Conversational agents: a more assertive form of chatbots
AI-based Conversational Agents (CAs), such as chatbots, are becoming increasingly important in organizations and academic research. Beyond their intuitive, (natural) language-based and fast-accessible interface, CAs provide a scalable and cost-effective platform for organizations supporting employees by retrieving, structuring, and analyzing information to assist work processes. CAs represent a novel class of information systems (IS) characterized by increasing levels of intelligence, autonomy, and personality. In this session we provide you insights from academia on the state of the art of conversational agents as well as best practices from 3 concrete implementations in Flanders.
Practical information:
Georganiseerd door:
Still a challenge for AI: Conversational Agents
Speaker: Prof. Dr. Walter Daelemans, professor at the University of Antwerp.
Professor Daelemans will provide an overview of the types of conversational agents (chatbots, dialogue systems) that are currently being developed and the state of the art in machine learning / deep learning based approaches (based on large language models). He will give an overview of the remaining problems (among others: finding good evaluation methods, portability to new domains and tasks, separating background knowledge from language knowledge, consistency in dialogue management, personalization, controling generation, reducing update time, ...), focus on proposed solutions to those problems, and illustrate them using the vaccinchat.be chatbot he and his team have developed in 2021 to answer questions about vaccination.
CITYBOT - an Intelligent Conversational Agent for the City of Ghent
Speaker : Stephen Lernout, Head of Strategy & Innovation @ Nalantis
Local city authorities have mountains of data, which only continue to grow as decisions are made on a monthly basis. This data overload makes it hard for city employees to quickly find and access the right information. At the same time, citizens have questions and expect quick responses from city personnel regarding topics from garbage disposal to parking and building regulations. This is extremely frustrating for both the city employees and the citizens. Nalantis' proprietary AI system uses natural language understanding to contextually understand City Council decisions in unstructured format (Text, Video and Audio) across multiple languages. The pre-trained NLU software extracts meaning from text through automatic semantic annotation at paragraph and sentence level.
How AI-assisted Question Answering helps Flanders Investment and Trade attract foreign investors
Speakers: Shoera Sels, Project Lead @Radix & Yves Ruland, Project Manager Data Architecture & Artificial Intelligence @ Flanders Investment & Trade
Flanders Investment and Trade (FIT) is a Flemish public agency that: supports the international activities of Flemish companies, and attracts foreign investors by highlighting Flanders’s central European location, its strongly developed infrastructure and its renowned innovative clusters.To become more competitive, FIT decided to invest in operational excellence, more specifically by using question answering techniques to process incoming questions and match them to historic questions and answers. We helped FIT build a solution that can now be used by FIT's advisors, and that is integrated with Dynamics CRM. Thanks to this solution, FIT saves time and effort, allowing to help 36% more clients in the same amount of time.
Business process automation for the expert HR services of Partena Professional
Speakers: Sammy Deprez, Managing Partner @ Arinti & Frauke Valcke, Project Manager @ Partena Professional
Is it possible to (partly) automate expert HR services? Can we build an easy-to-use tool to help highly skilled HR consultants perform their job in a more efficient way, having them spend less time on repetitive tasks and more time on interactions with customers?
Teachers / speakers
Walter Daelemans
Walter Daelemans is professor of Artificial Intelligence and Natural Language Processing (NLP) at the University of Antwerp. He helped pioneer the statistical and machine learning revolution in NLP in the nineties with the development of Memory-Based Language Processing and with work on the methodology of machine learning for language processing. He was awarded EurAI and ACL fellowships for this work, and has published influential work on text mining and knowledge extraction from biomedical, clinical, and social media text, and on stylometry and author profiling. With currently 32 supervised PhDs graduated and more than 400 co-authored publications he is one of the most prolific NLP researchers in the Low Countries. In addition, he has been involved in the creation of high profile valorization results with popular open-source software such as TiMBL and Pattern, and has been instrumental in the creation of several spin-offs (textkernel, textgain, fluent.ai).
Shoera Sels
Expertise in AI, Digital Transformation & AI Assisted Language Learning
Looking to implement AI in your organization? Shoera Sels is the go-to expert for strategic guidance and support in:
- Digital transformation and change management in AI projects
- Building a strong business case for AI adoption
- Introducing AI to non-technical professionals
- Applications of AI in language learning and education
She began her career as a Data Scientist at Delaware and went on to become Head of AI Solutions at AI consultancy Radix, where she led projects for clients such as the Port of Antwerp-Bruges. Her work included the development of a custom ChatGPT-based chatbot and initiatives to optimize ship navigation through AI.
Today, Shoera serves as data & AI Lead at language learning company BLCC, where she supports the digital transformation in language learning.
With a degree in Mathematical Engineering from KU Leuven and
extensive experience in both consultancy and education, Shoera combines
deep technical knowledge with a strong focus on real-world impact and
user adoption. Her approach is clear and human-centered.
Frauke Valcke
Project Manager at Partena Professional (strategic projects)
Sammy Deprez
As a seasoned Business Intelligence Consultant with over a decade of experience, Sammy has tackled diverse projects in various industries, ranging from finance to healthcare, with a specialization in the Microsoft Stack.
In 2015, he pivoted his focus towards Machine Learning and Artificial Intelligence, and in 2017 he played a pivotal role in launching a new company that specializes in maximizing organizations' potential through the use of Artificial Intelligence and Microsoft tools.
Yves Ruland
Project Manager Data Architecture & Artificial Intelligence at Flanders Investment & Trade
Stephen Lernout
Stephen Lernout is a serial entrepreneur with an extensive background in Technology Sales and Marketing. Before co-founding Deontic, he was responsible for strategy & innovation at several language technology companies like Miia and Nalantis. He is focused on building effective business models in the computational linguistics and natural language processing space.
Related courses
Machine learning and deep learning fundamentals
Workshop - Leuven - VIB, Training geselecteerd in de Belgische AI Factory Antenna (AIFA)