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 at RWRL NeurIPS 2020

A new paper from our group: Learning from Human Feedback: Challenges for Real-World Reinforcement Learning in NLP will appear in the Challenges of Real-World RL Workshop at NeurIPS 2020. Please access the paper on arxiv.

New publication at COLING 2020

New research from the StatNLP group on Embedding Meta-Textual Information for Improved Learning to Rank has been accepted at the COLING 2020. Please find the details here. The paper is available on arxiv.

Special mention award at LOD 2020

Our paper Sparse Perturbations for Improved Convergence in Stochastic Zeroth-Order Optimization got a “special mention” at LOD 2020 best paper award.

New publication at LOD 2020

New research from the StatNLP group on Sparse Perturbations for Improved Convergence in Stochastic Zeroth-Order Optimization has been accepted at the LOD 2020. The paper is available on arxiv.

New publication at EAMT 2020

New research from the StatNLP group on Learning from Error Corrections and Markings will appear at the EAMT 2020. Please access the paper on arxiv. Our data set is publicly available here.