Christian Heumann


CC-Top: Constrained Clustering for Dynamic Topic Discovery
Jann Goschenhofer | Pranav Ragupathy | Christian Heumann | Bernd Bischl | Matthias Aßenmacher
Proceedings of the The First Workshop on Ever Evolving NLP (EvoNLP)

Research on multi-class text classification of short texts mainly focuses on supervised (transfer) learning approaches, requiring a finite set of pre-defined classes which is constant over time. This work explores deep constrained clustering (CC) as an alternative to supervised learning approaches in a setting with a dynamically changing number of classes, a task we introduce as dynamic topic discovery (DTD).We do so by using pairwise similarity constraints instead of instance-level class labels which allow for a flexible number of classes while exhibiting a competitive performance compared to supervised approaches. First, we substantiate this through a series of experiments and show that CC algorithms exhibit a predictive performance similar to state-of-the-art supervised learning algorithms while requiring less annotation effort.Second, we demonstrate the overclustering capabilities of deep CC for detecting topics in short text data sets in the absence of the ground truth class cardinality during model training.Third, we showcase that these capabilities can be leveraged for the DTD setting as a step towards dynamic learning over time and finally, we release our codebase to nurture further research in this area.

Pre-trained language models evaluating themselves - A comparative study
Philipp Koch | Matthias Aßenmacher | Christian Heumann
Proceedings of the Third Workshop on Insights from Negative Results in NLP

Evaluating generated text received new attention with the introduction of model-based metrics in recent years. These new metrics have a higher correlation with human judgments and seemingly overcome many issues of previous n-gram based metrics from the symbolic age. In this work, we examine the recently introduced metrics BERTScore, BLEURT, NUBIA, MoverScore, and Mark-Evaluate (Petersen). We investigate their sensitivity to different types of semantic deterioration (part of speech drop and negation), word order perturbations, word drop, and the common problem of repetition. No metric showed appropriate behaviour for negation, and further none of them was overall sensitive to the other issues mentioned above.


pdf bib
Benchmarking down-scaled (not so large) pre-trained language models
Matthias Aßenmacher | Patrick Schulze | Christian Heumann
Proceedings of the 17th Conference on Natural Language Processing (KONVENS 2021)

How to Estimate Continuous Sentiments From Texts Using Binary Training Data
Sandra Wankmüller | Christian Heumann
Proceedings of the 17th Conference on Natural Language Processing (KONVENS 2021)