Search Results for author: Axel-Cyrille Ngonga Ngomo

Found 47 papers, 33 papers with code

RED$^{\rm FM}$: a Filtered and Multilingual Relation Extraction Dataset

1 code implementation16 Jun 2023 Pere-Lluís Huguet Cabot, Simone Tedeschi, Axel-Cyrille Ngonga Ngomo, Roberto Navigli

Relation Extraction (RE) is a task that identifies relationships between entities in a text, enabling the acquisition of relational facts and bridging the gap between natural language and structured knowledge.

Relation Relation Extraction

Learning Permutation-Invariant Embeddings for Description Logic Concepts

1 code implementation3 Mar 2023 Caglar Demir, Axel-Cyrille Ngonga Ngomo

We reformulate the learning problem as a multi-label classification problem and propose a neural embedding model (NERO) that learns permutation-invariant embeddings for sets of examples tailored towards predicting $F_1$ scores of pre-selected description logic concepts.

Multi-Label Classification Retrieval

Explaining $\mathcal{ELH}$ Concept Descriptions through Counterfactual Reasoning

no code implementations12 Jan 2023 Leonie Nora Sieger, Stefan Heindorf, Yasir Mahmood, Lukas Blübaum, Axel-Cyrille Ngonga Ngomo

Knowledge bases are widely used for information management, enabling high-impact applications such as web search, question answering, and natural language processing.

counterfactual Counterfactual Reasoning +2

Hardware-agnostic Computation for Large-scale Knowledge Graph Embeddings

1 code implementation18 Jul 2022 Caglar Demir, Axel-Cyrille Ngonga Ngomo

Knowledge graph embedding research has mainly focused on learning continuous representations of knowledge graphs towards the link prediction problem.

Continual Learning Knowledge Graph Embedding +3

Kronecker Decomposition for Knowledge Graph Embeddings

1 code implementation13 May 2022 Caglar Demir, Julian Lienen, Axel-Cyrille Ngonga Ngomo

Our experiments suggest that applying Kronecker decomposition on embedding matrices leads to an improved parameter efficiency on all benchmark datasets.

Hyperparameter Optimization Knowledge Graph Embedding +3

Neural Class Expression Synthesis

no code implementations16 Nov 2021 N'Dah Jean Kouagou, Stefan Heindorf, Caglar Demir, Axel-Cyrille Ngonga Ngomo

Our main intuition is that class expression learning can be regarded as a translation problem.

Machine Translation Translation

EvoLearner: Learning Description Logics with Evolutionary Algorithms

1 code implementation8 Nov 2021 Stefan Heindorf, Lukas Blübaum, Nick Düsterhus, Till Werner, Varun Nandkumar Golani, Caglar Demir, Axel-Cyrille Ngonga Ngomo

We contribute a novel initialization method for the initial population: starting from positive examples, we perform biased random walks and translate them to description logic concepts.

Benchmarking Evolutionary Algorithms +1

DRILL-- Deep Reinforcement Learning for Refinement Operators in $\mathcal{ALC}$

1 code implementation29 Jun 2021 Caglar Demir, Axel-Cyrille Ngonga Ngomo

In this work, we leverage deep reinforcement learning to accelerate the learning of concepts in $\mathcal{ALC}$ by proposing DRILL -- a novel class expression learning approach that uses a convolutional deep Q-learning model to steer its search.

Knowledge Graphs Q-Learning +2

Out-of-Vocabulary Entities in Link Prediction

1 code implementation26 May 2021 Caglar Demir, Axel-Cyrille Ngonga Ngomo

As benchmarks are crucial for the fair comparison of algorithms, ensuring their quality is tantamount to providing a solid ground for developing better solutions to link prediction and ipso facto embedding knowledge graphs.

Knowledge Graph Embedding Knowledge Graphs +1

An Empirical Evaluation of Cost-based Federated SPARQL Query Processing Engines

1 code implementation2 Apr 2021 Umair Qudus, Muhammad Saleem, Axel-Cyrille Ngonga Ngomo, Young-Koo Lee

Albeit informative, these metrics are generic and unable to quantify and evaluate the accuracy of the cardinality estimators of cost-based federation engines.


A Survey of RDF Stores & SPARQL Engines for Querying Knowledge Graphs

no code implementations25 Feb 2021 Waqas Ali, Muhammad Saleem, Bin Yao, Aidan Hogan, Axel-Cyrille Ngonga Ngomo

RDF has seen increased adoption in recent years, prompting the standardization of the SPARQL query language for RDF, and the development of local and distributed engines for processing SPARQL queries.

Knowledge Graphs Databases

SeMantic AnsweR Type prediction task (SMART) at ISWC 2020 Semantic Web Challenge

1 code implementation1 Dec 2020 Nandana Mihindukulasooriya, Mohnish Dubey, Alfio Gliozzo, Jens Lehmann, Axel-Cyrille Ngonga Ngomo, Ricardo Usbeck

Each year the International Semantic Web Conference accepts a set of Semantic Web Challenges to establish competitions that will advance the state of the art solutions in any given problem domain.

Knowledge Base Question Answering Type prediction +1

Revealing Secrets in SPARQL Session Level

1 code implementation13 Sep 2020 Xinyue Zhang, Meng Wang, Muhammad Saleem, Axel-Cyrille Ngonga Ngomo, Guilin Qi, Haofen Wang

Based on Semantic Web technologies, knowledge graphs help users to discover information of interest by using live SPARQL services.

Knowledge Graphs

Convolutional Complex Knowledge Graph Embeddings

1 code implementation7 Aug 2020 Caglar Demir, Axel-Cyrille Ngonga Ngomo

In this paper, we study the problem of learning continuous vector representations of knowledge graphs for predicting missing links.

Knowledge Graph Embeddings Knowledge Graphs +1

Template-based Question Answering using Recursive Neural Networks

1 code implementation3 Apr 2020 Ram G Athreya, Srividya Bansal, Axel-Cyrille Ngonga Ngomo, Ricardo Usbeck

When the top-2 most likely templates were considered the model achieves an accuracy of 0. 945 on the LC-QuAD dataset and 0. 786 on the QALD-7 dataset.

Feature Engineering Question Answering +2

Knowledge Graphs

2 code implementations4 Mar 2020 Aidan Hogan, Eva Blomqvist, Michael Cochez, Claudia d'Amato, Gerard de Melo, Claudio Gutierrez, José Emilio Labra Gayo, Sabrina Kirrane, Sebastian Neumaier, Axel Polleres, Roberto Navigli, Axel-Cyrille Ngonga Ngomo, Sabbir M. Rashid, Anisa Rula, Lukas Schmelzeisen, Juan Sequeda, Steffen Staab, Antoine Zimmermann

In this paper we provide a comprehensive introduction to knowledge graphs, which have recently garnered significant attention from both industry and academia in scenarios that require exploiting diverse, dynamic, large-scale collections of data.

Knowledge Graphs

A Physical Embedding Model for Knowledge Graphs

1 code implementation21 Jan 2020 Caglar Demir, Axel-Cyrille Ngonga Ngomo

We present a novel and scalable paradigm for the computation of knowledge graph embeddings, which we dub PYKE .

Knowledge Graph Embedding Knowledge Graph Embeddings +2

ORCA: a Benchmark for Data Web Crawlers

1 code implementation17 Dec 2019 Michael Röder, Geraldo de Souza, Denis Kuchelev, Abdelmoneim Amer Desouki, Axel-Cyrille Ngonga Ngomo

Although Data Web crawlers exist, and general Web crawlers could be adapted to focus on the Data Web, there is currently no benchmark to fairly evaluate their performance.

Databases Performance

Do your Resources Sound Similar?

no code implementations19 Nov 2019 Abdullah Fathi Ahmed, Mohamed Ahmed Sherif, Axel-Cyrille Ngonga Ngomo

Complex LS com- bine similarity measures with thresholds to determine whether a given predicate holds between two resources.

A Holistic Natural Language Generation Framework for the Semantic Web

no code implementations RANLP 2019 Axel-Cyrille Ngonga Ngomo, Diego Moussallem, Lorenz Bühmann

With the ever-growing generation of data for the Semantic Web comes an increasing demand for this data to be made available to non-semantic Web experts.

Text Generation

Semantic Web for Machine Translation: Challenges and Directions

no code implementations23 Jul 2019 Diego Moussallem, Matthias Wauer, Axel-Cyrille Ngonga Ngomo

Moreover, our research suggests that while Semantic Web technologies can enhance the quality of machine translation outputs for various problems, the combination of both is still in its infancy.

Machine Translation Translation

Augmenting Neural Machine Translation with Knowledge Graphs

1 code implementation23 Feb 2019 Diego Moussallem, Mihael Arčan, Axel-Cyrille Ngonga Ngomo, Paul Buitelaar

While neural networks have been used extensively to make substantial progress in the machine translation task, they are known for being heavily dependent on the availability of large amounts of training data.

Knowledge Graphs Machine Translation +2

Where is my URI?

1 code implementation European Semantic Web Conference 2018 Andre Valdestilhas, Tommaso Soru, Markus Nentwig, Edgard Marx, Muhammad Saleem, Axel-Cyrille Ngonga Ngomo

One of the Semantic Web foundations is the possibility to dereference URIs to let applications negotiate their semantic content.

RDF Dataset Discovery

LIDIOMS: A Multilingual Linked Idioms Data Set

1 code implementation LREC 2018 Diego Moussallem, Mohamed Ahmed Sherif, Diego Esteves, Marcos Zampieri, Axel-Cyrille Ngonga Ngomo

In this paper, we describe the LIDIOMS data set, a multilingual RDF representation of idioms currently containing five languages: English, German, Italian, Portuguese, and Russian.

RDF2PT: Generating Brazilian Portuguese Texts from RDF Data

1 code implementation LREC 2018 Diego Moussallem, Thiago castro Ferreira, Marcos Zampieri, Maria Claudia Cavalcanti, Geraldo Xexéo, Mariana Neves, Axel-Cyrille Ngonga Ngomo

The generation of natural language from Resource Description Framework (RDF) data has recently gained significant attention due to the continuous growth of Linked Data.

Machine Translation using Semantic Web Technologies: A Survey

no code implementations26 Nov 2017 Diego Moussallem, Matthias Wauer, Axel-Cyrille Ngonga Ngomo

A large number of machine translation approaches have recently been developed to facilitate the fluid migration of content across languages.

Machine Translation Translation

Mandolin: A Knowledge Discovery Framework for the Web of Data

1 code implementation3 Nov 2017 Tommaso Soru, Diego Esteves, Edgard Marx, Axel-Cyrille Ngonga Ngomo

Markov Logic Networks join probabilistic modeling with first-order logic and have been shown to integrate well with the Semantic Web foundations.

Link Prediction Relational Reasoning

Using Multi-Label Classification for Improved Question Answering

1 code implementation24 Oct 2017 Ricardo Usbeck, Michael Hoffmann, Michael Röder, Jens Lehmann, Axel-Cyrille Ngonga Ngomo

In particular, we develop a multi-label classification-based metasystem for question answering over 6 existing systems using an innovative set of 14 question features.

Classification General Classification +2

An Evaluation of Models for Runtime Approximation in Link Discovery

no code implementations1 Dec 2016 Kleanthi Georgala, Micheal Hoffmann, Axel-Cyrille Ngonga Ngomo

Some of the most rapid Link Discovery approaches rely internally on planning to execute link specifications.

Self-Wiring Question Answering Systems

no code implementations6 Nov 2016 Ricardo Usbeck, Jonathan Huthmann, Nico Duldhardt, Axel-Cyrille Ngonga Ngomo

Based on these descriptions, our approach will be able to automatically compose QA systems using a data-driven approach automatically.

Question Answering

A tool suite for creating question answering benchmarks

no code implementations LREC 2014 Axel-Cyrille Ngonga Ngomo, Norman Heino, Ren{\'e} Speck, Prodromos Malakasiotis

We introduce the BIOASQ suite, a set of open-source Web tools for the creation, assessment and community-driven improvement of question answering benchmarks.

Question Answering Retrieval

Cannot find the paper you are looking for? You can Submit a new open access paper.