22 Hits in 7.0 sec

Semantic Hypergraphs [article]

Telmo Menezes, Camille Roth
2021 arXiv   pre-print
The central idea of our approach is the Semantic Hypergraph (SH), a novel knowledge representation model that is intrinsically recursive and accommodates the natural hierarchical richness of natural language  ...  The SH model is hybrid in two senses. First, it attempts to combine the strengths of ML and symbolic approaches.  ...  A machine learning model trained over NLP-annotated chunks of text classifies pairs of claims as "agreement", "conflict", "confinement" and "evidence".  ... 
arXiv:1908.10784v2 fatcat:mpf3qtkst5hldbyrvpvcx4vtnu

A State of the Art of Word Sense Induction: A Way Towards Word Sense Disambiguation for Under-Resourced Languages [article]

Mohammad Nasiruddin
2013 arXiv   pre-print
Word Sense Disambiguation (WSD), the process of automatically identifying the meaning of a polysemous word in a sentence, is a fundamental task in Natural Language Processing (NLP).  ...  Progress in this approach to WSD opens up many promising developments in the field of NLP and its applications.  ...  Acknowledgements The work presented in this paper was conducted in the context of the VideoSense project, funded by the French National Research Agency (ANR) under its CONTINT 2009 program (grant ANR-09  ... 
arXiv:1310.1425v1 fatcat:6rrkfn6khfdzldweedzdgq2ru4

MEDEA: Merging Event knowledge and Distributional vEctor Addition [chapter]

Ludovica Pannitto, Alessandro Lenci
2018 Proceedings of the Fifth Italian Conference on Computational Linguistics CLiC-it 2018  
English. The great majority of compositional models in distributional semantics present methods to compose distributional vectors or tensors in a representation of the sentence.  ...  Here we propose to enrich the best performing method (vector addition, which we take as a baseline) with distributional knowledge about events, outperforming our baseline. Italiano.  ...  Relations were automatically extracted from a 2018 dump of Wikipedia, BNC, and ukWaC corpora, parsed with the Stanford CoreNLP Pipeline (Manning et al., 2014) .  ... 
doi:10.4000/books.aaccademia.3577 fatcat:fs6nztlig5fotnopv75dd7cmu4

Event Knowledge in Compositional Distributional Semantics

Ludovica Pannitto, Alessandro Lenci
2019 Italian Journal of Computational Linguistics  
The training data comes from the concatenation of three dependencyparsed corpora: BNC (Leech 1992) , ukWaC (Baroni et al. 2009 ) and a 2018 dump of the English Wikipedia, for a combined size of approximately  ...  Note that in Rimell et al. (2016) the training corpus was a 2015 dump of Wikpedia.  ... 
doi:10.4000/ijcol.463 fatcat:tdksyobqszgw5gusp2x4jqbvui

Utilising Wikipedia for Text Mining Applications

Muhammad Atif Qureshi
2016 SIGIR Forum  
This system exploits Wikipedia dumps in an efficient way (see Appendix A).  ...  utilised the dumps made available by DBPedia.  ...  same time proposing a technique on top of Wikipedia hyperlink 1 structure to determine context of a tweet.  ... 
doi:10.1145/2888422.2888449 fatcat:lck3kkxoazcj5powaqhjs6epty

Linked knowledge sources for topic classification of microposts: A semantic graph-based approach

Andrea Varga, Amparo Elizabeth Cano Basave, Matthew Rowe, Fabio Ciravegna, Yulan He
2014 Journal of Web Semantics  
The accurate TC of Microposts however is a challenging task since the limited number of tokens in a post often implies a lack of sufficient contextual information.  ...  This novel meta-graph provides a more fine grained categorisation of concepts providing a set of novel semantic features.  ...  Moreover, when building the cross-source topic classifiers, our models still require a large number of annotated Tweets to outperform the single-source Twitter models.  ... 
doi:10.1016/j.websem.2014.04.001 fatcat:64qvdi3snramrovjqhxuimcpwe

Linked Knowledge Sources for Topic Classification of Microposts: A Semantic Graph-Based Approach

Andrea Varga, Amparo E. Cano, Matthew Rowe, Fabio Ciravegna, Yulan He
2014 Social Science Research Network  
The accurate TC of Microposts however is a challenging task since the limited number of tokens in a post often implies a lack of sufficient contextual information.  ...  This novel meta-graph provides a more fine grained categorisation of concepts providing a set of novel semantic features.  ...  Moreover, when building the cross-source topic classifiers, our models still require a large number of annotated Tweets to outperform the single-source Twitter models.  ... 
doi:10.2139/ssrn.3199099 fatcat:2febxkwyfbc6jisntu24z4ro3a

Question Answering over Knowledge Base using Factual Memory Networks

Sarthak Jain
2016 Proceedings of the NAACL Student Research Workshop  
Additionally, we also improve the run-time efficiency of our model using various computational heuristics.  ...  Our system generate distributed representation of questions and KB in same word vector space, extract a subset of initial candidate facts, then try to find a path to answer entity using multi-hop reasoning  ...  like Wikipedia) in our model, to extend and improve its utility.  ... 
doi:10.18653/v1/n16-2016 dblp:conf/naacl/Jain16 fatcat:kgtl2y7mkzffrpdnqnxridg3ky

Entity Centric Information Retrieval

Xitong Liu
2016 SIGIR Forum  
of query hypergraphs.  ...  Along with the data collection, a set of 29 topic entities (27 people and 2 organizations) are provided, denoted as target entities. All the entities are chosen from a Wikipedia dump of January 2012.  ... 
doi:10.1145/2964797.2964815 fatcat:qdmhwfminnaefonienqyggckbm

Knowledge Graphs [article]

Aidan Hogan, Eva Blomqvist, Michael Cochez, Claudia d'Amato, Gerard de Melo, Claudio Gutierrez, José Emilio Labra Gayo, Sabrina Kirrane, Sebastian Neumaier, Axel Polleres, Roberto Navigli, Axel-Cyrille Ngonga Ngomo (+6 others)
2021 arXiv   pre-print
We discuss the roles of schema, identity, and context in knowledge graphs. We explain how knowledge can be represented and extracted using a combination of deductive and inductive techniques.  ...  After some opening remarks, we motivate and contrast various graph-based data models and query languages that are used for knowledge graphs.  ...  Acknowledgements: We thank the attendees of the Dagstuhl Seminar on "Knowledge Graphs" for discussions that inspired and influenced this paper, and all those that make such seminars possible.  ... 
arXiv:2003.02320v5 fatcat:ab4hmm2f2bbpvobwkjw4xbrz4u

Implicit Entity Networks: A Versatile Document Model

Andreas Spitz
Finally, we combine the insights gained from these applications in a versatile hypergraph document model that bridges the gap between unstructured text and structured knowledge sources. v Z Unsere Zeit  ...  In this thesis, we introduce implicit entity networks as a comprehensive document model that addresses this shortcoming and provides a holistic representation of document collections and document streams  ...  search engine that supports the exploration of a static document collection, represented by an annotated dump of Wikipedia.  ... 
doi:10.11588/heidok.00026328 fatcat:2vhgwwoxxvhglgutnreykuvcja

Translation-based Ranking in Cross-Language Information Retrieval

Felix Hieber
ranking"), and (3) by presenting a joint model of translation and retrieval for "document ranking".  ...  I present substantial improvements over stateof-the-art translation-based CLIR baseline systems, indicating that a joint model of translation and retrieval is a promising direction of research in the field  ...  Chapter 4 Automatic Extraction of Relevance Annotations from Wikipedia  ... 
doi:10.11588/heidok.00018696 fatcat:dkh5nfuco5dt7gfslcjzu7dvd4

Number 2 in Bratislava on

P Kapec, J Sedláèková, L Holík, M Bieliková, P Návrat, F Burda, R Èapla, Mária Bieliková, Johann, Viliam Geffert, Tomáš Hruška, Robert Lorencz (+9 others)
2011 unpublished
We have developed a visualization system that utilize hypergraph-based representation of software arti-facts and relations between them.  ...  Interactive 3D visualization displays directly these hypergraph representations of software.  ...  VG1/0675/11, and it is the partial result of the Research & Development Operational Programme for the project Research of methods for acquisition, analysis and personalized conveying of information and  ... 

Searching Community-built Semantic Web Resources to Support Personal Media Annotation

Annett Mitschick, Ronny Winkler, Klaus Meißner
Appropriate annotation of documents is a central aspect of efficient media management and retrieval.  ...  As ontology-based description of documents and facts enables exchange and reuse of metadata among communities and across applications, the annotation of personal media collections using Semantic Web technologies  ...  Acknowledgements We thank M. d'Aquin for his useful comments on earlier versions of this paper.  ... 

Content Modeling for Automatic Document Summarization [article]

Leonhard Hennig, Technische Universität Berlin, Technische Universität Berlin, Sahin Albayrak
However, the ambiguity of natural language and the sparsity of sentence vocabularies present problems that go beyond the capabilities of common modeling techniques.  ...  Current search engines filter the vast amounts of information available on the Internet by retrieving a potentially large set of documents in response to a user's query.  ...  Acknowledgments This dissertation would not have been possible without the constant encouragement and support of many inspiring people. Above all, I would like  ... 
doi:10.14279/depositonce-3039 fatcat:phocc7ykafa3lj7vugj2sbdmo4
« Previous Showing results 1 — 15 out of 22 results