ECTS credits ECTS credits: 6
ECTS Hours Rules/Memories Hours of tutorials: 3 Expository Class: 24 Interactive Classroom: 24 Total: 51
Use languages Spanish, Galician
Type: Ordinary Degree Subject RD 1393/2007 - 822/2021
Departments: Electronics and Computing
Areas: Computer Science and Artificial Intelligence
Center Higher Polytechnic Engineering School
Call: Second Semester
Teaching: With teaching
Enrolment: Enrollable
The student who has successfully completed the course will be able to:
- Know the basic techniques for natural language processing and generation.
- Know the basic methodologies and techniques for the design, implementation and validation of an interactive conversational system.
- Know the technologies available for the implementation of conversational agents.
- Apply design techniques for natural language processing and generation.
- Apply the available technologies for the implementation of conversational agents.
- Apply the methodologies available for the evaluation of conversational agents.
- Be able to design, implement and validate natural language processing and generation systems in the context of robotic dialog systems.
- To be able to design a basic conversational agent and integrate it into a robotic system.
- To be able to use the main technologies available for the implementation of conversational agents.
THEORY TOPICS
Block 1: Introduction to Conversational Systems (4 hours)
• Adaptive interactive systems
• Language-based interaction
• Gestural or symbolic interaction
Block 2: Conversational Agent Technologies and Design (20 hours)
• Natural language processing and generation technologies
• Design of interactive conversational systems
• Main technologies for implementing conversational agents
• Evaluation methodologies and frameworks
• Multimodal and multi-device interaction
LABORATORY/COMPUTER PRACTICALS (20 hours)
• Practice 1: Design of a basic dialogue system (4h)
• Practice 2: Implementation of a chatbot using modern frameworks (16h): Dialogflow, LangChain, Rasa, AWS
SEMINARS (4 hours)
• Seminar 1: Comparative evaluation of conversational agents (e.g., PARADISE)
INDIVIDUAL TUTORING (3 hours):
• Sessions for guidance, answering questions, and following up on practical projects
Non-classroom work: 99 hours, spread out continuously throughout the semester, for the theoretical and practical parts of the course.
Basic bibliography:
• McTear, M. (2020). Conversational AI: Dialogue Systems, Conversational Agents, and Chatbots. Morgan & Claypool.
• McTear, M., Callejas, Z. & Griol, D. (2016). The Conversational Interface. Springer.
Complementary bibliography:
• Janarthanam, S. (2017). Hands-on Chatbots and Conversational UI Development. Packt.
• Jurafsky, D. & Martin, J. H. (2021). Speech and Language Processing, Chapter 24. https://web.stanford.edu/~jurafsky/slp3/24.pdf
Knowledge:
Con90. Know the basic techniques for natural language processing and generation.
Con91. Know the basic methodologies and techniques for the design, implementation and validation of an interactive conversational system.
Con92. Know the technologies available for the implementation of conversational agents.
Skills:
H/D94. Apply design techniques for natural language processing and generation.
H/D95. Apply available technologies for the implementation of conversational agents.
H/D96. Apply available methodologies for the evaluation of conversational agents.
Competency:
Comp15. Use and implement computational learning methods in the analysis of sensory data and for decision making in robotic systems.
Comp21. Ability to design robots and intelligent systems oriented to interaction with people, and adapted to domestic and urban environments.
Lectures: 14 hours in class
Maxistrais classes with audiovisual support and ICTs.
Interactive activities, individual or group problems and debates.
Use of cooperative learning techniques such as “puzzles.”
Virtual classroom as a space for materials, communication, and support.
Seminars: 4 hours in class
Individual or group work with presentation and discussion of results.
Laboratory practice: 16 classroom hours
Practical development in the laboratory or computer room.
Small group tutorials: 3 hours
Resolution of doubts and guidance on projects.
Final exam: 25%
• Compulsory activity. Minimum pass mark: 5 out of 10.
• A mark of 5 must be obtained in the exam in order to count towards the continuous assessment mark.
Practical work: 50%
• Compulsory attendance. Assessment based on a report and active participation.
• Minimum mark: 5 out of 10 to count towards the final mark.
Seminars: 15%
• Minimum attendance at 2/3 of the sessions. Assessment based on participation and/or submission/presentation of a report.
Continuous assessment: 10%
• Active participation in classes and related activities.
Second chance and repeat students:
• The grades for the activities assessed during the course will be maintained.
• The final exam must be repeated.
Students exempt from attendance:
Students who have been granted exemption from attendance by the Degree Committee in accordance with the provisions of the
Class Attendance Regulations must bear in mind that in order to pass the subject, they must complete the compulsory practical work and optional seminars. If these are not completed, the final exam will account for 75% of the final grade.
In cases of fraudulent completion of exercises or tests, the provisions of the “Regulations on the assessment of academic performance of students and review of qualifications” will apply.
Classroom work:
• Lectures: 24 hours
• Practical work: 20 hours
• Seminars: 4 hours
• Tutorials: 3 hours
• Exam: 1 hour
• Total classroom work: 52 hours
Non-classroom work: 47 hours
Total workload: 99 hours
None
None
Sonia Maria Valladares Rodriguez
Coordinador/a- Department
- Electronics and Computing
- Area
- Computer Science and Artificial Intelligence
- sonia.valladares [at] usc.es
- Category
- PROFESOR/A PERMANENTE LABORAL