6 citations · 41 across the 21 of their papers we have counts for
7 papers · 1 filter
Interpretable Topic Extraction and Word Embedding Learning using row-stochastic DEDICOM
Lars Hillebrand, David Biesner, Christian Bauckhage +1
The DEDICOM algorithm provides a uniquely interpretable matrix factorization method for symmetric and asymmetric square matrices. We employ a new row-stochastic variation of DEDICO…
Controlled Randomness Improves the Performance of Transformer Models
Tobias Deußer, Cong Zhao, Wolfgang Krämer +3
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 tex…
Informed Named Entity Recognition Decoding for Generative Language Models
Tobias Deußer, Lars Hillebrand, Christian Bauckhage +1
Ever-larger language models with ever-increasing capabilities are by now well-established text processing tools. Alas, information extraction tasks such as named entity recognition…
Improving Zero-Shot Text Matching for Financial Auditing with Large Language Models
Lars Hillebrand, Armin Berger, Tobias Deußer +8
Auditing financial documents is a very tedious and time-consuming process. As of today, it can already be simplified by employing AI-based solutions to recommend relevant text pass…
Towards automating Numerical Consistency Checks in Financial Reports
Lars Hillebrand, Tobias Deußer, Tim Dilmaghani +4
We 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…
NLPGym -- A toolkit for evaluating RL agents on Natural Language Processing Tasks
Rajkumar Ramamurthy, Rafet Sifa, Christian Bauckhage
Reinforcement learning (RL) has recently shown impressive performance in complex game AI and robotics tasks. To a large extent, this is thanks to the availability of simulated envi…