Filters








6,657 Hits in 8.1 sec

Mining Semantic Structures from Syntactic Structures in Free Text Documents

Hamid Mousavi, Deirdre Kerr, Markus Iseli, Carlo Zaniolo
2014 2014 IEEE International Conference on Semantic Computing  
Our framework, SemScape, uses a statistical parser to generate few of the most probable parse trees for each sentence and employs a novel two-step pattern-based technique to extract from parse trees candidate  ...  Moreover, SemScape resolves coreferences by a novel technique, generates domain-specific TextGraphs by consulting ontologies, and provides a SPARQL-like query language and an optimized engine for semantically  ...  designed to extract knowledge from text by combining graph-based and statistical methods.  ... 
doi:10.1109/icsc.2014.31 dblp:conf/semco/MousaviKIZ14 fatcat:5omm44j6gzg7jbtssxhmeyp4mm

GPU-based Commonsense Paradigms Reasoning for Real-Time Query Answering and Multimodal Analysis [article]

Nguyen Ha Tran, Erik Cambria
2018 arXiv   pre-print
In addition, in order to ex- tract important textual features from multimodal sources we generate domain-specific graphs based on commonsense knowledge and apply GPU-based graph traversal for fast feature  ...  We utilize commonsense knowledge bases to address the problem of real- time multimodal analysis.  ...  -We introduce a GPU implementation of Bloom Filter algorithm for detecting triple duplication when performing the inference rules which generate a large number of new triples.  ... 
arXiv:1807.08804v1 fatcat:xu5m2oh55ndahct7rtrbecjz3m

Application of concepts of neighbours to knowledge graph completion1

Sébastien Ferré, Tobias Kuhn
2020 Data Science  
Acknowledgements I kindly thank the reviewers for their insightful remarks, and valuable suggestions, which contributed to significantly improve this paper.  ...  Ferré / Application of concepts of neighbors to knowledge graph completion Theoretical definitions We start by defining graph concepts, introduced in Graph-FCA [10] , which is a generalization of Formal  ...  Ferré / Application of concepts of neighbors to knowledge graph completion higher the correct node is in the ranking, the better the prediction is.  ... 
doi:10.3233/ds-200030 fatcat:yltciq6slbg2lctlpy3fxnqrpm

Mandolin: A Knowledge Discovery Framework for the Web of Data [article]

Tommaso Soru, Diego Esteves, Edgard Marx, Axel-Cyrille Ngonga Ngomo
2017 arXiv   pre-print
Our framework imports knowledge from referenced graphs, creates similarity relationships among similar literals, and relies on state-of-the-art techniques for rule mining, grounding, and inference computation  ...  In this paper, we fill this gap by introducing a framework called Mandolin, which implements a workflow for knowledge discovery specifically on RDF datasets.  ...  For each test triple (s, p, o), we generated as many corrupted triples (s, p,õ) as there are nodes in the graph such that o =õ ∈ V .  ... 
arXiv:1711.01283v1 fatcat:qrzlefmn5jgeth554vt4olwiku

Evolutionary and Swarm Computing for the Semantic Web

Christophe Gueret, Stefan Schlobach, Kathrin Dentler, Martijn Schut, Gusz Eiben
2012 IEEE Computational Intelligence Magazine  
These data sets are machine readable and unambiguously interpretable, thanks to their underlying standard representation languages.  ...  Finally, we will discuss two case studies in which we successfully applied soft computing methods to two of the main reasoning tasks; an evolutionary approach to querying, and a swarm algorithm for entailment  ...  Agents thus locally expand the knowledge by traversing RDF graphs and applying their rules on the triples they visit.  ... 
doi:10.1109/mci.2012.2188583 fatcat:5guizi4b2nbhjmdhopyqwlev74

Synonym Analysis for Predicate Expansion [chapter]

Ziawasch Abedjan, Felix Naumann
2013 Lecture Notes in Computer Science  
We applied our algorithm to various data sets as shown in a thorough evaluation of different strategies and rule-based techniques for this purpose.  ...  For example, users searching for movies with a certain artist cannot rely on a single given property artist, because some movies may be connected to that artist by the predicate starring.  ...  For each frequent itemset a generate rules of the form l → a − l with l ⊂ a, and check the confidence of the rule.  ... 
doi:10.1007/978-3-642-38288-8_10 fatcat:hyzt4szeuzdpdhtenfjuqiceay

On Evaluating Embedding Models for Knowledge Base Completion [article]

Yanjie Wang, Daniel Ruffinelli, Rainer Gemulla, Samuel Broscheit, Christian Meilicke
2019 arXiv   pre-print
This work indicates the need for more research into the embedding models and evaluation protocols for knowledge base completion.  ...  We show that when focusing on a different prediction task for evaluating knowledge base completion, the performance of current embedding models is unsatisfactory even on datasets previously thought to  ...  In the following, we briefly review some recent embedding models for knowledge base completion. We focus throughout on the set of models investigated with respect to their expressiveness in Liu et al.  ... 
arXiv:1810.07180v4 fatcat:iuxewsnjwbf5fobr7yqfmu2ree

Pay-As-You-Go OWL Query Answering Using a Triple Store

Yujiao Zhou, Yavor Nenov, Bernardo Cuenca Grau, Ian Horrocks
2014 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We present an enhanced hybrid approach to OWL query answering that combines an RDF triple-store with an OWL reasoner in order to provide scalable pay-as-you-go performance.  ...  We have implemented these techniques in a prototype system, a preliminary evaluation of which has produced very encouraging results.  ...  Acknowledgements This work was supported by the Royal Society, the EPSRC projects Score!, Exoda, and MaSI 3 , and the FP7 project OPTIQUE.  ... 
doi:10.1609/aaai.v28i1.8856 fatcat:4qkvevaxyvdapchd2cy56ywixi

HDSKG: Harvesting domain specific knowledge graph from content of webpages

Xuejiao Zhao, Zhenchang Xing, Muhammad Ashad Kabir, Naoya Sawada, Jing Li, Shang-Wei Lin
2017 2017 IEEE 24th International Conference on Software Analysis, Evolution and Reengineering (SANER)  
We incorporate the dependency parser with rule-based method to chunk the relations triple candidates, then we extract advanced features of these candidate relation triples to estimate the domain relevance  ...  The extraction of domain specific relation triples (subject, verb phrase, object) is one of the important techniques for domain specific knowledge graph construction.  ...  This research is partially supported by the National Research Foundation, Prime Minister's Office, Singapore under its IDM Futures Funding Initiative.  ... 
doi:10.1109/saner.2017.7884609 dblp:conf/wcre/ZhaoXKSLL17 fatcat:x7yacqpifndxhntw7muwuegeoa

Evaluating the Calibration of Knowledge Graph Embeddings for Trustworthy Link Prediction [article]

Tara Safavi, Danai Koutra, Edgar Meij
2020 arXiv   pre-print
knowledge graph triples.  ...  performance in a knowledge graph completion task.  ...  Acknowledgments We thank Caleb Belth for his feedback. This material is partially supported by the National Science Foundation under Grant No. IIS 1845491, Army Young Investigator Award No.  ... 
arXiv:2004.01168v3 fatcat:csjkv5z6dnc2rjmif3f6wmfimy

Benchmarking Knowledge-driven Zero-shot Learning [article]

Yuxia Geng, Jiaoyan Chen, Xiang Zhuang, Zhuo Chen, Jeff Z. Pan, Juan Li, Zonggang Yuan, Huajun Chen
2021 arXiv   pre-print
Some very recent studies thus propose to use Knowledge Graph (KG) due to its high expressivity and compatibility for representing kinds of knowledge.  ...  Each resource has a normal ZSL benchmark and a KG containing semantics ranging from text to attribute, from relational knowledge to logical expressions.  ...  Then, we invite volunteers to check these candidates with their images as references so that ensuring the correctness of extracted class disjointness.  ... 
arXiv:2106.15047v2 fatcat:vfe4vdxlprcrtpcjshda7ofxtu

On Evaluating Embedding Models for Knowledge Base Completion

Yanjie Wang, Daniel Ruffinelli, Rainer Gemulla, Samuel Broscheit, Christian Meilicke
2019 Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)  
Our findings suggest that there is a need for more research into embedding models as well as their training strategies for the task of knowledge base completion. 1 We discuss other less adopted evaluation  ...  In this paper, we study the question of how well recent embedding models perform for the task of knowledge base completion, i.e., the task of inferring new facts from an incomplete knowledge base.  ...  Therefore, more research into embedding models and their training is needed to assess whether, when, and how KGE models can be exploited for knowledge base completion.  ... 
doi:10.18653/v1/w19-4313 dblp:conf/rep4nlp/WangRGBM19 fatcat:5hei7k2jwjfrdbqrwah5tu5gdu

FarsBase-KBP: A Knowledge Base Population System for the Persian Knowledge Graph [article]

Majid Asgari-Bidhendi, Behrooz Janfada, Behrouz Minaei-Bidgoli
2020 arXiv   pre-print
Then, the system uses knowledge fusion techniques with minimal intervention of human experts to integrate and filter the proper knowledge instances, extracted by each module.  ...  22015 FarsBase triples and verified by human experts.  ...  After this stage, triples are passed to human experts to check the correctness of the triples. The correct triples then are added to the FarsBase.  ... 
arXiv:2005.01879v1 fatcat:6dgj5ch6jbfd3kw7omblxblwfe

Reinforced Anytime Bottom Up Rule Learning for Knowledge Graph Completion [article]

Christian Meilicke, Melisachew Wudage Chekol, Manuel Fink, Heiner Stuckenschmidt
2020 arXiv   pre-print
Most of todays work on knowledge graph completion is concerned with sub-symbolic approaches that focus on the concept of embedding a given graph in a low dimensional vector space.  ...  Its core algorithm is based on sampling paths, which are generalized into Horn rules.  ...  The task to construct missing triples using the vocabulary already used in the graph is known as knowledge graph completion or link prediction.  ... 
arXiv:2004.04412v1 fatcat:xa2fhlyyxvdlhcdvdfsqgk426e

Improving the Question Answering Quality using Answer Candidate Filtering based on Natural-Language Features [article]

Aleksandr Gashkov, Aleksandr Perevalov, Maria Eltsova, Andreas Both
2021 arXiv   pre-print
Hence, filtering incorrect answers from a list of answer candidates is leading to a highly improved QA quality.  ...  In particular, our approach has shown its potential while removing in many cases the majority of incorrect answers, which increases the QA quality significantly in comparison to the non-filtered output  ...  In this paper, we address the following research questions considering the task of filtering NL answer candidates: RQ 1 Is it possible to improve the QA quality while filtering answers just by their NL  ... 
arXiv:2112.05452v1 fatcat:2c6m76oiwrgjrpjbolinswloli
« Previous Showing results 1 — 15 out of 6,657 results