Language technology resources

The course can be part of the following programmes: 1) Master in Language Technology (H2LTG), 2) Master in Language Technology (H2MLT) and 3) Applied Data Science Master's Programme (N2ADS).

Admission to the course requires having passed the following courses:

• LT2001 Introduction to programming 7.5 credits
• LT2002 Introduction to formal linguistics 7.5 credits
• LT2003 Natural language processing, 15 credits (or LT2123 Basic skills for language technology, 7.5 credits together with LT2124 Themes in NLP and language technology, 7.5 credits)
• LT2212 Statistical methods 7.5 credits (or LT2222 Machine learning for statistical NLP: introduction 7.5 credits)

or equivalent language technology competence.

English 6 or equivalent is also required.

The course gives advanced knowledge in algorithmic resources for language technology (or language technology tools) such as algorithms for word sense and disambiguation, learning algorithms and sentence level classification. Language technology resources, such as corpora, dictionary, syntax, text and language models are covered with relevant algorithms. The course is thematic organised in the following main parts:

• Algorithmic resources for language technology
• Advanced language technology problems in text-based language technology
• Use of resources in language technology research and development

On successful completion of the course the student will be able to:

Knowledge and understanding

• describe which types of algorithms are used in language technology research and development and choose suitable algorithms for a given problem,
• describe challenges and open problems in advanced text-based language technology problems,
• describe existing language technology and data structure algorithms and their possible application on above mentioned problems,
• describe existing resources and algorithms and understand how these can be merged to tackle new problems and purposes,
• describe evaluation models with their limitations, pros and cons.

Competence and skills

• choose, develop or adapt algorithms, tools or resources for a given purpose and domain,
• use at least an existing implementation of algorithm or a tool or a resource,
• choose an evaluation model based on a given problem and purpose,
• perform work according to a predetermined schedule,

Judgement and approach

• Assess if a specific algorithm, tool or resource can be used for a given purpose and domain,
• interpret evaluation results in relation to a given purpose and domain,
• justify your choice and need of a specific resource for a given purpose and domain.

The teaching is given in the form of lectures, laboratories, assignments, seminars, exercises, individual work, or group work.

Two teaching sessions a week during the first four weeks, thereafter individual work with the project. During the project work it is possible to meet the lecturers and discuss with them. Submission and project presentation at the end of the course.

Language of instruction: English

The course is assessed through a course paper and an oral presentation. Compulsory attendance can apply for some course elements.

The grading teacher may request completion of examined student achievements.

If a student who has been failed twice for the same examination element wishes to change examiner before the next examination session, such a request is to be granted unless there are specific reasons to the contrary (Chapter 6 Section 22 HF).

If a student has received a certificate of disability study support from the University of Gothenburg with a recommendation of adapted examination and/or adapted forms of assessment, an examiner may decide, if this is consistent with the course’s intended learning outcomes and provided that no unreasonable resources would be needed, to grant the student adapted examination and/or adapted forms of assessment.

If a course has been discontinued or undergone major changes, the student must be offered at least two examination sessions in addition to ordinary examination sessions. These sessions are to be spread over a period of at least one year but no more than two years after the course has been discontinued/changed. The same applies to placement and internship (VFU) except that this is restricted to only one further examination session.

If a student has been notified that they fulfil the requirements for being a student at Riksidrottsuniversitetet (RIU student), to combine elite sports activities with studies, the examiner is entitled to decide on adaptation of examinations if this is done in accordance with the Local rules regarding RIU students at the University of Gothenburg.

The grading scale comprises: Pass with Distinction (VG), Pass (G) and Fail (U).

For a passing grade on the course, as passing grade must be acheived on the course paper and the oral presentation. For a pass-with-distinction grade, a pass with distinction must be achieved on the course paper, and as pass on the oral presentation.

Students participating in, or having completed the course, are given the chance to anonymously submit their opinions of and suggestions for the course in a course evaluation. A short version of the course evaluation, together with the reflections of the course coordinator, is published and made available to the students within a reasonable time after the course has finished. The next time the course will be given, a short version of the course evaluation will be presented together with any measures implemented.

The course requires access to a computer (or similar) with internet access.

The course may not be included in a degree together with the course LT2304.