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 data release: LibriVoxDeEn

We released a new corpus for German-to-English Speech Translation and Speech Recognition. This dataset consists of sentence-aligned triples of German audio, German text, and English translation, based on German audio books. Please find the details here. The paper is available on arxiv.

New publication at IWSLT 2019

New research from the StatNLP group on Multi-Task Modeling of Phonographic Languages: Translating Middle Egyptian Hieroglyphs has been accepted at the IWSLT 2019. Please access the paper here.

New publication in Journal of Artificial Intelligence in Medicine

New research from the StatNLP group and the University Medical Center Mannheim on Sepsis prediction in the intensive care unit has been accepted for publication in Journal of Artificial Intelligence in Medicine. Access the preprint here.

New publication at EMNLP-IJCNLP Demo Track 2019

Joey NMT will be presented at the demo track in EMNLP-IJCNLP 2019. The paper is available on arxiv. We released pre-trained models for the WMT17 en-de and lv-en benchmarks here.

New publications at ACL and MT Summit

New research from the StatNLP group on sequence-to-sequence reinforcement learning has been accepted at the ACL and MT SUMMIT conferences. Please access the papers here.