Johannes Hellrich


pdf bib
The Influence of Down-Sampling Strategies on SVD Word Embedding Stability
Johannes Hellrich | Bernd Kampe | Udo Hahn
Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP

The stability of word embedding algorithms, i.e., the consistency of the word representations they reveal when trained repeatedly on the same data set, has recently raised concerns. We here compare word embedding algorithms on three corpora of different sizes, and evaluate both their stability and accuracy. We find strong evidence that down-sampling strategies (used as part of their training procedures) are particularly influential for the stability of SVD-PPMI-type embeddings. This finding seems to explain diverging reports on their stability and lead us to a simple modification which provides superior stability as well as accuracy on par with skip-gram embedding

pdf bib
Modeling Word Emotion in Historical Language: Quantity Beats Supposed Stability in Seed Word Selection
Johannes Hellrich | Sven Buechel | Udo Hahn
Proceedings of the 3rd Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature

To understand historical texts, we must be aware that language—including the emotional connotation attached to words—changes over time. In this paper, we aim at estimating the emotion which is associated with a given word in former language stages of English and German. Emotion is represented following the popular Valence-Arousal-Dominance (VAD) annotation scheme. While being more expressive than polarity alone, existing word emotion induction methods are typically not suited for addressing it. To overcome this limitation, we present adaptations of two popular algorithms to VAD. To measure their effectiveness in diachronic settings, we present the first gold standard for historical word emotions, which was created by scholars with proficiency in the respective language stages and covers both English and German. In contrast to claims in previous work, our findings indicate that hand-selecting small sets of seed words with supposedly stable emotional meaning is actually harm- rather than helpful.

pdf bib
Continuous Quality Control and Advanced Text Segment Annotation with WAT-SL 2.0
Christina Lohr | Johannes Kiesel | Stephanie Luther | Johannes Hellrich | Tobias Kolditz | Benno Stein | Udo Hahn
Proceedings of the 13th Linguistic Annotation Workshop

Today’s widely used annotation tools were designed for annotating typically short textual mentions of entities or relations, making their interface cumbersome to use for long(er) stretches of text, e.g, sentences running over several lines in a document. They also lack systematic support for hierarchically structured labels, i.e., one label being conceptually more general than another (e.g., anamnesis in relation to family anamnesis). Moreover, as a more fundamental shortcoming of today’s tools, they provide no continuous quality con trol mechanisms for the annotation process, an essential feature to intrinsically support iterative cycles in the development of annotation guidelines. We alleviated these problems by developing WAT-SL 2.0, an open-source web-based annotation tool for long-segment labeling, hierarchically structured label sets and built-ins for quality control.


pdf bib
A Method for Human-Interpretable Paraphrasticality Prediction
Maria Moritz | Johannes Hellrich | Sven Büchel
Proceedings of the Second Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature

The detection of reused text is important in a wide range of disciplines. However, even as research in the field of plagiarism detection is constantly improving, heavily modified or paraphrased text is still challenging for current methodologies. For historical texts, these problems are even more severe, since text sources were often subject to stronger and more frequent modifications. Despite the need for tools to automate text criticism, e.g., tracing modifications in historical text, algorithmic support is still limited. While current techniques can tell if and how frequently a text has been modified, very little work has been done on determining the degree and kind of paraphrastic modification—despite such information being of substantial interest to scholars. We present a human-interpretable, feature-based method to measure paraphrastic modification. Evaluating our technique on three data sets, we find that our approach performs competitive to text similarity scores borrowed from machine translation evaluation, being much harder to interpret.

pdf bib
JeSemE: Interleaving Semantics and Emotions in a Web Service for the Exploration of Language Change Phenomena
Johannes Hellrich | Sven Buechel | Udo Hahn
Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations

We here introduce a substantially extended version of JeSemE, an interactive website for visually exploring computationally derived time-variant information on word meanings and lexical emotions assembled from five large diachronic text corpora. JeSemE is designed for scholars in the (digital) humanities as an alternative to consulting manually compiled, printed dictionaries for such information (if available at all). This tool uniquely combines state-of-the-art distributional semantics with a nuanced model of human emotions, two information streams we deem beneficial for a data-driven interpretation of texts in the humanities.


pdf bib
Exploring Diachronic Lexical Semantics with JeSemE
Johannes Hellrich | Udo Hahn
Proceedings of ACL 2017, System Demonstrations


pdf bib
An Assessment of Experimental Protocols for Tracing Changes in Word Semantics Relative to Accuracy and Reliability
Johannes Hellrich | Udo Hahn
Proceedings of the 10th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities

pdf bib
Feelings from the Past—Adapting Affective Lexicons for Historical Emotion Analysis
Sven Buechel | Johannes Hellrich | Udo Hahn
Proceedings of the Workshop on Language Technology Resources and Tools for Digital Humanities (LT4DH)

We here describe a novel methodology for measuring affective language in historical text by expanding an affective lexicon and jointly adapting it to prior language stages. We automatically construct a lexicon for word-emotion association of 18th and 19th century German which is then validated against expert ratings. Subsequently, this resource is used to identify distinct emotional patterns and trace long-term emotional trends in different genres of writing spanning several centuries.

pdf bib
UIMA-Based JCoRe 2.0 Goes GitHub and Maven Central ― State-of-the-Art Software Resource Engineering and Distribution of NLP Pipelines
Udo Hahn | Franz Matthies | Erik Faessler | Johannes Hellrich
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

We introduce JCoRe 2.0, the relaunch of a UIMA-based open software repository for full-scale natural language processing originating from the Jena University Language & Information Engineering (JULIE) Lab. In an attempt to put the new release of JCoRe on firm software engineering ground, we uploaded it to GitHub, a social coding platform, with an underlying source code versioning system and various means to support collaboration for software development and code modification management. In order to automate the builds of complex NLP pipelines and properly represent and track dependencies of the underlying Java code, we incorporated Maven as part of our software configuration management efforts. In the meantime, we have deployed our artifacts on Maven Central, as well. JCoRe 2.0 offers a broad range of text analytics functionality (mostly) for English-language scientific abstracts and full-text articles, especially from the life sciences domain.

pdf bib
Bad Company—Neighborhoods in Neural Embedding Spaces Considered Harmful
Johannes Hellrich | Udo Hahn
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

We assess the reliability and accuracy of (neural) word embeddings for both modern and historical English and German. Our research provides deeper insights into the empirically justified choice of optimal training methods and parameters. The overall low reliability we observe, nevertheless, casts doubt on the suitability of word neighborhoods in embedding spaces as a basis for qualitative conclusions on synchronic and diachronic lexico-semantic matters, an issue currently high up in the agenda of Digital Humanities.


pdf bib
Collaboratively Annotating Multilingual Parallel Corpora in the Biomedical Domain—some MANTRAs
Johannes Hellrich | Simon Clematide | Udo Hahn | Dietrich Rebholz-Schuhmann
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

The coverage of multilingual biomedical resources is high for the English language, yet sparse for non-English languages―an observation which holds for seemingly well-resourced, yet still dramatically low-resourced ones such as Spanish, French or German but even more so for really under-resourced ones such as Dutch. We here present experimental results for automatically annotating parallel corpora and simultaneously acquiring new biomedical terminology for these under-resourced non-English languages on the basis of two types of language resources, namely parallel corpora (i.e. full translation equivalents at the document unit level) and (admittedly deficient) multilingual biomedical terminologies, with English as their anchor language. We automatically annotate these parallel corpora with biomedical named entities by an ensemble of named entity taggers and harmonize non-identical annotations the outcome of which is a so-called silver standard corpus. We conclude with an empirical assessment of this approach to automatically identify both known and new terms in multilingual corpora.

pdf bib
Disclose Models, Hide the Data - How to Make Use of Confidential Corpora without Seeing Sensitive Raw Data
Erik Faessler | Johannes Hellrich | Udo Hahn
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

Confidential corpora from the medical, enterprise, security or intelligence domains often contain sensitive raw data which lead to severe restrictions as far as the public accessibility and distribution of such language resources are concerned. The enforcement of strict mechanisms of data protection consitutes a serious barrier for progress in language technology (products) in such domains, since these data are extremely rare or even unavailable for scientists and developers not directly involved in the creation and maintenance of such resources. In order to by-pass this problem, we here propose to distribute trained language models which were derived from such resources as a substitute for the original confidential raw data which remain hidden to the outside world. As an example, we exploit the access-protected German-language medical FRAMED corpus from which we generate and distribute models for sentence splitting, tokenization and POS tagging based on software taken from OPENNLP, NLTK and JCORE, our own UIMA-based text analytics pipeline.