Beyond publications

Tools

1. Ancient Greek Hexameter Analysis

I have developed a Python library for the automatic annotation of Ancient Greek hexameter verse. The code is open-source and can be downloaded from my GitHub.

2. German Sentiment Classification

This is joint work with Oliver Guhr and colleagues. Information about the Python module and the paper is available here.

3. Multilingual Punctuation

This is also joint work with Oliver and colleagues. More information can be found here.

Data sets

1. ACL RD-TEC: Manual Annotation of Terms and Semantic Classes

Behrang QasemiZadeh and I have annotated computational linguistics terms and their semantic classes in a set of abstracts sampled from the ACL Anthology Reference Corpus (ACL ARC).

• Overview of the data set

• Annotation guidelines

• LREC paper

• Extended version of the data set with unified XML for both annotators

2. Complingterm: Automatic Annotation of Semantic Classes

Héctor Martínez Alonso and I have created a data set that extends ACL RD-TEC. Complingterm contains terms from the ACL RD-TEC (versions 1.0 and 2.0) and attributes all of them to 1 of 4 coarse-grained semantic classes. For training, we used semantic classes from ACL RD-TEC 2.0, but merged them into larger containers. The resulting term-class list contains automatically annotated items that had not been annotated in the ACL RD-TEC.

• Download of the data

• LREC paper

3. SemEval Data

For the SemEval-2018 Task 7, a data set containing (specialised) entity and semantic relation annotations was created. The texts were taken from the ACL ARC, the domain is computational linguistics. The data can be downloaded here.

4. Other

I have also collected a (short) list of Russian non-breaking prefixes for the Perl Lingua::Sentence module.

Community

• Consulting member of the appointing commission for a full professor of Computational Linguistics at FernUniversität in Hagen

Workshops and Teaching

• Podcast with German radio station "MDR Sachsen. Das Sachsenradio" on current AI topics (in German)

• Another podcast on recent advances in NLP and their effects on society, along with André Hollstein (in German)

• Webinar series on Azure ML

• Webinar covering introductory topics of computational linguistics within Microsoft's AI Data Tuesday series

• I am one of the organisers of the SemEval 2018 Task 7 (paper).

• I have given a plenary at LICTRA conference in Leipzig in March, 2017 (topic: translation and translation studies in the digital age).

• Students: MA thesis on term variation in the ACL data

• Terminology for Translators, a workshop that I organised together with Andrea Wurm at Saarland University

• EXPERT Winter School, 2013

Reviews

I have reviewed for the following conferences and journals:

• LREC 

• SemEval

• NAACL 

• ACL 

• EMNLP ("outstanding reviewer" recognition in 2020)

• ACL Rolling Review

• Fachsprache – International Journal of Specialized Communication

• Applied Linguistics

• Language Resources and Evaluation

• Natural Language Engineering