26,978 Hits in 9.7 sec

Improving Relation Extraction by Using an Ontology Class Hierarchy Feature [chapter]

Pedro H. R. Assis, Marco A. Casanova, Alberto H. F. Laender, Ruy Milidiu
2015 Lecture Notes in Computer Science  
This paper proposes a new ontology class hierarchy feature to improve relation extraction when applying a method based on the distant supervision approach.  ...  It argues in favour of the expressiveness of the feature, in multi-class perceptrons, by experimentally showing its effectiveness when compared with combinations of (regular) lexical features.  ...  Conclusions In this paper, we introduced a feature defined by ontology class hierarchies to improve relation extraction methods based on the distant supervision approach.  ... 
doi:10.1007/978-3-319-26187-4_20 fatcat:jvchi25x5jhmhpg43lp6y4twxy

Distant Supervision for Relation Extraction Using Ontology Class Hierarchy-Based Features [chapter]

Pedro H. R. Assis, Marco A. Casanova
2014 Lecture Notes in Computer Science  
In particular, the classifier uses a feature based on the class hierarchy of an ontology that, in conjunction with basic lexical features, improves accuracy and recall.  ...  The paper contains extensive experiments, using a corpus extracted from the Wikipedia and the DBpedia ontology, to demonstrate the usefulness of the new feature.  ...  In particular, the classifier uses a feature based on the class hierarchy of an ontology that, in conjunction with basic lexical features, improves accuracy and recall.  ... 
doi:10.1007/978-3-319-11955-7_68 fatcat:qfrjdxdyujcptnfirpowko7eie

Automatic Extraction of Hierarchical Relations from Text [chapter]

Ting Wang, Yaoyong Li, Kalina Bontcheva, Hamish Cunningham, Ji Wang
2006 Lecture Notes in Computer Science  
The results show there is a trade-off among these factors for relation extraction and the features containing more information such as semantic ones can improve the performance of the ontological relation  ...  Automatic extraction of semantic relationships between entity instances in an ontology is useful for attaching richer semantic metadata to documents.  ...  The ACE2004 Relation Hierarchy In an ontology, the concepts are not only organised in a taxonomy representing IS-A relations, but also linked together by semantic relations such as Part-Whole, Subsidiary  ... 
doi:10.1007/11762256_18 fatcat:fknmei4gezdznev7fdxibrei6i

New-Fangled Alignment of Ontologies for Content Based Semantic Image Retrieval

Anuja khodaskar, Siddarth Ladhake
2015 Procedia Computer Science  
To overcome this weakness, proposed image retrieval system designed using core semantic multiple ontology which merges feature ontology, semantic feature ontology, user ontology and metadata ontology.  ...  This paper highlights content based image retrieval system using alignment of ontologies. The traditional contents-based image retrieval systems using single ontology retrieve imprecise images.  ...  Ontologies are often equated with taxonomic hierarchies of classes, class definitions, and the subsumption relation.  ... 
doi:10.1016/j.procs.2015.04.185 fatcat:zxe7fjinmbeo3ptokasdqkftoa

Leveraging Machine Learning to Extend Ontology-Driven Geographic Object-Based Image Analysis (O-GEOBIA): A Case Study in Forest-Type Mapping

Sachit Rajbhandari, Jagannath Aryal, Jon Osborn, Arko Lucieer, Robert Musk
2019 Remote Sensing  
Using relevant features extracted from the Boruta algorithm, the classification accuracy is further improved (82.57%).  ...  The results demonstrate that the use of relevant variogram features together with spectral and LiDAR features resulted in improved classification accuracy.  ...  The semantic relations approach is based on the semantic relations between classes and uses an ontology. A semantic variogram is used for this approach.  ... 
doi:10.3390/rs11050503 fatcat:fr5mort43vcblckcgej4psgvni

DOG I : An Annotation System for Images of Dog Breeds [chapter]

Antonios Dimas, Pyrros Koletsis, Euripides G. M. Petrakis
2012 Lecture Notes in Computer Science  
Annotation relies on feature extraction and on associating low-level features with image concepts in an ontology.  ...  Evaluation results are realized using images collected from the Web. Almost 95% of the test images is correctly annotated (i.e., DOGI identified their class correctly).  ...  Class descriptions are complemented by an enhanced set of low-level features extracted from the image instances of the class.  ... 
doi:10.1007/978-3-642-31295-3_48 fatcat:ba43tsichfgm7oew7bc7szoo4i

Sentiment-Based Semantic Rule Learning for Improved Product Recommendations [chapter]

Dandibhotla Teja Santosh, Bulusu Vishnu Vardhan
2018 Machine Learning - Advanced Techniques and Emerging Applications  
These parent features are present at the higher level near the root of the ontology. The sentiments of the related product features are also improved.  ...  This approach improves the sentiments of the parent features and the related features that eventually improve the aggregated sentiment of the product.  ...  Author details Figure 1 . 1 Class hierarchies and related classes in PROO. Figure 2 . 2 Model for improving the sentiments of the product features.  ... 
doi:10.5772/intechopen.72514 fatcat:qlsvcr33dzgqjepsoixcbkzj7y

Exploring Reasoning with the DMOP Ontology

C. Maria Keet, Claudia d'Amato, Zubeida Casmod Khan, Agnieszka Lawrynowicz
2014 International Workshop on OWL Reasoner Evaluation  
The choices made led to v5.4 of the DMOP ontology. We report some evaluations on processing DMOP with a standard reasoner by considering different DMOP features.  ...  We describe the Data Mining OPtimization Ontology (DMOP), which was developed to support informed decision-making at various choice points of the knowledge discovery (KD) process.  ...  The top levels of the algorithm hierarchy match those of the task hierarchy, since each algorithm class is defined by the task it addresses, but the overall hierarchy is much deeper, since there is an  ... 
dblp:conf/ore/KeetdKL14 fatcat:enjgk6vanrdhlp5ypafljolnui

Ontology-Driven Cross-Domain Transfer Learning [chapter]

Mattia Fumagalli, Gábor Bella, Samuele Conti, Fausto Giunchiglia
2020 Frontiers in Artificial Intelligence and Applications  
We show that ontologies, if properly designed, are able to support transfer learning by improving generalization and discrimination across classes.  ...  We validate the solution on an experiment over an image classification task, demonstrating the system's improved classification performance.  ...  This paper was supported by the WeNet project, funded by the European Union (EU) Horizon 2020 programme under grant number 823783.  ... 
doi:10.3233/faia200676 fatcat:7o3vjapgqjbd7emszxpzutmzce

Classifying Biomedical Text Abstracts Based On Hierarchical 'Concept' Structure

Rozilawati Binti Dollah, Masaki Aono
2011 Zenodo  
In this paper, we present an approach for classifying a collection of biomedical text abstracts downloaded from Medline database with the help of ontology alignment.  ...  Then, we enrich the OHSUMED disease hierarchy before adapting it to ontology alignment process for finding probable concepts or categories.  ...  ACKNOWLEDGMENT This work was supported in part by Global COE Program "Frontiers of Intelligent Sensing" from the Ministry of Education, Culture, Sports, Science and Technology, Japan.  ... 
doi:10.5281/zenodo.1080995 fatcat:zjjn3mx6z5ax5jkvvxl72w5suq

Ontology extraction from relational database: Concept hierarchy as background knowledge

Heru Agus Santoso, Su-Cheng Haw, Ziyad.T. Abdul-Mehdi
2011 Knowledge-Based Systems  
This paper proposed the approach for ontology extraction on top of RDB by incorporating concept hierarchy as background knowledge.  ...  Relational Database (RDB) has been widely used as the back-end database of information system.  ...  The following are the rules for mapping (1) If there is an is -a relation between r 1 and r 2 represented by binary relation, and the associated classes of them are connected by an edge in a concept hierarchy  ... 
doi:10.1016/j.knosys.2010.11.003 fatcat:omsiivrjrzc4jkqqb4j7ktupcq

Concept Hierarchy Extraction from Legal Literature

Sabine Wehnert, David Broneske, Stefan Langer, Gunter Saake
2018 International Conference on Information and Knowledge Management  
Since different authors have their own notion of hierarchy given by the table of con-tents, we propose a heterogeneous lightweight ontology allowing for the coexistence of similar, yet diverse concept  ...  Starting with rule-based annotation, we cluster extracted references, given their context features derived from tables of contents and reasons for citing from various textbook formats.  ...  The work is supported by Legal Horizon AG, Grant No.:1704/00082  ... 
dblp:conf/cikm/WehnertBLS18 fatcat:hs56kcg5offy5avbat6eihtxtu

Exploring binary relations for ontology extension and improved adaptation to clinical text [article]

Luke T Slater, Robert Hoehndorf, Andreas Karwath, Georgios V Gkoutos
2020 bioRxiv   pre-print
The controlled domain vocabularies provided by ontologies make them an indispensable tool for text mining.  ...  Results: We develop and present a framework for identifying new classes in text corpora, which can be integrated into existing ontology hierarchies.  ...  Description of our workflow to extract new classes from a corpus by annotating a text, and examining binary relations. 3/11 .  ... 
doi:10.1101/2020.12.04.411751 fatcat:nkqstiv5cvb5bkionx5luu4z6i

KOSIMap: Use of Description Logic Reasoning to Align Heterogeneous Ontologies

Quentin Reul, Jeff Z. Pan
2010 International Workshop on Description Logics  
In this paper, we describe the Knowledge Organisation System Implicit Mapping (KOSIMap) framework, which differs from existing ontology mapping approaches by using description logic reasoning (i) to extract  ...  Such interoperability can be achieved by identifying similar information in heterogeneous ontologies.  ...  Thus, this further suggests that the use of the implicit hierarchy improves the coverage of the ontology mapping task.  ... 
dblp:conf/dlog/ReulP10 fatcat:knk722ur5bb3xkqbxljiqpb374

Product Domain Ontology Construction: Based on Online Review Features and Opinion Quintuple

2020 DEStech Transactions on Engineering and Technology Research  
This study extracts domain concepts both from professional and user-generated contents. All elements in opinion quintuple are expressed in the ontology.  ...  Based on the current literature research of online review and opinion mining demand, this paper focus on ontology construction in ontology-based opinion mining procedure to improve the effect of opinion  ...  Acknowledgement This work was financially supported by the Jiangasu Provience Social Science Foundation (16TQB009) and Jiangsu Provience University Philosophy and Social Science Foundation (2017SJB1892  ... 
doi:10.12783/dtetr/amee2019/33483 fatcat:6gsiakwvszhxzovmanp2t2yvce
« Previous Showing results 1 — 15 out of 26,978 results