to example problems within multiple small projects
  

Teaching methods

• Lecture
• Seminar
• Working independently on e.g. a project or thesis
• Presentation/symposium

Lectures by lecturers; Preparation and presentation of articles by students; practical training and project work

Learning activities

Attendance

The programme does not have requirements concerning attendance (OER-B).

Assessment

Assignments

Onderstaande opdrachten komen aan bod in deze cursus:

•    Naam opdracht 1 : beschrijving 2
•    Naam opdracht 2 : beschrijving 1
•    ....

Fraud and plagiarism

The 'Regulations governing fraud and plagiarism for UvA students' applies to this course. This will be monitored carefully. Upon suspicion of fraud or plagiarism the Examinations Board of the programme will be informed. For the 'Regulations governing fraud and plagiarism for UvA students' see: www.uva.nl/plagiarism

Course structure

Timetable

The schedule for this course is published on DataNose.

Additional information

Recommended prior knowledge: Natural Language Processing 1; Machine Learning: Pattern Recognition.

Contact information

Coordinator

• prof. dr. Khalil Sima'an

Staff

• W. Ferreira Aziz
• Miguel Rios
• Marion Weller