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 INTERSPEECH 2021

New research from the StatNLP group on On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASR has been accepted at the INTERSPEECH 2021. The paper is available on arxiv.

New publication at SpLU-RoboNLP workshop @ACL 2021

New research from the StatNLP group on Error-Aware Interactive Semantic Parsing of OpenStreetMap has been accepted at the SpLU-RoboNLP Workshop @ACL-IJCNLP 2021. The paper is available on arxiv.

New publication at ACL-IJCNLP 2021 main conference

New research from the StatNLP group on Generating Landmark Navigation Instructions from Maps as a Graph-to-Text Problem has been accepted at the ACL-IJCNLP 2021 main conference. The paper is available on arxiv. For more information on the corpus, see here.

New publication at IEEE ICASSP 2021

New research from the StatNLP group on Cascaded Models With Cyclic Feedback For Direct Speech Translation has been accepted at the IEEE ICASSP 2021. The paper is available on arxiv.

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.