Hillebrand, Lars PatrickLars PatrickHillebrandDeußer, TobiasTobiasDeußerDilmaghani, TimTimDilmaghaniKliem, BerndBerndKliemLoitz, RüdigerRüdigerLoitzBauckhage, ChristianChristianBauckhageSifa, RafetRafetSifa2023-10-172023-10-172022https://publica.fraunhofer.de/handle/publica/45178610.1109/BigData55660.2022.100203082-s2.0-85147951646We introduce KPI-Check, a novel system that automatically identifies and cross-checks semantically equivalent key performance indicators (KPIs), e.g. "revenue"or "total costs", in real-world German financial reports. It combines a financial named entity and relation extraction module with a BERT-based filtering and text pair classification component to extract KPIs from unstructured sentences before linking them to synonymous occurrences in the balance sheet and profit & loss statement. The tool achieves a high matching performance of 73.00% micro F1 on a hold out test set and is currently being deployed for a globally operating major auditing firm to assist the auditing procedure of financial statements.enfact checkingmachine learningnatural language processingoutlier detectiontext miningconference paper