Marius Kloft


pdf bib
A Call for Standardization and Validation of Text Style Transfer Evaluation
Phil Ostheimer | Mayank Kumar Nagda | Marius Kloft | Sophie Fellenz
Findings of the Association for Computational Linguistics: ACL 2023

Text Style Transfer (TST) evaluation is, in practice, inconsistent. Therefore, we conduct a meta-analysis on human and automated TST evaluation and experimentation that thoroughly examines existing literature in the field. The meta-analysis reveals a substantial standardization gap in human and automated evaluation. In addition, we also find a validation gap: only few automated metrics have been validated using human experiments. To this end, we thoroughly scrutinize both the standardization and validation gap and reveal the resulting pitfalls. This work also paves the way to close the standardization and validation gap in TST evaluation by calling out requirements to be met by future research.


pdf bib
Self-Attentive, Multi-Context One-Class Classification for Unsupervised Anomaly Detection on Text
Lukas Ruff | Yury Zemlyanskiy | Robert Vandermeulen | Thomas Schnake | Marius Kloft
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

There exist few text-specific methods for unsupervised anomaly detection, and for those that do exist, none utilize pre-trained models for distributed vector representations of words. In this paper we introduce a new anomaly detection method—Context Vector Data Description (CVDD)—which builds upon word embedding models to learn multiple sentence representations that capture multiple semantic contexts via the self-attention mechanism. Modeling multiple contexts enables us to perform contextual anomaly detection of sentences and phrases with respect to the multiple themes and concepts present in an unlabeled text corpus. These contexts in combination with the self-attention weights make our method highly interpretable. We demonstrate the effectiveness of CVDD quantitatively as well as qualitatively on the well-known Reuters, 20 Newsgroups, and IMDB Movie Reviews datasets.


pdf bib
Predicting MOOC Dropout over Weeks Using Machine Learning Methods
Marius Kloft | Felix Stiehler | Zhilin Zheng | Niels Pinkwart
Proceedings of the EMNLP 2014 Workshop on Analysis of Large Scale Social Interaction in MOOCs