Search Results for author:
Found 54 papers, 29 papers with code
Bootstrapping Multilingual Metadata Extraction: A Showcase in Cyrillic
Applications based on scholarly data are of ever increasing importance.
AIFB-WebScience at SemEval-2022 Task 12: Relation Extraction First - Using Relation Extraction to Identify Entities
In this paper, we present an end-to-end joint entity and relation extraction approach based on transformer-based language models.
RAGentA: Multi-Agent Retrieval-Augmented Generation for Attributed Question Answering
Central to the framework is a hybrid retrieval strategy that combines sparse and dense methods, improving Recall@20 by 12. 5% compared to the best single retrieval model, resulting in more correct and well-supported answers.
Hateful Person or Hateful Model? Investigating the Role of Personas in Hate Speech Detection by Large Language Models
Hate speech detection is a socially sensitive and inherently subjective task, with judgments often varying based on personal traits.
Paths to Causality: Finding Informative Subgraphs Within Knowledge Graphs for Knowledge-Based Causal Discovery
Inferring causal relationships between variable pairs is crucial for understanding multivariate interactions in complex systems.
Bridging RDF Knowledge Graphs with Graph Neural Networks for Semantically-Rich Recommender Systems
Graph Neural Networks (GNNs) have substantially advanced the field of recommender systems.
SimplifyMyText: An LLM-Based System for Inclusive Plain Language Text Simplification
Text simplification is essential for making complex content accessible to diverse audiences who face comprehension challenges.
Can LLMs Leverage Observational Data? Towards Data-Driven Causal Discovery with LLMs
Specifically, we examine whether LLMs can effectively utilize observational data through two prompting strategies: pairwise prompting and breadth first search (BFS)-based prompting.
Explainable LiDAR 3D Point Cloud Segmentation and Clustering for Detecting Airplane-Generated Wind Turbulence
Wake vortices - strong, coherent air turbulences created by aircraft - pose a significant risk to aviation safety and therefore require accurate and reliable detection methods.
Revisiting Projection-based Data Transfer for Cross-Lingual Named Entity Recognition in Low-Resource Languages
These findings highlight the robustness of projection-based data transfer as an alternative to model-based methods for crosslingual named entity recognition in lowresource languages.
Hallucinations Can Improve Large Language Models in Drug Discovery
In this paper, we come up with the hypothesis that hallucinations can improve LLMs in drug discovery.
Incorporating Quantum Advantage in Quantum Circuit Generation through Genetic Programming
Designing efficient quantum circuits that leverage quantum advantage compared to classical computing has become increasingly critical.
Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models
This paper explores ideas and provides a potential roadmap for the development and evaluation of physics-specific large-scale AI models, which we call Large Physics Models (LPMs).
Graph-Guided Textual Explanation Generation Framework
Specifically, highlight explanations are extracted as highly faithful cues representing the model's reasoning and are subsequently encoded through a graph neural network layer, which explicitly guides the NLE generation process.
The Effects of Hallucinations in Synthetic Training Data for Relation Extraction
However, this approach often introduces hallucinations, such as spurious facts, whose impact on relation extraction remains underexplored.
Knowledge Graph Structure as Prompt: Improving Small Language Models Capabilities for Knowledge-based Causal Discovery
In this paper, we investigate the capabilities of Small Language Models (SLMs, defined as LLMs with fewer than 1 billion parameters) with prompt-based learning for knowledge-based causal discovery.
AutoRDF2GML: Facilitating RDF Integration in Graph Machine Learning
In this paper, we introduce AutoRDF2GML, a framework designed to convert RDF data into data representations tailored for graph machine learning tasks.
ComplexTempQA: A Large-Scale Dataset for Complex Temporal Question Answering
We introduce ComplexTempQA, a large-scale dataset consisting of over 100 million question-answer pairs designed to tackle the challenges in temporal question answering.
GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention Mechanism
Pretrained Language Models (PLMs) benefit from external knowledge stored in graph structures for various downstream tasks.
GreeDy and CoDy: Counterfactual Explainers for Dynamic Graphs
Temporal Graph Neural Networks (TGNNs), crucial for modeling dynamic graphs with time-varying interactions, face a significant challenge in explainability due to their complex model structure.
Embedded Named Entity Recognition using Probing Classifiers
Streaming text generation has become a common way of increasing the responsiveness of language model powered applications, such as chat assistants.
Decomposed Prompting: Unveiling Multilingual Linguistic Structure Knowledge in English-Centric Large Language Models
Despite the predominance of English in their training data, English-centric Large Language Models (LLMs) like GPT-3 and LLaMA display a remarkable ability to perform multilingual tasks, raising questions about the depth and nature of their cross-lingual capabilities.
Why Lift so Heavy? Slimming Large Language Models by Cutting Off the Layers
Large Language Models (LLMs) possess outstanding capabilities in addressing various natural language processing (NLP) tasks.
GNNavi: Navigating the Information Flow in Large Language Models by Graph Neural Network
Large Language Models (LLMs) exhibit strong In-Context Learning (ICL) capabilities when prompts with demonstrations are used.
ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks
However, most previous studies primarily focused on sentence-level classification tasks, and only a few considered token-level labeling tasks such as Named Entity Recognition (NER) and Part-of-Speech (POS) tagging.
HyperPIE: Hyperparameter Information Extraction from Scientific Publications
We create a labeled data set covering publications from a variety of computer science disciplines.
Analyzing the Impact of Companies on AI Research Based on Publications
Artificial Intelligence (AI) is one of the most momentous technologies of our time.
Linked Papers With Code: The Latest in Machine Learning as an RDF Knowledge Graph
In this paper, we introduce Linked Papers With Code (LPWC), an RDF knowledge graph that provides comprehensive, current information about almost 400, 000 machine learning publications.
A Full-fledged Commit Message Quality Checker Based on Machine Learning
By considering all rules from the most popular CM quality guideline, creating datasets for those rules, and training and evaluating state-of-the-art machine learning models to check those rules, we can answer the research question with: sufficiently well for practice, with the lowest F$_1$ score of 82. 9\%, for the most challenging task.
Vocab-Expander: A System for Creating Domain-Specific Vocabularies Based on Word Embeddings
In this paper, we propose Vocab-Expander at https://vocab-expander. com, an online tool that enables end-users (e. g., technology scouts) to create and expand a vocabulary of their domain of interest.
Measuring Variety, Balance, and Disparity: An Analysis of Media Coverage of the 2021 German Federal Election
Determining and measuring diversity in news articles is important for a number of reasons, including preventing filter bubbles and fueling public discourse, especially before elections.
SemOpenAlex: The Scientific Landscape in 26 Billion RDF Triples
We present SemOpenAlex, an extensive RDF knowledge graph that contains over 26 billion triples about scientific publications and their associated entities, such as authors, institutions, journals, and concepts.
Evaluating Generative Models for Graph-to-Text Generation
Large language models (LLMs) have been widely employed for graph-to-text generation tasks.
CoCon: A Data Set on Combined Contextualized Research Artifact Use
To enable more holistic analyses and systems dealing with academic publications and their content, we propose CoCon, a large scholarly data set reflecting the combined use of research artifacts, contextualized in academic publications' full-text.
unarXive 2022: All arXiv Publications Pre-Processed for NLP, Including Structured Full-Text and Citation Network
Large-scale data sets on scholarly publications are the basis for a variety of bibliometric analyses and natural language processing (NLP) applications.
Biases in Scholarly Recommender Systems: Impact, Prevalence, and Mitigation
With the remarkable increase in the number of scientific entities such as publications, researchers, and scientific topics, and the associated information overload in science, academic recommender systems have become increasingly important for millions of researchers and science enthusiasts.
Predicting Companies' ESG Ratings from News Articles Using Multivariate Timeseries Analysis
Environmental, social and governance (ESG) engagement of companies moved into the focus of public attention over recent years.
Few-Shot Document-Level Relation Extraction
We present FREDo, a few-shot document-level relation extraction (FSDLRE) benchmark.
AIFB-WebScience at SemEval-2022 Task 12: Relation Extraction First -- Using Relation Extraction to Identify Entities
In this paper, we present an end-to-end joint entity and relation extraction approach based on transformer-based language models.
Are Investors Biased Against Women? Analyzing How Gender Affects Startup Funding in Europe
For startup founders, it is therefore crucial to know whether investors have a bias against women as startup founders and in which way startups face disadvantages due to gender bias.
Towards Full-Fledged Argument Search: A Framework for Extracting and Clustering Arguments from Unstructured Text
We suggest (1) to combine the keyword search with precomputed topic clusters for argument-query matching, (2) to apply a novel approach based on sentence-level sequence-labeling for argument identification, and (3) to present aggregated arguments to users based on topic-aware argument clustering.
Cross-Lingual Citations in English Papers: A Large-Scale Analysis of Prevalence, Usage, and Impact
Citation information in scholarly data is an important source of insight into the reception of publications and the scholarly discourse.
Citation Intent Classification
Cross-Lingual Entity Linking
+1
Explaining Convolutional Neural Networks by Tagging Filters
Finally, we show that the tags are helpful in analyzing classification errors caused by noisy input images and that the tags can be further processed by machines.
Safe, Fast, Concurrent Proof Checking for the lambda-Pi Calculus Modulo Rewriting
Several proof assistants, such as Isabelle or Coq, can concurrently check multiple proofs.
Logic in Computer Science
Right for the Right Reason: Making Image Classification Robust
To this end, we propose a new explanation quality metric to measure object aligned explanation in image classification which we refer to as theObAlExmetric.
Semantic Modelling of Citation Contexts for Context-aware Citation Recommendation
New research is being published at a rate, at which it is infeasible for many scholars to read and assess everything possibly relevant to their work.
unarXive: A Large Scholarly Data Set with Publications' Full-Text, Annotated In-Text Citations, and Links to Metadata
The data set, which is made freely available for research purposes, not only can enhance the future evaluation of research paper-based and citation context-based approaches, but also serve as a basis for new ways to analyze in-text citations, as we show prototypically in this article.
Citation Recommendation: Approaches and Datasets
In recent years, several approaches and evaluation data sets have been presented.
HybridCite: A Hybrid Model for Context-Aware Citation Recommendation
The process of recommending citations for citation contexts is called local citation recommendation and is the focus of this paper.
Making Neural Networks FAIR
In this paper, we first present the neural network ontology FAIRnets Ontology, an ontology to make existing neural network models findable, accessible, interoperable, and reusable according to the FAIR principles.
Linked Crunchbase: A Linked Data API and RDF Data Set About Innovative Companies
Crunchbase is an online platform collecting information about startups and technology companies, including attributes and relations of companies, people, and investments.
Which Knowledge Graph Is Best for Me?
Furthermore, we proposed a framework for finding the most suitable knowledge graph for a given setting.
Monte Carlo Tableau Proof Search
We study Monte Carlo Tree Search to guide proof search in tableau calculi.
Internal Guidance for Satallax
We evaluated our method on a simply-typed higher-order logic version of the Flyspeck project, where it solves 26% more problems than Satallax without internal guidance.
