Filters








44,749 Hits in 8.2 sec

Combining Terms and Named Entities for Modeling Domain Ontologies from Texts

Nouha Omrane, Adeline Nazarenko, Sylvie Szulman
2010 International Conference Knowledge Engineering and Knowledge Management  
Building ontologies from plain texts is still a research issue.  ...  In this paper we present terminae and show through the analysis of three different experiments on policy documents how the initial terminological approach can be guided by taking named entities into account  ...  A COMBINED METHOD FOR BUILDING ONTOLOGIES FROM TEXTS The terminae text-based acquisition method decomposes the acquisition process into three main levels -the terminological, termino-ontological and conceptual  ... 
dblp:conf/ekaw/OmraneNS10 fatcat:y3rsfiepyje2xfxwvtuel66wae

Shallow Neural Network and Ontology-Based Novel Semantic Document Indexing for Information Retrieval

Anil Sharma, Suresh Kumar
2022 Intelligent Automation and Soft Computing  
The SNNOntoSDI approach identifies the concepts representing a document using the word2vec model (a Shallow Neural Network) and domain ontology.  ...  The relevance of a concept in the document is measured by assigning weight to the concept based on its statistical, semantic, and scientific Named Entity features.  ...  fact that the candidate concept belongs to scientific Named Entity for the domain or not [40] .  ... 
doi:10.32604/iasc.2022.026095 fatcat:nvb7wl5fgzc3vponislug7ibyu

BiOnt: Deep Learning using Multiple Biomedical Ontologies for Relation Extraction [article]

Diana Sousa, Francisco M. Couto
2020 arXiv   pre-print
To perform relation extraction, our deep learning system, BiOnt, employs four types of biomedical ontologies, namely, the Gene Ontology, the Human Phenotype Ontology, the Human Disease Ontology, and the  ...  those entities and their inherent mechanisms.  ...  [9] combines 5028 DDIs, from selected texts of the DrugBank database and Medline abstracts.  ... 
arXiv:2001.07139v1 fatcat:dsifxkfeinc7pmv7tgxnfz24iy

BiOnt: Deep Learning Using Multiple Biomedical Ontologies for Relation Extraction [chapter]

Diana Sousa, Francisco M. Couto
2020 Lecture Notes in Computer Science  
To perform relation extraction, our deep learning system, BiOnt, employs four types of biomedical ontologies, namely, the Gene Ontology, the Human Phenotype Ontology, the Human Disease Ontology, and the  ...  those entities and their inherent mechanisms.  ...  [9] combines 5028 DDIs, from selected texts of the DrugBank database and Medline abstracts. Drug-Drug Phenotype-Gene Relations (2).  ... 
doi:10.1007/978-3-030-45442-5_46 fatcat:jvg7zvcg3bcxnm72jhgn75mvku

Using Neural Networks for Relation Extraction from Biomedical Literature [article]

Diana Sousa, Andre Lamurias, Francisco M. Couto
2019 arXiv   pre-print
Thus, biomedical ontologies play a fundamental role by providing semantic and ancestry information about an entity.  ...  The right combination of data representations can eventually lead us to even higher evaluation scores in relation extraction tasks.  ...  Text mining uses IE methods to process text documents. Text mining systems usually include named-entity recognition (NER), named-entity linking (NEL), and relation extraction (RE) tasks.  ... 
arXiv:1905.11391v1 fatcat:uw2nifl7ufamfifi2kx3bx7yey

A Review of Geospatial Semantic Information Modeling and Elicitation Approaches

Margarita Kokla, Eric Guilbert
2020 ISPRS International Journal of Geo-Information  
The present paper provides a review of two research topics that are central to geospatial semantics: information modeling and elicitation.  ...  It discusses the problems and the challenges faced, highlights the types of semantic information formalized and extracted, as well as the methodologies and tools used, and identifies directions for future  ...  LSA is used to capture the semantic context of terms, while ontologies are used to represent domain knowledge and support the extraction of terms from text, as well as the identification of query terms  ... 
doi:10.3390/ijgi9030146 fatcat:e46jighegjhbzfy55u2alfb6um

Ontologies and Information Extraction [article]

Claire Nédellec
2006 arXiv   pre-print
It is not a mere text filtering method based on simple pattern matching and keywords, because the extracted pieces of texts are interpreted with respect to a predefined partial domain model.  ...  This report is mainly illustrated in biology, a domain in which there are critical needs for content-based exploration of the scientific literature and which becomes a major application domain for IE.  ...  Sets of entities Recognizing and classifying named entities in texts require knowledge on the domain entities.  ... 
arXiv:cs/0609137v1 fatcat:s5374ygzwzbnxp2ejzq2wmxw3a

Scenario-Driven Selection and Exploitation of Semantic Data for Optimal Named Entity Disambiguation

Panos Alexopoulos, Carlos Ruiz, José Manuél Gómez-Pérez
2012 International Conference Knowledge Engineering and Knowledge Management  
The rapidly increasing use of large-scale data on the Web has made named entity disambiguation a key research challenge in Information Extraction (IE) and development of the Semantic Web.  ...  in open domain and unconstrained situations.  ...  Acknowledgements This work was supported by the Spanish project CENIT-2009-1026 BuscaMedia and by the European Commission under contract FP7-248984 GLOCAL.  ... 
dblp:conf/ekaw/AlexopoulosRG12 fatcat:ig5eiaa7srhjhh6uvrb3o3umfu

Extracting Semantics from Maintenance Records [article]

Sharad Dixit, Varish Mulwad, Abhinav Saxena
2021 arXiv   pre-print
Rapid progress in natural language processing has led to its utilization in a variety of industrial and enterprise settings, including in its use for information extraction, specifically named entity recognition  ...  entities of interest from maintenance records.  ...  We address these challenges by developing approaches for extracting and capturing semantics from MX records comprising of entity and relation extraction techniques that combine ontology-driven extraction  ... 
arXiv:2108.05454v1 fatcat:2e5eewmllngm7hit2cm4iyerja

An Ontology-based Name Entity Recognition NER and NLP Systems in Arabic Storytelling

Marwa Elgamal, Mohamed Abou-Kreisha, Reda Abo Elezz, Salwa Hamada
2020 Al-Azhar Bulletin of Science  
This paper intends to investigate the problem of automatically construct and build an Arabic storytelling ontology based on Arabic named entity recognition (NER) from unstructured story text.  ...  In this work, a practical methodology presented for Arabic Storytelling ontology construction for domain ontology extraction from unstructured Arabic story documents.  ...  domain model.  ... 
doi:10.21608/absb.2020.44367.1088 fatcat:al6yof2kozajvot77cta2globe

Ontology-based Entity Recognition and Annotation

Thomas Hoppe, Jamal Al Qundus, Silvio Peikert
2020 Conference on Digital Curation Technologies  
of entities in highly specialized domains and describe our approach to ontology-based entity recognition and annotation (OER).  ...  While Named Entity Recognition (NER) is an important task for the extraction of factual information and the construction of knowledge graphs, other information such as terminological concepts and relations  ...  about named entities.  ... 
dblp:conf/qurator/HoppeQP20 fatcat:z5to2bp7ebednlmgpvctt7ow2m

An Overview of Ontology Learning Process from Arabic Text

Mariam Muhammed, Nesrine Azim, Mervat Gheith
2020 The Egyptian Journal of Language Engineering  
Most of these works focused on three main issues: extracting the terms, extracting the semantic relations, and building the ontology from the Arabic text.  ...  There is a lot of research work interested in Ontology Learning for Arabic texts.  ...  TERM EXTRACTION Term extraction extracts the relevant phrases and terms from the text for a specific domain by applying information extraction (IE) methods to extract terms.  ... 
doi:10.21608/ejle.2020.19841.1000 fatcat:s3fe6obmnjdixlr4zqvhtcepsu

Challenges in Information Retrieval from Unstructured Arabic Data

Hussein Khalil, Taha Osman
2014 2014 UKSim-AMSS 16th International Conference on Computer Modelling and Simulation  
This paper investigates the Semantic Web (SW) support for handling documents that are authored and/or annotated in Arabic, and how to bridge the gap between the SW and Natural Language Processing (NLP)  ...  Moreover, to improve the intelligent exploration of unstructured documents in the Arabic domain.  ...  In the Arabic language, domain, for example, there are many approaches to address the extraction of terms. Oudah and Mai developed a new system called Named Entity Recognition Arabic (NERA).  ... 
doi:10.1109/uksim.2014.115 dblp:conf/uksim/KhalilO14 fatcat:qkys7hsn6zcehj3ubxdrzhpwfm

KGen: a knowledge graph generator from biomedical scientific literature

Anderson Rossanez, Julio Cesar dos Reis, Ricardo da Silva Torres, Hélène de Ribaupierre
2020 BMC Medical Informatics and Decision Making  
Our method links entities and relations represented in KGs to concepts from existing biomedical ontologies available on the Web.  ...  Conclusions We demonstrate that our proposal is effective on building ontology-linked KGs representing the knowledge obtained from biomedical scientific texts.  ...  For instance, named entity recognition explored ScispaCy's models that are targeted for biomedical texts.  ... 
doi:10.1186/s12911-020-01341-5 pmid:33317512 fatcat:gkn23t5lp5eqpnrjoioiqtxrom

NeuroNames: An Ontology for the BrainInfo Portal to Neuroscience on the Web

Douglas M. Bowden, Evan Song, Julia Kosheleva, Mark F. Dubach
2011 Neuroinformatics  
The ontology is maintained in a relational database with three core tables: Names, Concepts and Models.  ...  The ontology of NeuroNames accommodates synonyms and homonyms of the standard terms in many languages.  ...  The work was supported by the International Neuroinformatics Coordinating Facility (INCF) and by grants LM-008247, MH-069259 and RR-000166 from the U.S.  ... 
doi:10.1007/s12021-011-9128-8 pmid:21789500 pmcid:PMC3247656 fatcat:leit4jbkzjhsbmbtj656w3ux6y
« Previous Showing results 1 — 15 out of 44,749 results