Filters








1,568 Hits in 3.3 sec

Domain-independent data cleaning via analysis of entity-relationship graph

Dmitri V. Kalashnikov, Sharad Mehrotra
2006 ACM Transactions on Database Systems  
The key difference between the approach we propose (called RELDC) and the traditional techniques is that RELDC analyzes not only object features but also inter-object relationships to improve the disambiguation  ...  Specifically, we consider a situation where entities in the database are referred to using descriptions (e.g., a set of instantiated attributes).  ...  The undirected edges in this graph are labeled with a 'base' similarity τ (x, y) measure.  ... 
doi:10.1145/1138394.1138401 fatcat:l2encb2zhbbzrm7fwixzinjvjm

Explore Person Specific Evidence in Web Person Name Disambiguation

Liwei Chen, Yansong Feng, Lei Zou, Dongyan Zhao
2012 Conference on Empirical Methods in Natural Language Processing  
We therefore propose a topic-based model to exploit the person specific global importance and embed it into the person name similarity.  ...  In this paper, we investigate different usages of feature representations in the web person name disambiguation task which has been suffering from the mismatch of vocabulary and lack of clues in web environments  ...  Acknowledgments We would like to thank Yidong Chen, Wei Wang and Tinghua Wang for their useful discussions and the anonymous reviewers for their helpful comments which greatly improved the work and the  ... 
dblp:conf/emnlp/ChenFZZ12 fatcat:lcebclk3gbgrtbjjhwo3anp4wa

SEL

Salvatore Trani, Diego Ceccarelli, Claudio Lucchese, Salvatore Orlando, Raffaele Perego
2016 Proceedings of the 2016 ACM Symposium on Document Engineering - DocEng '16  
The Entity Linking task consists in automatically identifying and linking the entities mentioned in a text to their URIs in a given Knowledge Base, e.g., Wikipedia.  ...  The first step is based on a classifier aimed at identifying a set of candidate entities that are likely to be mentioned in the document, thus maximizing the precision of the method without hindering its  ...  In WAT [12] authors extended Tagme with a new spotting module (using gazetteers, named-entity recognition analysis and a binary classifier for tuning performance), voting-based and graph-based disambiguation  ... 
doi:10.1145/2960811.2960819 dblp:conf/doceng/TraniCLOP16 fatcat:ijpjlou4t5bgxdqmjyy2dptv4q

Automated Semantic Tagging of Textual Content

Jelena Jovanovic, Ebrahim Bagheri, John Cuzzola, Dragan Gasevic, Zoran Jeremic, Reza Bashash
2014 IT Professional Magazine  
Motivated by a continually increasing demand for applications that depend on machine comprehension of text-based content, researchers, in both academia and industry, have developed innovative solutions  ...  In this article, we focus on a subset of such toolsi.e., semantic taggersthat not only extract and disambiguate entities mentioned in the text, but also identify topics that unambiguously describe the  ...  for each mention Combined use of popularitybased prior, context-based approach and graph-based approach N/A YAGO2, a general purpose knowledge base where each entity is associated with a set of labels  ... 
doi:10.1109/mitp.2014.85 fatcat:lklbciaiyrh7dh6fhw55zcpdge

From TagME to WAT

Francesco Piccinno, Paolo Ferragina
2014 Proceedings of the first international workshop on Entity recognition & disambiguation - ERD '14  
As a side result, the final software can be interpreted as a flexible library of several parsing/disambiguation and pruning modules that can be used to build up new and more sophisticated entity annotators  ...  and pruning.  ...  More recently [18] proposed another approach to entity disambiguation based on the HITS algorithm which is run over a sub-graph of the RDF Knowledge Base (DBPedia [1] ), derived using a truncated BFS  ... 
doi:10.1145/2633211.2634350 dblp:conf/sigir/PiccinnoF14 fatcat:yz26jxsd6vblfm4ni6udsb5zny

Question answering on interlinked data

Saeedeh Shekarpour, Axel-Cyrille Ngonga Ngomo, Sören Auer
2013 Proceedings of the 22nd international conference on World Wide Web - WWW '13  
This approach essentially relies on a combination of domain and range inference as well as a link traversal method for constructing a connected graph which ultimately renders a corresponding SPARQL query  ...  The contribution of this paper is two-fold: Firstly, we introduce a novel approach for determining the most suitable resources for a user-supplied query from different datasets (disambiguation).  ...  To connect two disjoint graphs we need to obtain edges that qualify for connecting a vertex in one graph with a suitable vertex in the other graph.  ... 
doi:10.1145/2488388.2488488 dblp:conf/www/ShekarpourNA13 fatcat:ydb2ukwqm5exfgtopqltxk5jei

SINA: Semantic Interpretation of User Queries for Question Answering on Interlinked Data

Saeedeh Shekarpour, Edgard Marx, Axel-Cyrille Ngonga Ngomo, SSren Auer
2015 Social Science Research Network  
Sina uses a hidden Markov model to determine the most suitable resources for a user-supplied query from different datasets.  ...  Second, different datasets employ heterogeneous schemas and each one may only contain a part of the answer for a certain user query.  ...  To connect two disjoint graphs we need to obtain edges that qualify for connecting a vertex in one graph with a suitable vertex in the other graph.  ... 
doi:10.2139/ssrn.3199174 fatcat:mihk7rtrw5bq5ck2zr4f3kl7ka

SINA: Semantic interpretation of user queries for question answering on interlinked data

Saeedeh Shekarpour, Edgard Marx, Axel-Cyrille Ngonga Ngomo, Sören Auer
2015 Journal of Web Semantics  
Sina uses a hidden Markov model to determine the most suitable resources for a user-supplied query from different datasets.  ...  Second, different datasets employ heterogeneous schemas and each one may only contain a part of the answer for a certain user query.  ...  To connect two disjoint graphs we need to obtain edges that qualify for connecting a vertex in one graph with a suitable vertex in the other graph.  ... 
doi:10.1016/j.websem.2014.06.002 fatcat:wqxbprnm6zbvbgjeb2ohzq3qda

REDEN: Named Entity Linking in Digital Literary Editions Using Linked Data Sets

Carmen Brando, Francesca Frontini, Jean-Gabriel Ganascia
2016 Complex Systems Informatics and Modeling Quarterly  
Description of the Algorithm With REDEN 13 , we propose a graph-based, centrality-based approach.  ...  In this paper we shall first present previous approaches to NE disambiguation and linking, then introduce our graph based disambiguation algorithm, named REDEN, which includes strategies to consistently  ... 
doi:10.7250/csimq.2016-7.04 fatcat:bwsq7w44qrgndfk2h2giesixla

Automatic Induction of Synsets from a Graph of Synonyms

Dmitry Ustalov, Alexander Panchenko, Chris Biemann
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
This paper presents a new graph-based approach that induces synsets using synonymy dictionaries and word embeddings.  ...  Our meta-clustering approach lets us use an efficient hard clustering algorithm to perform a fuzzy clustering of the graph.  ...  suggested the WATSET name.  ... 
doi:10.18653/v1/p17-1145 dblp:conf/acl/UstalovPB17 fatcat:mw7mv6q74jhwnlk23ra4bhyyh4

Pair-Linking for Collective Entity Disambiguation: Two Could Be Better Than All [article]

Minh C. Phan and Aixin Sun and Yi Tay and Jialong Han and Chenliang Li
2018 arXiv   pre-print
As a remedy, we introduce MINTREE, a new tree-based objective for the entity disambiguation problem.  ...  Instead of considering all the given mentions, Pair-Linking iteratively selects a pair with the highest confidence at each step for decision making.  ...  Graph-based Approach Graph-based approaches solve the disambiguation problem by performing collective linking on mention-entity graph.  ... 
arXiv:1802.01074v3 fatcat:nvtwb2iz6va77e2gfe6lyagntm

Tulip

Marek Lipczak, Arash Koushkestani, Evangelos Milios
2014 Proceedings of the first international workshop on Entity recognition & disambiguation - ERD '14  
Each entity is represented by an accurate and compact feature vector extracted from a category graph built based on information from 120 language versions of Wikipedia.  ...  To achieve it, Tulip prunes the set of entity candidates focusing on a core subset of related entities capturing the context of the document.  ...  useful discussions and help with the evaluation of the system.  ... 
doi:10.1145/2633211.2634351 dblp:conf/sigir/LipczakKM14 fatcat:gacer2ag6fflxf3m2h3iz7xnza

TAGME

Paolo Ferragina, Ugo Scaiella
2010 Proceedings of the 19th ACM international conference on Information and knowledge management - CIKM '10  
In this paper we address the problem of accurately and efficiently cross-referencing text fragments with Wikipedia pages, in a way that structured knowledge is provided about the (unstructured) input text  ...  on long texts with the plus of being faster.  ...  In [15] the authors showed an impressive precision of 97% for disambiguation and an F-Measure of 74.8% for pruning.  ... 
doi:10.1145/1871437.1871689 dblp:conf/cikm/FerraginaS10 fatcat:uldajld4vbbxrn5z57otfqwhmm

Watset: Local-Global Graph Clustering with Applications in Sense and Frame Induction [article]

Dmitry Ustalov and Alexander Panchenko and Chris Biemann and Simone Paolo Ponzetto
2019 arXiv   pre-print
We present a detailed theoretical and computational analysis of the Watset meta-algorithm for fuzzy graph clustering, which has been found to be widely applicable in a variety of domains.  ...  Then, it uses hard clustering to discover clusters in this "disambiguated" intermediate graph.  ...  acknowledge the support of the Deutsche Forschungsgemeinschaft (DFG) foundation under the "JOIN-T" and "ACQuA" projects, the Deutscher Akademischer Austauschdienst (DAAD), and the Russian Foundation for  ... 
arXiv:1808.06696v3 fatcat:jdd5cnkhffhaxlti72oskgleye

Query Segmentation and Resource Disambiguation Leveraging Background Knowledge

Saeedeh Shekarpour, Axel-Cyrille Ngonga Ngomo, Sören Auer
2012 International Semantic Web Conference  
In this paper we introduce a novel approach for determining the correct resources for user-supplied keyword queries based on a hidden Markov model.  ...  While linguistic methods like named entity, multi-word unit recognition and POS-tagging fail in the case of an incomplete sentences (e.g. for keyword-based queries), we will show that our statistical approach  ...  Results We evaluated our hidden Markov model for resource disambiguation by combining it with the naive (Naive & HMM) and the greedy segmentation (Greedy & HMM) approaches for segmentation.  ... 
dblp:conf/semweb/ShekarpourNA12 fatcat:6ca57bzoqjghtkedqrqnokhcsq
« Previous Showing results 1 — 15 out of 1,568 results