Filters








12,978 Hits in 6.7 sec

Graph-Based Named Entity Linking with Wikipedia [chapter]

Ben Hachey, Will Radford, James R. Curran
2011 Lecture Notes in Computer Science  
Named entity linking (NEL) grounds entity mentions to their corresponding Wikipedia article.  ...  State-of-the-art supervised NEL systems use features over the rich Wikipedia document and link-graph structure.  ...  ., a Wikipedia link to another article or disambiguation page describing entities with the same name.  ... 
doi:10.1007/978-3-642-24434-6_16 fatcat:ekg3op6i2ncc5iq4lvt3ltdtgq

TCAR at TAC-KBP-2010

Alan Goldschen, Brian Kapp, Tim Meyer, Boyan A. Onyshkevych, Patrick Schone
2010 Text Analysis Conference  
The TCAR team developed multiple information retrieval based entity linking systems in a matter of weeks for the TAC-KBP evaluation task.  ...  We focused primarily on developing entity linking algorithms that do not require Wikipedia text and correctly detect when a given entity does not exist in Wikipedia (NIL).  ...  System GRAPH Overview: GRAPH uses a graph-based approach that attempts to resolve identities of several other named entities in the reference document in addition to the one named in the query.  ... 
dblp:conf/tac/GoldschenKMOS10 fatcat:hvsaaksd4jaffh4emc42oguil4

Entity Disambiguation with Web Links

Andrew Chisholm, Ben Hachey
2015 Transactions of the Association for Computational Linguistics  
We explore whether web links can replace a curated encyclopaedia, obtaining entity prior, name, context, and coherence models from a corpus of web pages with links to Wikipedia.  ...  Entity disambiguation with Wikipedia relies on structured information from redirect pages, article text, inter-article links, and categories.  ...  The structure is the same as the cor-Wikipedia Web links Names 1.4m 3.1m Entities 1.5m 1.7m responding model from Wikipedia, both are bipartite graphs with cooccurrence frequencies on edges.  ... 
doi:10.1162/tacl_a_00129 fatcat:gsykvrjypzg4fpsnwdq5uew4ma

A search based approach to entity recognition

Michal Laclavik, Marek Ciglan, Alex Dorman, Stefan Dlugolinsky, Sam Steingold, Martin Šeleng
2014 Proceedings of the first international workshop on Entity recognition & disambiguation - ERD '14  
Our approach combines techniques of information retrieval, gazetteer based annotation and entity link graph analysis to identify and disambiguate candidate entities.  ...  Finally, we exploit Wikipedia link graph to asses the similarity of candidate entities for the purpose of disambiguation and further candidate filtering.  ...  results exploiting Wikipedia link graph.  ... 
doi:10.1145/2633211.2634352 dblp:conf/sigir/LaclavikCDDSS14 fatcat:cltolzcuezbf3jnv3a2gxajemu

Linking Entities in Chinese Queries to Knowledge Graph [chapter]

Jun Li, Jinxian Pan, Chen Ye, Yong Huang, Danlu Wen, Zhichun Wang
2015 Lecture Notes in Computer Science  
of entity in the knowledge graph.  ...  It combines several different metrics to evaluate the probability of each entity link, including entity relatedness in the given knowledge graph, document similarity between query and the virtual document  ...  In order to incorporate search engines with knowledge graphs, one important task is to link entities in search queries to knowledge graphs.  ... 
doi:10.1007/978-3-319-25207-0_56 fatcat:aikgmsus3zc2fno7e5pctebmke

What's New? Analysing Language-Specific Wikipedia Entity Contexts to Support Entity-Centric News Retrieval [chapter]

Yiwei Zhou, Elena Demidova, Alexandra I. Cristea
2017 Lecture Notes in Computer Science  
First, we discuss alternative ways such contexts can be built, including Graph-based and Article-based approaches.  ...  Second, we analyse the similarities and the differences in these contexts in a case study including 220 entities and five Wikipedia language editions.  ...  However, one named entity is typically related to various other named entities and events, as we observed during the context creation using the Wikipedia link structure.  ... 
doi:10.1007/978-3-319-59268-8_10 fatcat:gkeuf6fhm5ctzglpsh4x4qjnjm

CIRG IRGDISCO at RepLab2013 Filtering Task: Use of Wikipedia's Graph Structure for Entity Name Disambiguation in Tweets

Muhammad Atif Qureshi, Arjumand Younus, Daniel Abril, Colm O'Riordan, Gabriella Pasi
2013 Conference and Labs of the Evaluation Forum  
graph-based features may show a promising outcome when used in combination with sophisticated learning algorithms.  ...  in a tweet and Wikipedia disambiguated articles for a particular entity in an SVM classifier that utilizes features extracted from the Wikipedia graph structure i.e., links into Wikipedia articles and  ...  As future work we aim to investigate the value of Wikipedia graph-based features when used in combination with sophisticated learning algorithms.  ... 
dblp:conf/clef/0001YAOP13 fatcat:t2tbyded6rghjntpbmionjazvi

Creating and Exploiting a Hybrid Knowledge Base for Linked Data [chapter]

Zareen Syed, Tim Finin
2011 Communications in Computer and Information Science  
A key resource in our work is Wikitology, a hybrid knowledge base of structured and unstructured information extracted from Wikipedia.  ...  Twenty years ago Tim Berners-Lee proposed a distributed hypertext system based on standard Internet protocols.  ...  Acknowledgements This research was carried out with support from the Fulbright Foundation, Microsoft Research, NSF award IIS-0326460 and the Johns Hopkins University Human Language Technology Center of  ... 
doi:10.1007/978-3-642-19890-8_1 fatcat:ivnpnwxbujgvpmlz3fghwk7nzm

Wikipedia2Vec: An Efficient Toolkit for Learning and Visualizing the Embeddings of Words and Entities from Wikipedia [article]

Ikuya Yamada, Akari Asai, Jin Sakuma, Hiroyuki Shindo, Hideaki Takeda, Yoshiyasu Takefuji, Yuji Matsumoto
2020 arXiv   pre-print
In this paper, we present Wikipedia2Vec, a Python-based open-source tool for learning the embeddings of words and entities from Wikipedia.  ...  The embeddings of entities in a large knowledge base (e.g., Wikipedia) are highly beneficial for solving various natural language tasks that involve real world knowledge.  ...  Link Graph Matrix During training, our link graph model needs to obtain numerous neighboring entities of an entity in a large link graph of Wikipedia.  ... 
arXiv:1812.06280v4 fatcat:ah4cnrebbbhn5anevcu4c6rmv4

CMU System for Entity Discovery and Linking at TAC-KBP 2017

Xuezhe Ma, Nicolas R. Fauceglia, Yiu-Chang Lin, Eduard H. Hovy
2017 Text Analysis Conference  
This paper describes CMU's system for the Tri-lingual Entity Discovery and Linking (TEDL) task at TAC-KBP 2017.  ...  Our system is a unified graph-based approach that achieves competitive results for English, Spanish, and Chinese.  ...  This yields a KB with around 4.9M pages. Graph of Wikipedia We first represent Wikipedia as a directed weighted graph, where the vertices in the graph are the entities and concepts in Wikipedia.  ... 
dblp:conf/tac/MaFLH17 fatcat:hksmo2ndbbhdxjtdsbcggsgi3q

CMU System for Entity Discovery and Linking at TAC-KBP 2016

Xuezhe Ma, Nicolas R. Fauceglia, Yiu-Chang Lin, Eduard H. Hovy
2016 Text Analysis Conference  
Our system is a unified graph-based approach which achieved competitive results for three languages.  ...  This paper describes CMU's system for the Tri-lingual Entity Discovery and Linking (TEDL) task at TAC-KBP 2016.  ...  The major difference is that, in this year, we utilize Wikipedia as our Knowledge Base instead of Freebase. Our system first links all mentions to corresponding entities in Wikipedia.  ... 
dblp:conf/tac/MaFLH16 fatcat:kooav2tmkrarzjskcpecpn7bja

HIT Approaches to Entity Linking at TAC 2011

Yuhang Guo, Guohua Tang, Wanxiang Che, Ting Liu, Sheng Li
2011 Text Analysis Conference  
This paper describes the system of HIT at the 2011 Text Analysis Conference (TAC) Knowledge Base Population (KBP) track English Entity Linking task.  ...  We model the query context as a graph of the entities and utilize the referential relationship between the context entities and the candidate entities in Wikipedia to measure the relatedness between the  ...  Entity Linking is the task of linking a name mention in a document to the correspondence entity in a Knowledge Base (KB) (McNamee and Dang, 2009; Ji and Grishman, 2011) .  ... 
dblp:conf/tac/GuoTCLL11 fatcat:rc46yklhgzeitl5qrh635pv7x4

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.  ...  Given the core set of accepted entities Tulip uses the Wikipedia-based feature vectors to extract more related entities from the document text.  ...  can be found at: https://web.cs.dal.ca/~lipczak/erd/ ACKNOWLEDGMENTS We would like to thank Axel Soto, Armin Sajadi, Seyednaser Nourashrafeddin and Krzysztof Lipczak for useful discussions and help with  ... 
doi:10.1145/2633211.2634351 dblp:conf/sigir/LipczakKM14 fatcat:gacer2ag6fflxf3m2h3iz7xnza

With a Little Help from my Neighbors

Johanna Geiß, Michael Gertz
2016 Proceedings of the 25th International Conference Companion on World Wide Web - WWW '16 Companion  
In this paper, we present a novel approach to person name disambiguation and linking that uses a large-scale social network extracted from the English Wikipedia.  ...  Driven by the popularity of social networks, there has been an increasing interest in employing such networks in the context of named entity linking.  ...  The graph in [2] is built from the Wikipedia link structure.  ... 
doi:10.1145/2872518.2891109 dblp:conf/www/GeissG16 fatcat:7djflvy6mbcuzjsufqjii7gpsq

Analysing Entity Context in Multilingual Wikipedia to Support Entity-Centric Retrieval Applications [chapter]

Yiwei Zhou, Elena Demidova, Alexandra I. Cristea
2015 Lecture Notes in Computer Science  
We discuss alternative ways such contexts can be built, including graph-based and article-based contexts.  ...  Furthermore, we analyse the similarities and the differences in these contexts in a case study including 80 entities and five Wikipedia language editions.  ...  In addition, we add the names of the linked articles to the entity context.  ... 
doi:10.1007/978-3-319-27932-9_17 fatcat:vshzpjqpmvdalmgmscjhgrjsii
« Previous Showing results 1 — 15 out of 12,978 results