Farhad Abedini
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Farhad Abedini has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Mohammad Reza Keyvanpour
Department of Computer Engineering, Faculty of Engineering, Alzahra University, Tehran, Iran
4 shared publications - Mohammad Bagher Menhaj
Department of Electrical Engineering, Amirkabir University of Technology, Tehran, Iran
3 shared publications - Seyedeh Masoumeh Mirhashem3 shared publications
- Fariborz Mahmoudi2 shared publications
- Amir Hossein Jadidinejad1 shared publication
Mohammad Bagher Menhaj
Center of Excellence in Control and Robotics, Electrical Engineering Department, Amirkabir University of Technology, 424, Hafez Ave., Tehran, Iran
1 shared publication
Latest Publications
- 8 January 2020
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 34 (10)
Correction Tower: A General Embedding Method of the Error Recognition for the Knowledge Graph Correction
Today, knowledge graphs (KGs) are growing by enrichment and refinement methods. The enrichment and refinement can be gained using the correction and completion of the KG. The studies of the KG completion are rich, but less attention has been paid to the methods of the KG error correction. The correction methods are divided into embedding and nonembedding methods. Embedding correction methods have been recently introduced in which a KG is embedded into a vector space. Also, existing correction approaches focused on the recognition of the three types of errors, the outliers, inconsistencies and erroneous relations. One of the challenges is that most outlier correction methods can recognize only numeric outlier entities by nonembedding methods. On the other hand, inconsistency errors are recognized during the knowledge extraction step and existing methods of this field do not pay attention to the recognition of these errors as post-correction by embedding methods. Also, to correct erroneous relations, new embedding techniques have not been used. Since the errors of a KG are variant and there is no method to cover all of them, a new general correction method is proposed in this paper. This method is called correction tower in which these three error types are corrected in three trays. In this correction tower, a new configuration will be suggested to solve the above challenges. For this aim, a new embedding method is proposed for each tray. Finally, the evaluation results show that the proposed correction tower can improve the KG error correction methods and proposed configuration can outperform previous results.
- 8 January 2020
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 34 (10)
Correction Tower: A General Embedding Method of the Error Recognition for the Knowledge Graph Correction
Today, knowledge graphs (KGs) are growing by enrichment and refinement methods. The enrichment and refinement can be gained using the correction and completion of the KG. The studies of the KG completion are rich, but less attention has been paid to the methods of the KG error correction. The correction methods are divided into embedding and nonembedding methods. Embedding correction methods have been recently introduced in which a KG is embedded into a vector space. Also, existing correction approaches focused on the recognition of the three types of errors, the outliers, inconsistencies and erroneous relations. One of the challenges is that most outlier correction methods can recognize only numeric outlier entities by nonembedding methods. On the other hand, inconsistency errors are recognized during the knowledge extraction step and existing methods of this field do not pay attention to the recognition of these errors as post-correction by embedding methods. Also, to correct erroneous relations, new embedding techniques have not been used. Since the errors of a KG are variant and there is no method to cover all of them, a new general correction method is proposed in this paper. This method is called correction tower in which these three error types are corrected in three trays. In this correction tower, a new configuration will be suggested to solve the above challenges. For this aim, a new embedding method is proposed for each tray. Finally, the evaluation results show that the proposed correction tower can improve the KG error correction methods and proposed configuration can outperform previous results.
- 8 July 2019
- Published by Taylor & Francis in IETE Journal of Research
- Vol. 68 (2) , 1043-1055
EPCI: An Embedding Method for Post-Correction of Inconsistency in the RDF Knowledge Bases
There are many methods for the RDF knowledge base correction in which errors are detected and then deleted or repaired if necessary. Although most of them do only detection and deletion of the errors and do not pay attention to repair. There are only a few methods to repair these errors that their accuracy is not acceptable. To solve this problem, a method will be proposed with a suitable accuracy that is called EPCI. The focus of EPCI is on inconsistency errors correction because previous correction methods have paid less attention to these kinds of errors. Most of its existing studies avoid these errors before knowledge base creation in the form of pre-correction. Although in some cases, it is needed to correct these errors after its creation as post-correction. For this reason, in EPCI a post-correction method is proposed for this objective. In the studied post-correction methods so far it has not been mentioned that inconsistency can be solved with the embedding methods and most of them solved only numeric inconsistencies. Nowadays, embedding methods are rapidly growing with high precision. So in EPCI, this technique will be used to solve also the problem of non-numeric inconsistent triples.
- 8 July 2019
- Published by Taylor & Francis in IETE Journal of Research
- Vol. 68 (2) , 1043-1055
EPCI: An Embedding Method for Post-Correction of Inconsistency in the RDF Knowledge Bases
There are many methods for the RDF knowledge base correction in which errors are detected and then deleted or repaired if necessary. Although most of them do only detection and deletion of the errors and do not pay attention to repair. There are only a few methods to repair these errors that their accuracy is not acceptable. To solve this problem, a method will be proposed with a suitable accuracy that is called EPCI. The focus of EPCI is on inconsistency errors correction because previous correction methods have paid less attention to these kinds of errors. Most of its existing studies avoid these errors before knowledge base creation in the form of pre-correction. Although in some cases, it is needed to correct these errors after its creation as post-correction. For this reason, in EPCI a post-correction method is proposed for this objective. In the studied post-correction methods so far it has not been mentioned that inconsistency can be solved with the embedding methods and most of them solved only numeric inconsistencies. Nowadays, embedding methods are rapidly growing with high precision. So in EPCI, this technique will be used to solve also the problem of non-numeric inconsistent triples.
- 16 April 2019
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 33 (7) , 656-667
Neural Tensor Network Training Using Meta-Heuristic Algorithms for RDF Knowledge Bases Completion
Neural tensor network (NTN) has been recently introduced to complete Resource Description Framework (RDF) knowledge bases, which has been the state-of-the-art in the field so far. An RDF knowledge base includes some facts from the real world shown as RDF “triples.” In the previous methods, an objective function has been used for training this type of network, and the network parameters should have been set in a way to minimize the function. For this purpose, a classic nonlinear optimization method has been used. Since many replications are needed in this method to get the minimum amount of the function, in this paper, we suggest to combine meta-heuristic optimization methods to minimize the replications and increase the speed of training consequently. So, this problem will be improved using some meta-heuristic algorithms in this new approach to specify which algorithm will get the best results on NTN and its results will be compared with the results of the former methods finally.
- 16 April 2019
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 33 (7) , 656-667
Neural Tensor Network Training Using Meta-Heuristic Algorithms for RDF Knowledge Bases Completion
Neural tensor network (NTN) has been recently introduced to complete Resource Description Framework (RDF) knowledge bases, which has been the state-of-the-art in the field so far. An RDF knowledge base includes some facts from the real world shown as RDF “triples.” In the previous methods, an objective function has been used for training this type of network, and the network parameters should have been set in a way to minimize the function. For this purpose, a classic nonlinear optimization method has been used. Since many replications are needed in this method to get the minimum amount of the function, in this paper, we suggest to combine meta-heuristic optimization methods to minimize the replications and increase the speed of training consequently. So, this problem will be improved using some meta-heuristic algorithms in this new approach to specify which algorithm will get the best results on NTN and its results will be compared with the results of the former methods finally.
- 23 June 2017
- Published by Springer Nature in Neural Computing and Applications
- Vol. 31 (S2) , 1135-1144
An MLP-based representation of neural tensor networks for the RDF data models
- 23 June 2017
- Published by Springer Nature in Neural Computing and Applications
- Vol. 31 (S2) , 1135-1144
An MLP-based representation of neural tensor networks for the RDF data models
- 1 January 2013
- Published by IACSIT Press in International Journal of Computer Theory and Engineering
- p. 432-435
Entity Disambiguation in Text by YAGO Ontology
- 1 January 2013
- Published by IACSIT Press in International Journal of Computer Theory and Engineering
- p. 432-435
Entity Disambiguation in Text by YAGO Ontology
- 1 January 2012
- Published by EJournal Publishing in International Journal of Machine Learning and Computing
- p. 183-187
From Text to Facts: Recognizing Ontological Facts for a New Application
- 1 January 2012
- Published by EJournal Publishing in International Journal of Machine Learning and Computing
- p. 183-187
From Text to Facts: Recognizing Ontological Facts for a New Application
- 1 January 2012
- Published by EJournal Publishing in International Journal of Machine Learning and Computing
- p. 178-182
Using Semantic Entity Extraction Method for a New Application
- 1 January 2012
- Published by EJournal Publishing in International Journal of Machine Learning and Computing
- p. 178-182
Using Semantic Entity Extraction Method for a New Application
- 1 January 2011
- Published by EJournal Publishing in International Journal of Machine Learning and Computing
- p. 113-119
From Text to Knowledge: Semantic Entity Extractionusing YAGO Ontology
- 1 January 2011
- Published by EJournal Publishing in International Journal of Machine Learning and Computing
- p. 113-119
From Text to Knowledge: Semantic Entity Extractionusing YAGO Ontology