Natural Language Processing and Machine Learning

At the moment I’m a post-doctoral researcher at the Technical University of Darmstadt. My research focus is on using deep learning for NLP.



  • Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
    Nils Reimers, Iryna Gurevych. EMNLP 2019. [pdf] [software]
  • Classification and Clustering of Arguments with Contextualized Word Embeddings
    Nils Reimers, Benjamin Schiller, Tilman Beck, Johannes Daxenberger, Christian Stab, Iryna Gurevych. ACL 2019. [pdf] [software]
  • Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution
    Shany Barhom, Vered Shwartz, Alon Eirew, Michael Bugert, Nils Reimers, Ido Dagan. ACL 2019. [pdf] [software]
  • Alternative Weighting Schemes for ELMo Embeddings
    Nils Reimers, Iryna Gurevych. arxiv 2019. [pdf] [software]


  • Universal Machine Learning Methods for Detecting and Temporal Anchoring of Events
    Nils Reimers. Ph.D. thesis. [pdf]
  • Why Comparing Single Performance Scores Does Not Allow to Draw Conclusions About Machine Learning Approaches
    Nils Reimers, Iryna Gurevych. arxiv 2018. [pdf]
  • Event Time Extraction with a Decision Tree of Neural Classifiers
    Nils Reimers, Nazanin Dehghani, Iryna Gurevych. TACL 2018. [pdf] [software]


  • Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging
    Nils Reimers, Iryna Gurevych. EMNLP 2017. [pdf] [software]
  • Optimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling Tasks
    Nils Reimers, Iryna Gurevych. arxiv 2017. [pdf] [software]


  • Task-Oriented Intrinsic Evaluation of Semantic Textual Similarity
    Nils Reimers, Philip Beyer, Iryna Gurevych. COLING 2016. [pdf]
  • Temporal Anchoring of Events for the TimeBank Corpus
    Nils Reimers, Nazanin Dehghani, Iryna Gurevych. ACL 2016. [pdf] [software]
  • DARIAH‐DKPro‐Wrapper Output Format(DOF) Specification
    Fotis Jannidis, Stefan Pernes, Isabella Reger, Nils Reimers, Steffen Pielström, Thorsten Vitt. DARIAH-DE Working Paper. [pdf] [software].
  • A Tool for NLP-Preprocessing in Literary Text Analysis
    Nils Reimers, Fotis Jannidis, Steffen Pielström, Stefan Pernes, Isabella Reger. Digital Humanities 2016: Conference Abstracts. [software].
  • A Novel Attack Model for Collusion Secure Fingerprinting Codes
    Marcel Schäfer, Waldemar Berchtold, Nils Reimers, Teetje Stark, Martin Steinebach. EI 2016. [pdf]


  • Event Nugget Detection, Classification and Coreference Resolution using Deep Neural Networks and Gradient Boosted Decision Trees
    Nils Reimers, Iryna Gurevych. TAC 2015. [pdf] [software]


  • GermEval-2014: Nested Named Entity Recognition with Neural Networks
    Nils Reimers, Judith Eckle-Kohler, Carsten Schnober, Jungi Kim, Iryna Gurevych. Konvens 2014. [pdf] [software]


  • Robust Hash Algorithms for Text
    Martin Steinebach, Peter Klöckner, Nils Reimers, Dominik Wienand, Patrick Wolf. Communications and Multimedia Security, Volume 8099. [pdf]
  • Computing on Authenticated Data for Adjustable Predicates
    Björn Deiseroth, Victoria Fehr, Marc Fischlin, Manuel Maasz, Nils Reimers, Richard Stein. ACNS 2013. [pdf]



  • Deep Learning for NLP
    In October 2015 I gave a lecture on Deep Learning and how it can be used in NLP. In November 2016, I gave a 1-day seminar on this topic at the University of Duisburg-Essen. The slides, videos and supplementary code can be found on Github. In the sommer semester 2018 I gave this lecture at the TU Darmstadt.
  • Foundations of Language Technology
    In the winter semester 2014/2015 I created and supervised the exercise for the lecture ‘Foundations of Language Technology’, where the students learned the basic principles of NLP.


  • 2019 – Sentence Tranformers
    Framework for generation of state-of-the-art sentence embeddings using tranformer networks (BERT, RoBERTa, XLNet). [Github]
  • 2019 – Argument Classification and Clustering
    Using BERT to classify sentential arguments and to cluster them based on aspects. [Github]
  • 2018 – ELMo-BiLSTM-CNN-CRF Network for Sequence Classification
    Extension of the BiLSTM-CNN-CRF network for sequence classification using contextualized word embeddings (ELMo embeddings). [Github]
  • 2017 – BiLSTM-CNN-CRF Network for Sequence Classification
    A Python implementation of the state-of-the-art BiLSTM-CNN-CRF network for sequence classification. Up to 10 times faster than comparable implementations. [Github]
  • 2017 – Event Time Extraction with a Decision Tree of Neural Classifiers
    This is experimental software to temporally anchor events in time. The software uses Keras and provides methods to train own neural networks. [Github]
  • 2016 – Language independent truecaser in Python
    Truecasing is the process of restoring the correct capitalization of a text. This software creates a statistical language model to derive the correct casing for an input text. [Github]
  • 2015 – Event Nugget Detection using Deep Neural Networks
    This is experimental software to extract events from English text. The software uses Theano and provides methods to train own neural networks as well as pre-trained models that can be applied out of the box. [Github]
  • 2015 – DARIAH-DKPro-Wrapper
    The DARIAH-DKPro-Wrapper is an easy-to-use tool to extract basic linguistic information from text like Part-of-Speach, Named Entites, and syntax trees. Text as well as XML input files can be processed and the lingustic annotations are written to an easy to process file format. [Github]
Natural Language Processing
Machine Learning
Deep Learning


Information Extraction from Large News Corpora