CsFEVER and CTKFacts: Czech Datasets for Fact Verification

In this paper we present two Czech datasets aimed for training automated fact-checking machine learning models. Specifically we deal with the task of assessment of a textual claim veracity w.r.t. to a (presumably) verified corpus. The output of the system is the claim classification SUPPORTS or REFUTES complemented with evidence documents or NEI (Not Enough Info) alone. In the first place we publish CsFEVER of approximately 112k claims which is an automatically generated Czech version of the well-known Wikipedia-based FEVER dataset. We took a hybrid approach of machine translation and language alignment, where the same method (and tools we provide) can be easily applied to other languages. The second dataset CTKFacts of 3,097 claims is built on the corpus of approximately two million Czech News Agency news reports. We present an extended methodology based on the FEVER approach. Most notably, we describe a method to automatically generate wider claim contexts (dictionaries) for non-hyperlinked corpora. The datasets are analyzed for spurious cues, which are annotation patterns leading to model overfitting. CTKFacts is further examined for inter-annotator agreement, and a typology of common annotator errors is extracted. Finally, we provide baseline models for all stages of the fact-checking pipeline.