Conversational systems allow users to interact with machines through spoken or written language. Examples include smart speakers, voice assistants, chatbots, and social robots. This involves the use of technologies such as natural language processing, speech technology, and multi-modal interfaces. The course will give an in-depth understanding of conversational systems, from both a theoretical and practical perspective, through lectures, exercises and a project. Both classical rule-based approaches, as well as more recent deep learning approaches will be covered.
Information for research students about course offerings
Period 2, together with second cycle course DT2151
Choose semester and course offering
Choose semester and course offering to see current information and more about the course, such as course syllabus, study period, and application information.
Content and learning outcomes
The course consists of five lectures, three laboratory sessions, and a final project done individually or in groups. The project is presented at a project pitch and during a final seminar. In the laboratory sessions, we will use different platforms for building conversational systems (including graphical tools, social robotics and deep learning).
The lectures will cover the following topics:
- Introduction to conversational systems. Historical perspective. Overview of speech and language technlogy components.
- Theories of conversation. Semantics and pragmatics of dialog. Psycholinguistic perspectives.
- Natural language understanding. Grammar-based and data-driven approaches. Visual language grounding.
- Dialog management. Chat- and task-oriented dialog. Rule-based and neural models. Reinforcement learning.
- Multi-modal conversation, Social signals and Social robotics.
Intended learning outcomes
After the course, the student should be able to:
- Describe different state-of-the-art models for conversational systems, their weaknesses and strengths, and apply a suitable model depending on the application
- Implement a conversational system using rule-based frameworks and deep learning
- Identify research topics related to conversational systems, find relevant litterature, develop a research plan, and execute the research project
5 lectures, 3 labs, 2 project seminars
Literature and preparations
Doctoral students from EECS
Some knowledge of Machine learning is recommended (e.g. DD2421, DD2434, EN2202)
Some programming knowledge is required.
Compilation with relevant articles.
Examination and completion
If the course is discontinued, students may request to be examined during the following two academic years.
- EXA1 - Written examination, 7.5 credits, grading scale: P, F
Based on recommendation from KTH’s coordinator for disabilities, the examiner will decide how to adapt an examination for students with documented disability.
The examiner may apply another examination format when re-examining individual students.
Other requirements for final grade
All lectures, excercises and project seminar attended. Approved project report.
Opportunity to complete the requirements via supplementary examination
Opportunity to raise an approved grade via renewed examination
- All members of a group are responsible for the group's work.
- In any assessment, every student shall honestly disclose any help received and sources used.
- In an oral assessment, every student shall be able to present and answer questions about the entire assignment and solution.
Further information about the course can be found on the Course web at the link below. Information on the Course web will later be moved to this site.Course web FDT3151