Welcome to the Statistical Natural Language Processing Group at the Institute for Computational Linguistics at Heidelberg University. Our research is on the intersection of machine learning and natural language processing, with a special focus on interactive statistical learning techniques. For example, we work on interactive neural machine translation and neural question answering systems, where an artificial intelligence agent learns from human reinforcement/bandit feedback.

We organize the weekly Statistical NLP Colloquium.

group photo
StatNLP group @ Botanical Gardens (next to our department)

Latest news

New publication in TMLR

New research from the StatNLP group titled Compositionality in Time Series: A Proof of Concept using Symbolic Dynamics and Compositional Data Augmentation will be published in the journal TMLR. A copy is already available on OpenReview.

publications
New publication at WMT 2024

New research from the StatNLP group titled Post-edits Are Preferences Too will be presented at WMT 2024. A pre-print of the paper is available here.

publications
New publication at MLHC 2024

New research from the StatNLP group about Early Prediction of Causes (not Effects) in Healthcare by Long-Term Clinical Time Series Forecasting will be presented at MLHC 2024. The paper is available here.

publications
Second edition of "Validity, Reliability, and Significance: Empirical Methods for NLP and Data Science" published

The monograph is published in the Synthesis Lectures on Human Language Technologies series by Springer. More info

publications
New publication at EAMT2024

New research from the StatNLP group about Prompting Large Language Models with Human Error Markings for Self-Correcting Machine Translation will be presented at EAMT 2024. The paper is available here.

publications