activity
20122026
most citedNLPGym -- A toolkit for evaluating RL agents on Natural Language Processing Tasks

6 citations · 41 across the 21 of their papers we have counts for

collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL20251 cited

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…

cs.CL2023

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…

cs.CL20235 cited

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…

cs.CL20232 cited

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…

cs.CL20224 cited

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…

cs.CL20206 cited

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…