Moreo, A.; Esuli, A. & Sebastiani, F.: Word-Class Embeddings for Multiclass Text Classification. , 2019
[Volltext]
Pre-trained word embeddings encode general word semantics and lexical
gularities of natural language, and have proven useful across many NLP tasks,
cluding word sense disambiguation, machine translation, and sentiment
alysis, to name a few. In supervised tasks such as multiclass text
assification (the focus of this article) it seems appealing to enhance word
presentations with ad-hoc embeddings that encode task-specific information.
propose (supervised) word-class embeddings (WCEs), and show that, when
ncatenated to (unsupervised) pre-trained word embeddings, they substantially
cilitate the training of deep-learning models in multiclass classification by
pic. We show empirical evidence that WCEs yield a consistent improvement in
lticlass classification accuracy, using four popular neural architectures and
x widely used and publicly available datasets for multiclass text
assification. Our code that implements WCEs is publicly available at
tps://github.com/AlexMoreo/word-class-embeddings

Olson, R. S.; Cava, W. G. L.; Mustahsan, Z.; Varik, A. & Moore, J. H.: Data-driven Advice for Applying Machine Learning to Bioinformatics Problems.. , 2017
[Volltext]
As the bioinformatics field grows, it must keep pace not only with new data
t with new algorithms. Here we contribute a thorough analysis of 13
ate-of-the-art, commonly used machine learning algorithms on a set of 165
blicly available classification problems in order to provide data-driven
gorithm recommendations to current researchers. We present a number of
atistical and visual comparisons of algorithm performance and quantify the
fect of model selection and algorithm tuning for each algorithm and dataset.
e analysis culminates in the recommendation of five algorithms with
perparameters that maximize classifier performance across the tested
oblems, as well as general guidelines for applying machine learning to
pervised classification problems.

Jannidis, F.; Pielström, S.; Schöch, C. & Vitt, T.: Improving Burrows Delta. In: Abstracts for the Digital Humanities 2015 (2015),
[Volltext]

Jannidis, F.: Figur und Person. Beitrag zu einer historischen Narratologie. Berlin/New York: De Gruyter, 2004Narratologia
[Volltext]

Jannidis, F.: Figur und Person: Beitrag zu einer historischen Narratologie. De Gruyter, 2004Narratologia