no code implementations • spnlp (ACL) 2022 • Daniel Daza, Michael Cochez, Paul Groth
We present SlotGAN, a framework for training a mention detection model that only requires unlabeled text and a gazetteer.
no code implementations • 4 Nov 2024 • Tom Pelletreau-Duris, Ruud van Bakel, Michael Cochez
While other works have focused on instance-based explanation methods for GNNs, very few have investigated model-based methods and, to our knowledge, none have tried to probe the embedding of the GNNs for well-known structural graph properties.
1 code implementation • 11 Aug 2024 • Taewoon Kim, Vincent François-Lavet, Michael Cochez
Humans observe only part of their environment at any moment but can still make complex, long-term decisions thanks to our long-term memory.
Ranked #1 on
RoomEnv-v2
on RoomEnv-v2
no code implementations • 10 Jul 2024 • Daniel Daza, Cuong Xuan Chu, Trung-Kien Tran, Daria Stepanova, Michael Cochez, Paul Groth
Second, they are consistent: the effect of selecting certain inputs overlaps very little with the effect of discarding them.
1 code implementation • 4 Dec 2023 • Ruijie Wang, Luca Rossetto, Michael Cochez, Abraham Bernstein
Most current methods for multi-hop question answering (QA) over knowledge graphs (KGs) only provide final conclusive answers without explanations, such as a set of KG entities that is difficult for normal users to review and comprehend.
no code implementations • 9 Nov 2023 • Azhar Shaikh, Michael Cochez, Denis Diachkov, Michiel de Rijcke, Sahar Yousefi
This paper introduces DONUT-hole, a sparse OCR-free visual document understanding (VDU) model that addresses the limitations of its predecessor model, dubbed DONUT.
no code implementations • 6 Oct 2023 • Tamara Cucumides, Daniel Daza, Pablo Barceló, Michael Cochez, Floris Geerts, Juan L Reutter, Miguel Romero
We introduce a framework for answering arbitrary graph pattern queries over incomplete knowledge graphs, encompassing both cyclic queries and tree-like queries with existentially quantified leaves.
no code implementations • 12 Aug 2023 • Michael Cochez, Dimitrios Alivanistos, Erik Arakelyan, Max Berrendorf, Daniel Daza, Mikhail Galkin, Pasquale Minervini, Mathias Niepert, Hongyu Ren
We will first provide an overview of the different query types which can be supported by these methods and datasets typically used for evaluation, as well as an insight into their limitations.
1 code implementation • 6 Jun 2023 • Daniel Daza, Dimitrios Alivanistos, Payal Mitra, Thom Pijnenburg, Michael Cochez, Paul Groth
We train models using a biomedical KG containing approximately 2 million triples, and evaluate the performance of the resulting entity embeddings on the tasks of link prediction, and drug-protein interaction prediction, comparing against methods that do not take attribute data into account.
no code implementations • 24 Apr 2023 • Bo Xiong, Mojtaba Nayyeri, Ming Jin, Yunjie He, Michael Cochez, Shirui Pan, Steffen Staab
Geometric relational embeddings map relational data as geometric objects that combine vector information suitable for machine learning and structured/relational information for structured/relational reasoning, typically in low dimensions.
Hierarchical Multi-label Classification
Knowledge Graph Completion
+3
1 code implementation • 26 Mar 2023 • Hongyu Ren, Mikhail Galkin, Michael Cochez, Zhaocheng Zhu, Jure Leskovec
Extending the idea of graph databases (graph DBs), NGDB consists of a Neural Graph Storage and a Neural Graph Engine.
1 code implementation • 25 Dec 2022 • Md. Rezaul Karim, Tanhim Islam, Oya Beyan, Christoph Lange, Michael Cochez, Dietrich Rebholz-Schuhmann, Stefan Decker
Explainable artificial intelligence (XAI) aims to overcome the opaqueness of black-box models and provide transparency in how AI systems make decisions.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+1
1 code implementation • 5 Dec 2022 • Taewoon Kim, Michael Cochez, Vincent François-Lavet, Mark Neerincx, Piek Vossen
Inspired by the cognitive science theory of the explicit human memory systems, we have modeled an agent with short-term, episodic, and semantic memory systems, each of which is modeled with a knowledge graph.
Ranked #1 on
RoomEnv-v1
on RoomEnv-v1
1 code implementation • 23 Aug 2022 • Dimitrios Alivanistos, Selene Báez Santamaría, Michael Cochez, Jan-Christoph Kalo, Emile van Krieken, Thiviyan Thanapalasingam
ProP implements a multi-step approach that combines a variety of prompting techniques to achieve this.
1 code implementation • 3 Jun 2022 • Ruijie Wang, Luca Rossetto, Michael Cochez, Abraham Bernstein
Multi-relation question answering (QA) is a challenging task, where given questions usually require long reasoning chains in KGs that consist of multiple relations.
1 code implementation • 4 Apr 2022 • Taewoon Kim, Michael Cochez, Vincent Francois-Lavet, Mark Neerincx, Piek Vossen
Inspired by the cognitive science theory, we explicitly model an agent with both semantic and episodic memory systems, and show that it is better than having just one of the two memory systems.
Ranked #1 on
RoomEnv-v0
on RoomEnv-v0
no code implementations • 5 Mar 2022 • Alessandro Generale, Till Blume, Michael Cochez
The amount of gradient information that needs to be stored during training for real-world graphs is often too large for the amount of memory available on most GPUs.
no code implementations • 22 Sep 2021 • Christopher Wewer, Florian Lemmerich, Michael Cochez
To utilize information from Knowledge Graphs, many state-of-the-art machine learning approaches use embedding techniques.
1 code implementation • ICLR 2022 • Dimitrios Alivanistos, Max Berrendorf, Michael Cochez, Mikhail Galkin
Besides that, we propose a method to answer such queries and demonstrate in our experiments that qualifiers improve query answering on a diverse set of query patterns.
1 code implementation • 26 Feb 2021 • Leandro Eichenberger, Michael Cochez, Benjamin Heitmann, Stefan Decker
During the protocol, the intersection between the two knowledge graphs is determined in a privacy preserving fashion.
no code implementations • 22 Feb 2021 • Ruud van Bakel, Teodor Aleksiev, Daniel Daza, Dimitrios Alivanistos, Michael Cochez
Structured querying on such incomplete graphs will result in incomplete sets of answers, even if the correct entities exist in the graph, since one or more edges needed to match the pattern are missing.
4 code implementations • ICLR 2021 • Erik Arakelyan, Daniel Daza, Pasquale Minervini, Michael Cochez
Finally, we demonstrate that it is possible to explain the outcome of our model in terms of the intermediate solutions identified for each of the complex query atoms.
Ranked #1 on
Complex Query Answering
on NELL995
2 code implementations • 7 Oct 2020 • Daniel Daza, Michael Cochez, Paul Groth
However, the extent to which these representations learned for link prediction generalize to other tasks is unclear.
Ranked #1 on
Inductive knowledge graph completion
on WN18RR-ind
Inductive knowledge graph completion
Inductive Link Prediction
+9
1 code implementation • 11 Apr 2020 • Md. Rezaul Karim, Bharathi Raja Chakravarthi, John P. McCrae, Michael Cochez
Evaluations against several baseline embedding models, e. g., Word2Vec and GloVe yield up to 92. 30%, 82. 25%, and 90. 45% F1-scores in case of document classification, sentiment analysis, and hate speech detection, respectively during 5-fold cross-validation tests.
1 code implementation • 9 Apr 2020 • Md. Rezaul Karim, Till Döhmen, Dietrich Rebholz-Schuhmann, Stefan Decker, Michael Cochez, Oya Beyan
Amid the coronavirus disease(COVID-19) pandemic, humanity experiences a rapid increase in infection numbers across the world.
2 code implementations • 4 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.
1 code implementation • 6 Feb 2020 • Daniel Daza, Michael Cochez
The generality of our method allows it to encode a more diverse set of query types in comparison to previous work.
no code implementations • 23 Dec 2019 • Michael Ellers, Michael Cochez, Tobias Schumacher, Markus Strohmaier, Florian Lemmerich
In that setting, we analyze whether after the removal of the node from the network and the deletion of the vector representation of the respective node in the embedding significant information about the link structure of the removed node is still encoded in the embedding vectors of the remaining nodes.
1 code implementation • 9 Sep 2019 • Md. Rezaul Karim, Michael Cochez, Oya Beyan, Stefan Decker, Christoph Lange
In this paper, we propose a new approach called OncoNetExplainer to make explainable predictions of cancer types based on GE data.
no code implementations • 6 Sep 2019 • Ruijie Wang, Meng Wang, Jun Liu, Michael Cochez, Stefan Decker
At the core of the construction is to deduce the structure of the target query and determine the vertices/edges which constitute the query.
1 code implementation • 19 Aug 2019 • Svitlana Vakulenko, Javier David Fernandez Garcia, Axel Polleres, Maarten de Rijke, Michael Cochez
We propose a novel approach for complex KGQA that uses unsupervised message passing, which propagates confidence scores obtained by parsing an input question and matching terms in the knowledge graph to a set of possible answers.
no code implementations • 7 Aug 2019 • Andrei Ionita, André Pomp, Michael Cochez, Tobias Meisen, Stefan Decker
Smart cities around the world have begun monitoring parking areas in order to estimate available parking spots and help drivers looking for parking.
1 code implementation • 4 Aug 2019 • Md. Rezaul Karim, Michael Cochez, Joao Bosco Jares, Mamtaz Uddin, Oya Beyan, Stefan Decker
Existing data-driven prediction approaches for DDIs typically rely on a single source of information, while using information from multiple sources would help improve predictions.
no code implementations • 31 Jul 2018 • Martina Garofalo, Maria Angela Pellegrino, Abdulrahman Altabba, Michael Cochez
A natural way to represent the data generated by this large amount of sensors, which are not acting measuring independent variables, and the interaction of the different devices is by using a graph data model.
no code implementations • 31 Jul 2018 • Michael Cochez, Martina Garofalo, Jérôme Lenßen, Maria Angela Pellegrino
Graph embedding models produce embedding vectors for entities and relations in Knowledge Graphs, often without taking literal properties into account.
2 code implementations • 17 Jun 2018 • Svitlana Vakulenko, Maarten de Rijke, Michael Cochez, Vadim Savenkov, Axel Polleres
Conversational systems have become increasingly popular as a way for humans to interact with computers.
4 code implementations • 30 May 2018 • Md. Rezaul Karim, Michael Cochez, Achille Zappa, Ratnesh Sahay, Oya Beyan, Dietrich-Rebholz Schuhmann, Stefan Decker
The study of genetic variants can help find correlating population groups to identify cohorts that are predisposed to common diseases and explain differences in disease susceptibility and how patients react to drugs.
no code implementations • 16 Jul 2016 • Michael Cochez, Stefan Decker, Eric Prud'hommeaux
In this paper we present a practical implementation of a different kind of knowledge representation based on Prototypes.