no code implementations • 6 Feb 2024 • Elena Doering, Merle C. Hönig, Tobias Deußer, Gerard N. Bischof, Thilo van Eimeren, Alexander Drzezga, Lotta M. Ellingsen
In conclusion, both the I2I network and the linear model could offer valuable prognostic insights, guiding early intervention strategies to preemptively address anticipated declines in brain metabolism and potentially to monitor treatment effects.
no code implementations • 20 Oct 2023 • Tobias Deußer, Cong Zhao, Wolfgang Krämer, David Leonhard, Christian Bauckhage, Rafet Sifa
During the pre-training step of natural language models, the main objective is to learn a general representation of the pre-training dataset, usually requiring large amounts of textual data to capture the complexity and diversity of natural language.
no code implementations • 15 Aug 2023 • Tobias Deußer, Lars Hillebrand, Christian Bauckhage, Rafet Sifa
Ever-larger language models with ever-increasing capabilities are by now well-established text processing tools.
no code implementations • 11 Aug 2023 • Lars Hillebrand, Armin Berger, Tobias Deußer, Tim Dilmaghani, Mohamed Khaled, Bernd Kliem, Rüdiger Loitz, Maren Pielka, David Leonhard, Christian Bauckhage, Rafet Sifa
Auditing financial documents is a very tedious and time-consuming process.
1 code implementation • 15 May 2023 • Lars Hillebrand, Maren Pielka, David Leonhard, Tobias Deußer, Tim Dilmaghani, Bernd Kliem, Rüdiger Loitz, Milad Morad, Christian Temath, Thiago Bell, Robin Stenzel, Rafet Sifa
We present sustainAI, an intelligent, context-aware recommender system that assists auditors and financial investors as well as the general public to efficiently analyze companies' sustainability reports.
no code implementations • 11 Nov 2022 • Lars Hillebrand, Tobias Deußer, Tim Dilmaghani, Bernd Kliem, Rüdiger Loitz, Christian Bauckhage, Rafet Sifa
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.
no code implementations • 19 Oct 2022 • Maren Pielka, Felix Rode, Lisa Pucknat, Tobias Deußer, Rafet Sifa
We analyze two Natural Language Inference data sets with respect to their linguistic features.
1 code implementation • 17 Oct 2022 • Tobias Deußer, Syed Musharraf Ali, Lars Hillebrand, Desiana Nurchalifah, Basil Jacob, Christian Bauckhage, Rafet Sifa
We introduce KPI-EDGAR, a novel dataset for Joint Named Entity Recognition and Relation Extraction building on financial reports uploaded to the Electronic Data Gathering, Analysis, and Retrieval (EDGAR) system, where the main objective is to extract Key Performance Indicators (KPIs) from financial documents and link them to their numerical values and other attributes.
Ranked #1 on Joint Entity and Relation Extraction on KPI-EDGAR
no code implementations • 3 Aug 2022 • Lars Hillebrand, Tobias Deußer, Tim Dilmaghani, Bernd Kliem, Rüdiger Loitz, Christian Bauckhage, Rafet Sifa
We present KPI-BERT, a system which employs novel methods of named entity recognition (NER) and relation extraction (RE) to extract and link key performance indicators (KPIs), e. g. "revenue" or "interest expenses", of companies from real-world German financial documents.