News
CATALPA sponsors 19th BEA Workshop
[19.06.2024]Get ready, the 19th BEA Workshop - Workshop on Innovative Use of NLP for Building Educational Applications starts in Mexico City tomorrow. CATALPA is a Gold Sponsor and CATALPA members Marie Bexte and Andrea Horbach are part of the organizing team.
Photo: Henrik Schipper/Hardy Welsch
The BEA Workshop is a leading venue for NLP (Natural Language Processing) innovation in the context of education. With over 100 participants, it’s also one of the largest one-day workshops in the Association for Computational Linguistics (ACL) community.
Natural Language Processing
NLP is a machine learning technology and primarily concerned with computers learning "language", or an understanding of data in the form of language. In recent years, this field of research has gained enormous importance for learning.
Shared Tasks
The annual Shared Tasks, in which researchers work together to solve a scientific problem, have even expanded into novel research areas, such as the automated evaluation of scientific writing, complex word identification, and generating AI teacher responses in educational dialogues. This year's workshop will include two shared tasks:
- Automated Prediction of Item Difficulty and Item Response Time (APIDIRT)
- Multilingual Lexical Simplification Pipeline (MLSP)
CATALPA at BEA
CATALPA is once again strongly represented in Mexico City this year:
Scoring with Confidence? - Exploring High-confidence Scoring for Saving Manual Grading Effort (Marie Bexte, Andrea Horbach, Lena Schützler, Oliver Christ and Torsten Zesch)
LLMs in Short Answer Scoring: Limitations and Promise of Zero-Shot and Few-Shot Approaches (Imran Chamieh, Torsten Zesch and Klaus Giebermann)
Transfer Learning of Argument Mining in Student Essays (Yuning Ding, Julian Lohmann, Nils-Jonathan Schaller, Thorben Jansen and Andrea Horbach)
Fairness in Automated Essay Scoring: A Comparative Analysis of Algorithms on German Learner Essays from Secondary Education (Nils-Jonathan Schaller, Yuning Ding, Andrea Horbach, Jennifer Meyer and Thorben Jansen)
