Search Results for author:
Found 40 papers, 10 papers with code
Pointer-Guided Pre-Training: Infusing Large Language Models with Paragraph-Level Contextual Awareness
We introduce "pointer-guided segment ordering" (SO), a novel pre-training technique aimed at enhancing the contextual understanding of paragraph-level text representations in large language models.
Model-agnostic Body Part Relevance Assessment for Pedestrian Detection
Model-agnostic explanation methods for deep learning models are flexible regarding usability and availability.
SugarViT -- Multi-objective Regression of UAV Images with Vision Transformers and Deep Label Distribution Learning Demonstrated on Disease Severity Prediction in Sugar Beet
One novelty in this work is the combination of remote sensing data with environmental parameters of the experimental sites for disease severity prediction.
Controlled Randomness Improves the Performance of Transformer Models
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.
Informed Named Entity Recognition Decoding for Generative Language Models
Ever-larger language models with ever-increasing capabilities are by now well-established text processing tools.
Improving Zero-Shot Text Matching for Financial Auditing with Large Language Models
Auditing financial documents is a very tedious and time-consuming process.
An Empirical Evaluation of the Rashomon Effect in Explainable Machine Learning
The Rashomon Effect describes the following phenomenon: for a given dataset there may exist many models with equally good performance but with different solution strategies.
Towards automating Numerical Consistency Checks in 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.
KPI-EDGAR: A Novel Dataset and Accompanying Metric for Relation Extraction from Financial Documents
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
Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization
To help answer this, we first introduce an open-source modular library, RL4LMs (Reinforcement Learning for Language Models), for optimizing language generators with RL.
Full Kullback-Leibler-Divergence Loss for Hyperparameter-free Label Distribution Learning
The concept of Label Distribution Learning (LDL) is a technique to stabilize classification and regression problems with ambiguous and/or imbalanced labels.
A New Aligned Simple German Corpus
"Leichte Sprache", the German counterpart to Simple English, is a regulated language aiming to facilitate complex written language that would otherwise stay inaccessible to different groups of people.
Gradient Flows for L2 Support Vector Machine Training
We explore the merits of training of support vector machines for binary classification by means of solving systems of ordinary differential equations.
KPI-BERT: A Joint Named Entity Recognition and Relation Extraction Model for Financial Reports
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.
Predict better with less training data using a QNN
Over the past decade, machine learning revolutionized vision-based quality assessment for which convolutional neural networks (CNNs) have now become the standard.
Informed Pre-Training on Prior Knowledge
In this paper, we propose a novel informed machine learning approach and suggest to pre-train on prior knowledge.
Towards Bundle Adjustment for Satellite Imaging via Quantum Machine Learning
Given is a set of images, where all images show views of the same area at different points in time and from different viewpoints.
QUBOs for Sorting Lists and Building Trees
We show that the fundamental tasks of sorting lists and building search trees or heaps can be modeled as quadratic unconstrained binary optimization problems (QUBOs).
Agricultural Plant Cataloging and Establishment of a Data Framework from UAV-based Crop Images by Computer Vision
Our workflow is able to automatize plant cataloging and training image extraction, especially for large datasets.
Dynamic Review-based Recommenders
In the present work we leverage the known power of reviews to enhance rating predictions in a way that (i) respects the causality of review generation and (ii) includes, in a bidirectional fashion, the ability of ratings to inform language review models and vice-versa, language representations that help predict ratings end-to-end.
Street-Map Based Validation of Semantic Segmentation in Autonomous Driving
Lastly, we present quantitative results on the Cityscapes dataset indicating that our validation approach can indeed uncover errors in semantic segmentation masks.
Quantum Circuit Evolution on NISQ Devices
The results provide intuition on how randomized search heuristics behave on actual quantum hardware and lay out a path for further refinement of evolutionary quantum gate circuits.
Recurrent Point Review Models
Specifically, we use the dynamic representations of recurrent point process models, which encode the history of how business or service reviews are received in time, to generate instantaneous language models with improved prediction capabilities.
NLPGym -- A toolkit for evaluating RL agents on Natural Language Processing Tasks
Reinforcement learning (RL) has recently shown impressive performance in complex game AI and robotics tasks.
Towards Map-Based Validation of Semantic Segmentation Masks
Artificial intelligence for autonomous driving must meet strict requirements on safety and robustness.
Learning Syllogism with Euler Neural-Networks
In contrast to traditional neural network, ENN can precisely represent all 24 different structures of Syllogism.
Recurrent Point Processes for Dynamic Review Models
Recent progress in recommender system research has shown the importance of including temporal representations to improve interpretability and performance.
Towards Supervised Extractive Text Summarization via RNN-based Sequence Classification
This article briefly explains our submitted approach to the DocEng'19 competition on extractive summarization.
Improving Word Embeddings Using Kernel PCA
Word-based embedding approaches such as Word2Vec capture the meaning of words and relations between them, particularly well when trained with large text collections; however, they fail to do so with small datasets.
Recurrent Adversarial Service Times
Service system dynamics occur at the interplay between customer behaviour and a service provider's response.
Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems
It considers the source of knowledge, its representation, and its integration into the machine learning pipeline.
Propagation kernels: efficient graph kernels from propagated information
We introduce propagation kernels, a general graph-kernel framework for efficiently measuring the similarity of structured data.
Ranked #8 on
Graph Classification
on NCI109
Neural Conditional Gradients
The move from hand-designed to learned optimizers in machine learning has been quite successful for gradient-based and -free optimizers.
Adiabatic Quantum Computing for Binary Clustering
Quantum computing for machine learning attracts increasing attention and recent technological developments suggest that especially adiabatic quantum computing may soon be of practical interest.
Using Echo State Networks for Cryptography
The key idea is to assume that Alice and Bob share a copy of an echo state network.
k-Means Clustering Is Matrix Factorization
We show that the objective function of conventional k-means clustering can be expressed as the Frobenius norm of the difference of a data matrix and a low rank approximation of that data matrix.
Exploring Human Vision Driven Features for Pedestrian Detection
Motivated by the center-surround mechanism in the human visual attention system, we propose to use average contrast maps for the challenge of pedestrian detection in street scenes due to the observation that pedestrians indeed exhibit discriminative contrast texture.
Propagation Kernels
We introduce propagation kernels, a general graph-kernel framework for efficiently measuring the similarity of structured data.
Informed Haar-like Features Improve Pedestrian Detection
Our main contribution is to systematically design a pool of rectangular templates that are tailored to this shape model.
Efficient Information Theoretic Clustering on Discrete Lattices
We consider the problem of clustering data that reside on discrete, low dimensional lattices.
