In this work we expand the UN Security Council Conflicts corpus (UNSCon) (Zaczynska at al. 2024) on verbal disputes in diplomatic speeches in English. By including annotations of a UNSC expert, we target the problem of annotating verbal conflicts in a domain with its own culture and rules. On the one hand, we aim to catch all conflicts detected by political domain experts which as a result will be interpretable only by people with advanced political science backgrounds. On the other hand, we target linguistically marked verbalisations that are domain-independent and potentially easier to detect for language models. This balancing act resulted in a refined annotation scheme, and we re-annotate and expand the corpus size by 40% by including new debates. We perform a pilot study using a Large Language Model to include lexical markers of negative evaluation within the conflict spans, which until now were not annotated separately. Classification experiments on the conflict labels in the corpus using Transformer models demonstrate that models trained on the political domain improve the results.

We investigate disputes in the United Nations Security Council (UNSC) by studying the linguistic means of expressing conflicts. As a result, we present the UNSC Conflict Corpus (UNSCon), a collection of 87 UNSC speeches that are annotated for conflicts. We explain and motivate our annotation scheme and report on a series of experiments for automatic conflict classification. Further, we demonstrate the difficulty when dealing with diplomatic language - which is highly complex and often implicit along various dimensions - by providing corpus examples, readability scores, and classification results.

More and more corpora are being annotated with Rhetorical Structure Theory (RST) trees, often in a multi-layer scenario, as analyzing RST annotations in combination with other layers can lead to a deeper understanding of texts. To date, prior work on RST for the analysis of diplomatic language however, is scarce. We are interested in political speeches and investigate what rhetorical strategies diplomats use to communicate critique or deal with disputes. To this end, we present a new dataset with RST annotations of 82 diplomatic speeches aligned to existing Conflict annotations (UNSC-RST). We explore ways of using rhetorical trees to analyze an annotated multi-layer corpus, looking at both the relation distribution and the tree structure of speeches. In preliminary analyses we already see patterns that are characteristic for particular topics or countries.

We present an extension of the SynSemClass Event-type Ontology, originally conceived as a bilingual Czech-English resource. We added German entries to the classes representing the concepts of the ontology. Having a different starting point than the original work (unannotated parallel corpus without links to a valency lexicon and, of course, different existing lexical resources), it was a challenge to adapt the annotation guidelines, the data model and the tools used for the original version. We describe the process and results of working in such a setup. We also show the next steps to adapt the annotation process, data structures and formats and tools necessary to make the addition of a new language in the future more smooth and efficient, and possibly to allow for various teams to work on SynSemClass extensions to many languages concurrently. We also present the latest release which contains the results of adding German, freely available for download as well as for online access.

We present a data set consisting of German news articles labeled for political bias on a five-point scale in a semi-supervised way. While earlier work on hyperpartisan news detection uses binary classification (i.e., hyperpartisan or not) and English data, we argue for a more fine-grained classification, covering the full political spectrum (i.e., far-left, left, centre, right, far-right) and for extending research to German data. Understanding political bias helps in accurately detecting hate speech and online abuse. We experiment with different classification methods for political bias detection. Their comparatively low performance (a macro-F1 of 43 for our best setup, compared to a macro-F1 of 79 for the binary classification task) underlines the need for more (balanced) data annotated in a fine-grained way.