Filters








5,589 Hits in 6.9 sec

On the Integration of Knowledge Graphs into Deep Learning Models for a More Comprehensible AI—Three Challenges for Future Research

Giuseppe Futia, Antonio Vetrò
2020 Information  
Within such a general direction, we identify three specific challenges for future research—knowledge matching, cross-disciplinary explanations and interactive explanations.  ...  In this context, Knowledge Graphs (KGs) and their underlying semantic technologies are the modern implementation of symbolic AI—while being less flexible and robust to noise compared to deep learning models  ...  for the deep learning model comparison, based on KGs and ontologies, to enable proper validation strategies.  ... 
doi:10.3390/info11020122 fatcat:77ni2i6tdrhqxopw25vbybghi4

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

Diana Sousa, Andre Lamurias, Francisco M. Couto
2019 arXiv   pre-print
The use of multichannel architectures composed of multiple data representations, as in deep neural networks, is leading to state-of-the-art results.  ...  Thus, biomedical ontologies play a fundamental role by providing semantic and ancestry information about an entity.  ...  learning (feature-based, kernel-based, and recurrent neural networks (RNN)).  ... 
arXiv:1905.11391v1 fatcat:uw2nifl7ufamfifi2kx3bx7yey

Toward a Deep Neural Approach for Knowledge-Based IR [article]

Gia-Hung Nguyen, Lynda Tamine, Laure Soulier, Nathalie Bricon-Souf
2016 arXiv   pre-print
In this paper, we review the main approaches of neural-based document ranking as well as those approaches for latent representation of entities and relations via KBs.  ...  In this context, knowledge bases (KBs) have already been acknowledged as valuable means since they allow the representation of explicit relations between entities.  ...  Then, with a deep architecture, the model will learn the raw representation as a latent semantic feature vector for each entity (document, query, and knowledge-based bridge).  ... 
arXiv:1606.07211v1 fatcat:jdypcyno3zcwphnoclk44dsfxi

A Method about Building Deep Knowledge Graph for the Plant Insect Pest and Disease (DKG-PIPD)

Yingying Liu
2021 IEEE Access  
relationship extraction and knowledge inference using deep learning are emphatically introduced.  ...  In this study, a method about building Deep Knowledge Graph for the Plant Insect Pest and Disease, namely DKG-PIPD, was proposed.  ...  KNOWLEDGE INFERENCE USING DEEP LEARNING The main idea of knowledge inference based on deep learning is to use the learning ability and generalization ability of the neural network to model the fact tuple  ... 
doi:10.1109/access.2021.3116467 fatcat:vyoluv7ln5ebnlrm3ogut32eoa

The design and implementation of Language Learning Chatbot with XAI using Ontology and Transfer Learning [article]

Nuobei Shi, Qin Zeng, Raymond Lee
2020 arXiv   pre-print
of neural network in bionics, and explain the output sentence from language model.  ...  In this paper, we proposed a transfer learning-based English language learning chatbot, whose output generated by GPT-2 can be explained by corresponding ontology graph rooted by fine-tuning dataset.  ...  ACKNOWLEDGEMENTS The authors would like to thank for UIC DST for the provision of computer equipment and facilities. This project is supported by UIC research grant R202008.  ... 
arXiv:2009.13984v1 fatcat:jrt6rykpsngejnvndgjzbcfxqa

A Framework for Service Semantic Description Based on Knowledge Graph

Qitong Sun, Jun Han, Dianfu Ma
2021 Electronics  
We constructed two experimental data sets, then designed and trained two different deep neural networks for the two tasks to extract the semantics of the natural language used in the service discovery  ...  We insist on the information of services described by Web Services Description Language (WSDL) and we design the ontology layer of web service knowledge graph and construct the service graph, and using  ...  Then, the word representations are used to compose a similarity matrix, which will be taken as the input for the CNN to learn the matching relationships.  ... 
doi:10.3390/electronics10091017 doaj:277ff9012ecc45eab2917f7047427584 fatcat:agwdan63aner3ls3dqzm4ntbwq

ERSOM: A Structural Ontology Matching Approach Using Automatically Learned Entity Representation

Chuncheng Xiang, Tingsong Jiang, Baobao Chang, Zhifang Sui
2015 Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing  
We propose in this paper an ontology matching approach, named ERSOM, which mainly includes an unsupervised representation learning method based on the deep neural networks to learn the general representation  ...  As a key representation model of knowledge, ontology has been widely used in a lot of NLP related tasks, such as semantic parsing, information extraction and text mining etc.  ...  The corresponding authors of this paper are Baobao Chang and Zhifang Sui.  ... 
doi:10.18653/v1/d15-1289 dblp:conf/emnlp/XiangJCS15 fatcat:2adcynkzrjbj5puxhoyd5omfba

Enhancing Question Answering by Injecting Ontological Knowledge through Regularization

Travis Goodwin, Dina Demner-Fushman
2020 Proceedings of Deep Learning Inside Out (DeeLIO): The First Workshop on Knowledge Extraction and Integration for Deep Learning Architectures  
In this paper, we present OSCR (Ontology-based Semantic Composition Regularization), a method for injecting task-agnostic knowledge from an Ontology or knowledge graph into a neural network during pre-training  ...  Deep neural networks have demonstrated high performance on many natural language processing (NLP) tasks that can be answered directly from text, and have struggled to solve NLP tasks requiring external  ...  National Library of Medicine, National Institutes of Health, and utilized the computational resources of the NIH HPC Biowulf cluster (http://hpc.nih.gov).  ... 
doi:10.18653/v1/2020.deelio-1.7 pmid:33364628 pmcid:PMC7757122 fatcat:emypfyo6hfdr5ebkoji52qgnma

Bridging the gap between an ontology and deep neural models by pattern mining

Tomas Martin, Abdoulaye Baniré Diallo, Petko Valtchev, René Lacroix
2020 Joint Ontology Workshops  
We propose to use ontology-rooted graph patterns mined from a DO-compatible graph translation of the raw data as a vector for injecting some domain knowledge into the neural network.  ...  Such patterns represent a frequently occurring regularities in the data yet they are expressed in terms of the ontological entities (classes, properties, etc.) and reflect additional knowledge from the  ...  ANN-based representations constitute an alternative knowledge capture tool [12] .  ... 
dblp:conf/jowo/MartinDVL20 fatcat:ozvoxlu56zdotfu3xr3owz4sea

BO-LSTM: classifying relations via long short-term memory networks along biomedical ontologies

Andre Lamurias, Diana Sousa, Luka A. Clarke, Francisco M. Couto
2019 BMC Bioinformatics  
Recent studies have proposed deep learning techniques, namely recurrent neural networks, to improve biomedical text mining tasks.  ...  We implemented BO-LSTM as a recurrent neural network with long short-term memory units and using open biomedical ontologies, specifically Chemical Entities of Biological Interest (ChEBI), Human Phenotype  ...  Availability of data and materials The data and code used for this study are available at https://github.com/ lasigeBioTM/BOLSTM.  ... 
doi:10.1186/s12859-018-2584-5 fatcat:2c2faf4jengjdf7eptr2nqfxgu

Learning adaptive representations for entity recognition in the biomedical domain

Ivano Lauriola, Fabio Aiolli, Alberto Lavelli, Fabio Rinaldi
2021 Journal of Biomedical Semantics  
Two mechanisms have been considered to perform the combination, which are neural networks and Multiple Kernel Learning.  ...  Results This paper investigates methods to learn the best representation from data directly, by combining several knowledge-based representations and word embeddings.  ...  See [45] for a recent and exhaustive survey on deep and neural network based NER methods.  ... 
doi:10.1186/s13326-021-00238-0 pmid:34001263 fatcat:bw76dwrw3rcfxjj676mw5rdg2y

Self-normalizing learning on biomedical ontologies using a deep Siamese neural network [article]

Fatima Zohra Smaili, Xin Gao, Robert Hoehndorf
2020 biorxiv/medrxiv   pre-print
The normalized ontologies and text are then used to generate embeddings, and relations between entities are predicted using a deep Siamese neural network model that takes these embeddings as input.  ...  Motivation:Ontologies are widely used in biomedicine for the annotation and standardization of data.One of the main roles of ontologies is to provide structured background knowledge within a domain as  ...  FCC/1/1976-04, FCC/1/1976-06, FCC/1/1976-17, FCC/1/1976-18, FCC/1/1976-23, FCC/1/1976-25, FCC/1/1976, URF/1/3450-01 and URF/1/3454-01.  ... 
doi:10.1101/2020.04.23.057117 fatcat:qr5yw7n4ajhxxebpxzjtcodhde

Construction and Research on Chinese Semantic Mapping Based on Linguistic Features and Sparse Self-Learning Neural Networks

Haiping Zhang, Bo Chao, Zhijing Huang, Tingyu Li, Gengxin Sun
2022 Computational Intelligence and Neuroscience  
The model uses deep memory networks and capsule networks to construct a transfer learning framework and effectively leverages the transfer learning properties of capsule networks to transfer knowledge  ...  of the network term entity and relational attribute recognition extraction and makes the knowledge map constructed in this paper.  ...  for windowed Chinese character sequences, and based on the idea of pointby-point mutual information, a matching lexical entity representation is sought for each cut, and the feature discovery of the cut  ... 
doi:10.1155/2022/2315802 pmid:35769283 pmcid:PMC9236845 fatcat:pwd5ryxrhzay3lnvmyxa2duvyi

A comprehensive survey of entity alignment for knowledge graphs

Kaisheng Zeng, Chengjiang Li, Lei Hou, Juanzi Li, Ling Feng
2021 AI Open  
This paper investigated almost all the latest knowledge graph representations learning and entity alignment methods and summarized their core technologies and features from different aspects.  ...  A B S T R A C T Knowledge Graphs (KGs), as a structured human knowledge, manage data in an ease-of-store, recognizable, and understandable way for machines and provide a rich knowledge base for different  ...  Graph neural networks-based models Graph Neural Networks (GNNs) is a new hot spot for deep learning researchers in recent years.  ... 
doi:10.1016/j.aiopen.2021.02.002 fatcat:mj2ens2perb5jn5koxdvjmryii

DAEOM: A Deep Attentional Embedding Approach for Biomedical Ontology Matching

Jifang Wu, Jianghua Lv, Haoming Guo, Shilong Ma
2020 Applied Sciences  
Firstly, these methods only focus on the terminological-based features to learn word vectors for discovering mappings, ignoring the network structure of ontology.  ...  Representation learning techniques have been introduced to the field of OM with the development of deep learning. However, there still exist two limitations.  ...  We based our ontology embedding architecture on Bert, Graph Attention Networks, and Siamese Neural Networks.  ... 
doi:10.3390/app10217909 fatcat:zqpshggw5jel5dqtuzwsqkboxy
« Previous Showing results 1 — 15 out of 5,589 results