Filters








1,826 Hits in 7.6 sec

A Semantic Best-Effort Approach for Extracting Structured Discourse Graphs from Wikipedia

André Freitas, Danilo S. Carvalho, João Carlos Pereira da Silva, Seán O'Riain, Edward Curry
2012 International Semantic Web Conference  
To cope with this scenario, this work introduces a semantic best-effort information extraction approach, which targets an information extraction scenario where text information is extracted under a pay-as-you-go  ...  A semantic information extraction framework (Graphia) is implemented and evaluated over the Wikipedia corpus.  ...  Conclusion & Future Work This work focuses on the analysis of a semantic best-effort extraction approach using structured discourse graphs (SDGs), a RDF-based discourse representation format.  ... 
dblp:conf/semweb/FreitasCSOC12 fatcat:usaxei3fkbcszpq5q5yrjjr4rq

Representing Texts as Contextualized Entity-Centric Linked Data Graphs

Andre Freitas, Sean ORiain, Edward Curry, Joao C.P. da Silva, Danilo S. Carvalho
2013 2013 24th International Workshop on Database and Expert Systems Applications  
The representation focuses on a semantic best-effort information extraction scenario, where information from text is extracted under a pay-as-you-go data quality perspective, trading terminological normalization  ...  This work focuses on bridging the gap between structured and unstructured data, proposing the representation of text as structured discourse graphs (SDGs), targeting an RDF representation of unstructured  ...  P. da Silva is a CNPq Fellow -Science without Borders (Brazil).  ... 
doi:10.1109/dexa.2013.21 dblp:conf/dexaw/FreitasOCSC13 fatcat:j6ww66y3njeovgkxydovyvkewi

On the Semantic Representation and Extraction of Complex Category Descriptors [chapter]

André Freitas, Rafael Vieira, Edward Curry, Danilo Carvalho, João Carlos Pereira da Silva
2014 Lecture Notes in Computer Science  
In the representation, complex categories are decomposed into a graph of primitive concepts, supporting their interlinking and semantic interpretation.  ...  Natural language descriptors used for categorizations are present from folksonomies to ontologies.  ...  A NLCD extractor is built and the extraction quality is evaluated (section 7). Motivational Scenario Wikipedia is built from a large-scale decentralized data curation effort.  ... 
doi:10.1007/978-3-319-07983-7_6 fatcat:7w7x3iioy5g7nf6ybfhh76ixoy

Collaboratively built semi-structured content and Artificial Intelligence: The story so far

Eduard Hovy, Roberto Navigli, Simone Paolo Ponzetto
2013 Artificial Intelligence  
Finally, we thank the Artificial Intelligence Journal Editors-in-Chief, Tony Cohn, Rina Dechter and Ray Perrault, for their continued support throughout the preparation of this special issue.  ...  A parallel effort, similar in spirit to YAGO, is DBPedia [22] , the goal of which is also to transform the semi-structured content of Wikipedia into a fully-structured representation using RDF, a Semantic  ...  [217] , on the other hand, developed a graph-based approach for constructing a multilingual thesaurus.  ... 
doi:10.1016/j.artint.2012.10.002 fatcat:mwk5o254urb2dejsh7c224uu3q

REMOD: Relation Extraction for Modeling Online Discourse [article]

Matthew Sumpter, Giovanni Luca Ciampaglia
2021 arXiv   pre-print
Here we develop a novel supervised learning method for relation extraction that combines graph embedding techniques with path traversal on semantic dependency graphs.  ...  A key challenge is relation extraction, which is the task of determining the semantic relationships between named entities in a claim.  ...  Acknowledgements The authors would like to thank Google for making publicly available both the GREC dataset and the Fact Check Explorer tool, and Alexios Mantzarlis for feedback on the manuscript.  ... 
arXiv:2102.11105v2 fatcat:iawjsfcmazg2npdxulcbrfjjqy

Information Extraction from Scientific Literature for Method Recommendation [article]

Yi Luan
2018 arXiv   pre-print
We propose to construct a knowledge graph in a way that can make minimal use of hand annotated data, using only the extracted terms, unsupervised relational signals such as co-occurrence, and structural  ...  In this proposal, we aim at making scientific recommendations by extracting scientific terms from a large collection of scientific papers and organizing the terms into a knowledge graph.  ...  An example of a Wikipedia-derived graph is shown in Fig. 9 . Figure 10 is an example of a graph with auxiliary relations from different resources.  ... 
arXiv:1901.00401v1 fatcat:owygelspnjblloa2eecf5etihe

Utilising Wikipedia for Text Mining Applications

Muhammad Atif Qureshi
2016 SIGIR Forum  
To the best of our knowledge, previous research efforts that utilise Wikipedia for knowledge extraction tasks have not taken both Wikipedia categories and Wikipedia articles together as a source of information  ...  Chapter 4 presents our framework for measures of "semantic relatedness" built on top of the Wikipedia category graph and Wikipedia category-article structure.  ...  B.2 The Approach In this section we present our strategy to exploit the Wikipedia articles' hyperlink structure; first we discuss phrase extraction which is followed by a discussion on how we actually  ... 
doi:10.1145/2888422.2888449 fatcat:lck3kkxoazcj5powaqhjs6epty

Specification of Web-based Analytics Methods and Tools D3.1

Laia Albó, Miriam Calvera Isabal, Sven Manske, David Roldán Álvarez
2021 Zenodo  
This perspective comprises semantic and pragmatic aspects of scientific discourse as well as more structural analyses that focus on connections and networking inside the projects, between different projects  ...  WP3 aims at extracting and further processing such pieces of information from web and social media sources.  ...  The DBpedia project aims to extract structured information from Wikipedia as RDF triples.  ... 
doi:10.5281/zenodo.5653454 fatcat:hq6g3lzdlbdm7pj5cmrccnilfa

Graphene: Semantically-Linked Propositions in Open Information Extraction [article]

Matthias Cetto, Christina Niklaus, André Freitas, Siegfried Handschuh
2018 arXiv   pre-print
In that way, we convert sentences that present a complex linguistic structure into simplified, syntactically sound sentences, from which we can extract propositions that are represented in a two-layered  ...  We present an Open Information Extraction (IE) approach that uses a two-layered transformation stage consisting of a clausal disembedding layer and a phrasal disembedding layer, together with rhetorical  ...  and investigate the creation of big knowledge graphs for QA by performing a large-scale Wikipedia extraction.  ... 
arXiv:1807.11276v1 fatcat:44x3le5cq5ajjjpqw52ugatszu

WikiBank: Using Wikidata to Improve Multilingual Frame-Semantic Parsing

Cezar Sas, Meriem Beloucif, Anders Søgaard
2020 International Conference on Language Resources and Evaluation  
We present WIKIBANK, a multilingual resource of partial semantic structures that can be used to extend pre-existing resources rather than creating new man-made resources from scratch.  ...  for semantic parsers.  ...  Conclusion We introduced WIKIBANK, a new multilingual resource for semantic parsing. WIKIBANK consists of partial semantic structures directly projected from Wikidata onto Wikipedia sentences.  ... 
dblp:conf/lrec/SasBS20 fatcat:dvaaatbtdfdbffggczeydv3vz4

Recent advances in methods of lexical semantic relatedness – a survey

ZIQI ZHANG, ANNA LISA GENTILE, FABIO CIRAVEGNA
2012 Natural Language Engineering  
A key to this challenge rests on the technology of Information Extraction, which automatically transforms unstructured textual data into structured representation that can be interpreted and manipulated  ...  them into pre-defined semantic categories.  ...  To do so, entity names from a single discourse are firstly extracted to form the context to each other. Next, candidate referent entities for each name are identified from Wikipedia.  ... 
doi:10.1017/s1351324912000125 fatcat:b62qbqwrqfaf3gytw22yktc5ae

Unsupervised scene detection and commentator building using multi-modal chains

Gert-Jan Poulisse, Yorgos Patsis, Marie-Francine Moens
2012 Multimedia tools and applications  
This paper presents a novel unsupervised method for identifying the semantic structure in long semi-structured video streams.  ...  We present two clustering strategies that accomplish this task, and compare them against a baseline Scene Transition Graph approach.  ...  for media production, FP7-ICT 287532).  ... 
doi:10.1007/s11042-012-1086-0 fatcat:bqnt5tnemnbl3j5xtkp7orrqru

Scientific document summarization via citation contextualization and scientific discourse

Arman Cohan, Nazli Goharian
2017 International Journal on Digital Libraries  
We present a framework for scientific summarization which takes advantage of the citations and the scientific discourse structure.  ...  We then train a model to identify the discourse facets for each citation.  ...  -Discourse structure: After extracting the context of the citation texts, we classify them into different discourse facets.  ... 
doi:10.1007/s00799-017-0216-8 fatcat:4zwdaqixnzei3i6yegahz3gxge

Natural Language Generation in the context of the Semantic Web

Nadjet Bouayad-Agha, Gerard Casamayor, Leo Wanner
2014 Semantic Web Journal  
We attempt to provide an overview of the main paradigms of NLG from SW data, emphasizing how the Semantic Web provides opportunities for the NLG community to improve their state-of-the-art approaches whilst  ...  bringing about challenges that need to be addressed before we can speak of a real symbiosis between NLG and the Semantic Web.  ...  Acknowledgements We would like to thank the reviewers for their very constructive and detailed comments on earlier versions of the paper. All mistakes and omissions are of course ours.  ... 
doi:10.3233/sw-130125 fatcat:gbh2vyjrv5e5jbjd6m6sjrxrly

Identifying Motifs For Evaluating Open Knowledge Extraction On The Web

Aldo Gangemi, Diego Reforgiato Recupero, Misael Mongiovì, Andrea Giovanni Nuzzolese, Valentina Presutti
2016 Zenodo  
We demonstrate the usage and extraction techniques of motifs using a broad-coverage OKE tool for the Semantic Web called FRED.  ...  Finally, we use identified motifs as empirical data for assessing the quality of OKE results, and show how they can be extended trough a use case represented by an application within the Semantic Sentiment  ...  Acknowledgments The research leading to these results has received funding from the European Union Horizons 2020 the Framework Programme for Research and Innovation (2014-2020) under grant agreement 643808  ... 
doi:10.5281/zenodo.1204443 fatcat:g4uv5yc765hmvh5lqpa6ol2mwe
« Previous Showing results 1 — 15 out of 1,826 results