Brigitte Krenn, Johann Petrak, Marina Kubina, Christian Burger This paper presents a sexism/misogyny dataset extracted from comments of a large online forum of an Austrian newspaper. The comments are in Austrian German language, and in some cases interspersed with dialectal or English elements. We describe the data collection, the annotation guidelines and the annotation process resulting in a corpus of approximately 8 000 comments which were annotated with 5 levels of sexism/misogyny, ranging from 0 (not sexist/misogynist) to 4 (highly sexist/misogynist). The professional forum moderators (self-identified females and males) of the online newspaper were involved as experts in the creation of the annotation guidelines and the annotation of the user comments. In addition, we also describe first results of training transformer-based classification models for both binarized and original label classification of the corpus.

This paper describes the participation of team “bertha-von-suttner” in the SemEval2019 task 4 Hyperpartisan News Detection task. Our system uses sentence representations from averaged word embeddings generated from the pre-trained ELMo model with Convolutional Neural Networks and Batch Normalization for predicting hyperpartisan news. The final predictions were generated from the averaged predictions of an ensemble of models. With this architecture, our system ranked in first place, based on accuracy, the official scoring metric.

In the sentence classification task, context formed from sentences adjacent to the sentence being classified can provide important information for classification. This context is, however, often ignored. Where methods do make use of context, only small amounts are considered, making it difficult to scale. We present a new method for sentence classification, Context-LSTM-CNN, that makes use of potentially large contexts. The method also utilizes long-range dependencies within the sentence being classified, using an LSTM, and short-span features, using a stacked CNN. Our experiments demonstrate that this approach consistently improves over previous methods on two different datasets.

We present GATE DictLemmatizer, a multilingual open source lemmatizer for the GATE NLP framework that currently supports English, German, Italian, French, Dutch, and Spanish, and is easily extensible to other languages. The software is freely available under the LGPL license. The lemmatization is based on the Helsinki Finite-State Transducer Technology (HFST) and lemma dictionaries automatically created from Wiktionary. We evaluate the performance of the lemmatizers against TreeTagger, which is only freely available for research purposes. Our evaluation shows that DictLemmatizer achieves similar or even better results than TreeTagger for languages where there is support from HFST. The performance drops when there is no support from HFST and the entire lemmatization process is based on lemma dictionaries. However, the results are still satisfactory given the fact that DictLemmatizer isopen-source and can be easily extended to other languages. The software for extending the lemmatizer by creating word lists from Wiktionary dictionaries is also freely available as open-source software.

Language resources extracted from structured data (e.g. Linked Open Data) have already been used in various scenarios to improve conventional Natural Language Processing techniques. The meanings of words and the relations between them are made more explicit in RDF graphs, in comparison to human-readable text, and hence have a great potential to improve legacy applications. In this paper, we describe an approach that can be used to extend or clarify the semantic meaning of a word by constructing a list of contextually related terms. Our approach is based on exploiting the structure inherent in an RDF graph and then applying the methods from statistical semantics, and in particular, Random Indexing, in order to discover contextually related terms. We evaluate our approach in the domain of life science using the dataset generated with the help of domain experts from a large pharmaceutical company (AstraZeneca). They were involved in two phases: firstly, to generate a set of keywords of interest to them, and secondly to judge the set of generated contextually similar words for each keyword of interest. We compare our proposed approach, exploiting the semantic graph, with the same method applied on the human readable text extracted from the graph.