Loading Events

« All Events

Open Class Observation – Prof. Christophe Coupé

November 5 @ 10:30 am - 12:20 pm HKT

Details

Date: 5 November 2024 (Tuesday)
Time: 10:30am – 12:20pm (HK time)
Venue: Learning Lab (RRS 321, Run Run Shaw Building, Main Campus, HKU)
Speaker: Prof. Christophe Coupé, Assistant Professor, Faculty of Arts, HKU


Class Topic

Harnessing the power of Large Language Models

Brief introduction to the course

Natural Language Processing (NLP) addresses how machines analyze, produce and understand natural language. The field lies at the crossroads of linguistics and computer science and encompasses a wide range of techniques including automatic speech recognition, text mining, machine translation, and speech synthesis. The goal of this course is to provide a thorough introduction to basic methods and issues of NLP, with a specific focus on text mining. Flipped classroom will be used for most of the lectures to allow more learning activities and hands-on practice in class. No previous experience in programming is required for this course, and students will experiment with various dedicated software and interfaces.

Number of seats for observers/visitors

8 seats per session (Enrolment will be on a first-come, first-served basis.)

Purpose of this Session

Given the flipped-classroom format, the session will be for the most part dedicated to hands-on activities letting the students experiment with prompting techniques, model assessment, and the construction of a chatbot.
This lecture centers on prompt engineering (i.e., how to query a large language model), from basic strategies to more advanced ones (including retrieval-augmented generation). It also discusses how to assess the performances of large language models, and the economic, social and ethical issues surrounding their use.
Intended Learning Outcomes:

  1. Describe and compare various strategies to write simple or more advanced prompts
  2. Create your own effective prompts to achieve a given task
  3. Describe and apply methods and frameworks to assess the performances of LLM
  4. Reflect on the creation of complex AI structures and tools, with memory and external sources of knowledge
  5. Reflect on the social and ethical issues raised by foundation models

Biography of the Teacher

Prof. Christophe Coupé is an assistant professor in the Department of Linguistics at the University of Hong Kong and was previously a CNRS researcher in France. With an educational background in computer science and cognitive science, he conducts research on language and communication across linguistics, bioacoustics, psychology, and phenomenology.

Christophe is committed to passing his enthusiasm for cross-disciplinary work on to students, and to developing innovative educative practices. He was awarded an Outstanding Teacher Award by the University of Hong Kong in 2021, and strives for a sensible, human-centered adoption of generative AI in education. He is currently the director of the Bachelor of Arts in Humanities and Digital Technologies at HKU.

Details

Date:
November 5
Time:
10:30 am - 12:20 pm HKT
Copyright © 2024 TALIC. All Rights Reserved.