Simon Ott
YOU?
Author Swipe
View article: Learning Rules from KGs Guided by Language Models
Learning Rules from KGs Guided by Language Models Open
Advances in information extraction have enabled the automatic construction of large knowledge graphs (e.g., Yago, Wikidata or Google KG), which are widely used in many applications like semantic search or data analytics. However, due to th…
View article: LiBOG: Lifelong Learning for Black-Box Optimizer Generation
LiBOG: Lifelong Learning for Black-Box Optimizer Generation Open
Meta-Black-Box Optimization (MetaBBO) garners attention due to its success in automating the configuration and generation of black-box optimizers, significantly reducing the human effort required for optimizer design and discovering optimi…
View article: Universal Remote Attestation for Cloud and Edge Platforms
Universal Remote Attestation for Cloud and Edge Platforms Open
With more computing workloads being shifted to the cloud, verifying the integrity of remote software stacks through remote attestation becomes an increasingly important topic. During remote attestation, a prover provides attestation eviden…
View article: ThoughtSource: A central hub for large language model reasoning data (dataset snapshot)
ThoughtSource: A central hub for large language model reasoning data (dataset snapshot) Open
ThoughtSource is a meta-dataset and software library for chain-of-thought reasoning in large language models (LLMs). This repository contains a snapshot of the openly available ThoughtSource datasets.
View article: ThoughtSource: A central hub for large language model reasoning data (dataset snapshot)
ThoughtSource: A central hub for large language model reasoning data (dataset snapshot) Open
ThoughtSource is a meta-dataset and software library for chain-of-thought reasoning in large language models (LLMs). This repository contains a snapshot of the openly available ThoughtSource datasets.
View article: ThoughtSource: A central hub for large language model reasoning data (code snapshot)
ThoughtSource: A central hub for large language model reasoning data (code snapshot) Open
ThoughtSource is a meta-dataset and software library for chain-of-thought reasoning in large language models (LLMs). This repository contains a snapshot of the associated GitHub repository.
View article: ThoughtSource: A central hub for large language model reasoning data (code snapshot)
ThoughtSource: A central hub for large language model reasoning data (code snapshot) Open
ThoughtSource is a meta-dataset and software library for chain-of-thought reasoning in large language models (LLMs). This repository contains a snapshot of the associated GitHub repository.
View article: ThoughtSource: A central hub for large language model reasoning data
ThoughtSource: A central hub for large language model reasoning data Open
ThoughtSource is a meta-dataset and software library for chain-of-thought reasoning in large language models (LLMs).
View article: ThoughtSource: A central hub for large language model reasoning data
ThoughtSource: A central hub for large language model reasoning data Open
ThoughtSource is a meta-dataset and software library for chain-of-thought reasoning in large language models (LLMs).
View article: ThoughtSource: A central hub for large language model reasoning data
ThoughtSource: A central hub for large language model reasoning data Open
Large language models (LLMs) such as GPT-4 have recently demonstrated impressive results across a wide range of tasks. LLMs are still limited, however, in that they frequently fail at complex reasoning, their reasoning processes are opaque…
View article: Evaluation of Transformer Architectures for Electrical Load Time-Series Forecasting
Evaluation of Transformer Architectures for Electrical Load Time-Series Forecasting Open
Accurate forecasts of the electrical load are needed to stabilize the electrical grid and maximize the use of renewable energies. Many good forecasting methods exist, including neural networks, and we compare them to the recently developed…
View article: Evaluation of Transformer Architectures for Electrical Load Time-Series Forecasting
Evaluation of Transformer Architectures for Electrical Load Time-Series Forecasting Open
Accurate forecasts of the electrical load are needed to stabilize the electrical grid and maximize the use of renewable energies. Many good forecasting methods exist, including neural networks, and we compare them to the recently developed…
View article: Supplementary data for "Mapping global dynamics of benchmark creation and saturation in artificial intelligence"
Supplementary data for "Mapping global dynamics of benchmark creation and saturation in artificial intelligence" Open
Supplementary data for the article "Mapping global dynamics of benchmark creation and saturation in artificial intelligence"
View article: Supplementary data for "Mapping global dynamics of benchmark creation and saturation in artificial intelligence"
Supplementary data for "Mapping global dynamics of benchmark creation and saturation in artificial intelligence" Open
Supplementary data for the article "Mapping global dynamics of benchmark creation and saturation in artificial intelligence"
View article: Supplementary data for "Mapping global dynamics of benchmark creation and saturation in artificial intelligence"
Supplementary data for "Mapping global dynamics of benchmark creation and saturation in artificial intelligence" Open
Supplementary data for the article "Mapping global dynamics of benchmark creation and saturation in artificial intelligence"
View article: BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing
BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing Open
Training and evaluating language models increasingly requires the construction of meta-datasets --diverse collections of curated data with clear provenance. Natural language prompting has recently lead to improved zero-shot generalization …
View article: Supplementary data for "Mapping global dynamics of benchmark creation and saturation in artificial intelligence"
Supplementary data for "Mapping global dynamics of benchmark creation and saturation in artificial intelligence" Open
Supplementary data for the article "Mapping global dynamics of benchmark creation and saturation in artificial intelligence"
View article: Pharmacogenomics decision support in the U-PGx project: Results and advice from clinical implementation across seven European countries
Pharmacogenomics decision support in the U-PGx project: Results and advice from clinical implementation across seven European countries Open
Background The clinical implementation of pharmacogenomics (PGx) could be one of the first milestones towards realizing personalized medicine in routine care. However, its widespread adoption requires the availability of suitable clinical …
View article: A global analysis of metrics used for measuring performance in natural language processing
A global analysis of metrics used for measuring performance in natural language processing Open
Measuring the performance of natural language processing models is challenging. Traditionally used metrics, such as BLEU and ROUGE, originally devised for machine translation and summarization, have been shown to suffer from low correlatio…
View article: Mapping global dynamics of benchmark creation and saturation in artificial intelligence
Mapping global dynamics of benchmark creation and saturation in artificial intelligence Open
Benchmarks are crucial to measuring and steering progress in artificial intelligence (AI). However, recent studies raised concerns over the state of AI benchmarking, reporting issues such as benchmark overfitting, benchmark saturation and …
View article: Dataset Debt in Biomedical Language Modeling
Dataset Debt in Biomedical Language Modeling Open
Jason Fries, Natasha Seelam, Gabriel Altay, Leon Weber, Myungsun Kang, Debajyoti Datta, Ruisi Su, Samuele Garda, Bo Wang, Simon Ott, Matthias Samwald, Wojciech Kusa. Proceedings of BigScience Episode #5 -- Workshop on Challenges & Perspect…
View article: A global analysis of metrics used for measuring performance in natural language processing
A global analysis of metrics used for measuring performance in natural language processing Open
Measuring the performance of natural language processing models is challenging. Traditionally used metrics, such as BLEU and ROUGE, originally devised for machine translation and summarization, have been shown to suffer from low correlatio…
View article: A curated, ontology-based, large-scale knowledge graph of artificial intelligence tasks and benchmarks
A curated, ontology-based, large-scale knowledge graph of artificial intelligence tasks and benchmarks Open
Research in artificial intelligence (AI) is addressing a growing number of tasks through a rapidly growing number of models and methodologies. This makes it difficult to keep track of where novel AI methods are successfully -- or still uns…
View article: SAFRAN: An interpretable, rule-based link prediction method outperforming embedding models
SAFRAN: An interpretable, rule-based link prediction method outperforming embedding models Open
Neural embedding-based machine learning models have shown promise for predicting novel links in knowledge graphs. Unfortunately, their practical utility is diminished by their lack of interpretability. Recently, the fully interpretable, ru…
View article: SAFRAN: An interpretable, rule-based link prediction method\n outperforming embedding models
SAFRAN: An interpretable, rule-based link prediction method\n outperforming embedding models Open
Neural embedding-based machine learning models have shown promise for\npredicting novel links in knowledge graphs. Unfortunately, their practical\nutility is diminished by their lack of interpretability. Recently, the fully\ninterpretable,…
View article: Scalable and interpretable rule-based link prediction for large heterogeneous knowledge graphs
Scalable and interpretable rule-based link prediction for large heterogeneous knowledge graphs Open
Neural embedding-based machine learning models have shown promise for predicting novel links in biomedical knowledge graphs. Unfortunately, their practical utility is diminished by their lack of interpretability. Recently, the fully interp…