- Home >
The Chatbots Lab hosts and is involved in multiple internal and cooperation projects. This is the short list of the most recent projects.
The artificial conversational assistant SafeTraveller helps people understand travel regulations related to COVID-19. The current implementation covers travel regulations for BeNeLux countries. It is implemented using RASA and works in Facebook Messenger. The heuristic-based evaluation of user experience shows performance above average.
Read the paper here.
Conversation Analysis and Conversational Interfaces
Despite all difficulties in the beginning, a lot of research effort has been invested to bring various insights gained from Conversation analysis (CA) into Dialogue Processing. Several attempts have been made to involve CA in dialogue-based human-machine interaction. In this internal cross-faculty collaboration project we explore further involvement of CA methods in all sorts of conversational interfaces and chatbots. Partner: Béatrice Arend (University of Luxembourg, Faculty of Humanities, Education and Social Sciences, Department of Social Sciences).
Artificial Conversation Companion
Practicing foreign language conversation with a machine may have multiple advantages: a machine does not judge, a machine is always available and accessible from everywhere. In this project we focus on language understanding and generation for German as a communication language for non-native speakers.
Read the whole story here: https://www.springer.com/de/book/9783030155032
SQL QuizBot: Conversational Interfaces for E-Assessment
In this proof-of concept project we investigate the opportunities and limitations of using conversational interfaces for e-assessment. We are working on connecting the open-source assessment software TAO with various instant messengers. This project is a continuation of the master thesis project by Bharathi Vijayakumar who successfully finished her thesis in September 2018.
Robo-Chat: Using Conversational Interfaces for Communication with Complex Systems (Internal)
In this internal research cooperation between the ACC Lab and SnT, we focus on using conversational interfaces for communication with complex technical systems in order to foster the explainability of their decisions, facilitation of the maintenance and a better understanding of human needs for such interfaces. We chose a data-driven approach for building a rule-based system, for which we analyse a dataset from Wizard-of-Oz experiments. This research is grounded in Conversation Analysis which allows dialogue modelling from small datasets and small number of examples. Cooperation partner: Nico Hochgeschwender (SnT).