Filters








30,694 Hits in 9.4 sec

Detecting candidate named entities in search queries

Areej Alasiry, Mark Levene, Alexandra Poulovassilis
2012 Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval - SIGIR '12  
The information extraction task of Named Entities Recognition (NER) has been recently applied to search engine queries, in order to better understand their semantics.  ...  Here we concentrate on the task prior to the classification of the named entities (NEs) into a set of categories, which is the problem of detecting candidate NEs via the subtask of query segmentation.We  ...  of candidate NEs, especially in multiple NE queries; and (iii) Fine-grained evaluation of NER for search engine queries.  ... 
doi:10.1145/2348283.2348463 dblp:conf/sigir/AlasiryLP12 fatcat:douoe2lesvgvripxtijlcaelj4

The NLPR_TAC Entity Linking System at TAC 2011

Tao Zhang, Kang Liu, Jun Zhao
2011 Text Analysis Conference  
Specially, for acronym mentions, we detect their entities by expanding acronym in the source documents. 2) Entity Linker, in which the similarity between an entity mention and an entity candidate in KB  ...  Our system mainly contains three components. 1) Entity Candidate Detector, in this component, out system identifies all the possible entities for an entity mention through a variety of knowledge sources  ...  for detecting the entity candidates through web search for these entity mentions.  ... 
dblp:conf/tac/ZhangL011 fatcat:vmgdjge2crf4pbb4ac663cv7lu

Neural Networks Models for Entity Discovery and Linking [article]

Dan Liu and Wei Lin and Shiliang Zhang and Si Wei and Hui Jiang
2016 arXiv   pre-print
This paper describes the USTC_NELSLIP systems submitted to the Trilingual Entity Detection and Linking (EDL) track in 2016 TAC Knowledge Base Population (KBP) contests.  ...  The entity linking (EL) system consists of two modules: a rule based candidate generation and a neural networks probability ranking model.  ...  Entity Linking In the entity linking task, each detected mention needs to be linked to a known entity in an existing knowledge base, namely Freebase in this task.  ... 
arXiv:1611.03558v1 fatcat:ehrctunyqndohn3wlu57cztsvy

A Hybrid Model for Trilingual Entity Detection and Linking Tasks at TAC KBP 2017

Zhenzhen Li, Qun Zhang, Ting Li, Jun Xu, Dawei Feng
2017 Text Analysis Conference  
The search engine and wikidata API are helpful to query expansion, so they are used to enhance the candidate coverage in the process of entity linking.  ...  This paper describes the our systems submitted to the Trilingual Entity Detection and Linking (EDL) track in 2017 TAC Knowledge Base Population (KBP) contests.  ...  Mention Detection In our work, we consider the nominal mention as a special named entity and detect both named and nominal mentions in the same model.  ... 
dblp:conf/tac/LiZLXF17 fatcat:qmlwyqxqnfcpnjhulxaqmhhasu

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  
This write-up describes Magnetic-IISAS team's approach to the entity recognition in search queries with which we have participated in ERD 2014 challenge.  ...  We match gathered entity surface forms against the original query to confirm the entity relevance to the query.  ...  detection: additional, gazeteer-based detection of Countries, US states and large websites names Entities Related by Wikipage Links In this section we discuss search result extension with entities related  ... 
doi:10.1145/2633211.2634352 dblp:conf/sigir/LaclavikCDDSS14 fatcat:cltolzcuezbf3jnv3a2gxajemu

The USTC NELSLIP Systems for Trilingual Entity Detection and Linking Tasks at TAC KBP 2016

Dan Liu, Wei Lin, Si Wei, Shiliang Zhang, Hui Jiang
2016 Text Analysis Conference  
This paper describes the USTC NELSLIP systems submitted to the Trilingual Entity Detection and Linking (EDL) track in 2016 TAC Knowledge Base Population (KBP) contests.  ...  The entity linking (EL) system consists of two modules: a rule based candidate generation and a neural networks probability ranking model.  ...  Entity Linking In the entity linking task, each detected mention needs to be linked to a known entity in an existing knowledge base, namely Freebase in this task.  ... 
dblp:conf/tac/LiuLWZJ16 fatcat:hsrwrmw7qzganealjh5qhsw634

Evaluating Entity Linking with Wikipedia

Ben Hachey, Will Radford, Joel Nothman, Matthew Honnibal, James R. Curran
2013 Artificial Intelligence  
Named Entity Linking (nel) grounds entity mentions to their corresponding node in a Knowledge Base (kb).  ...  Such systems typically search for candidate entities and then disambiguate them, returning either the best candidate or nil.  ...  Extraction is the detection and preparation of named entity mentions. Most nel datasets supply mention strings as queries.  ... 
doi:10.1016/j.artint.2012.04.005 fatcat:n7yrkdxdnzat7pk3m2qx4khn7y

A Piggyback System for Joint Entity Mention Detection and Linking in Web Queries

Marco Cornolti, Paolo Ferragina, Massimiliano Ciaramita, Stefan Rüd, Hinrich Schütze
2016 Proceedings of the 25th International Conference on World Wide Web - WWW '16  
In this paper we study the problem of linking open-domain web-search queries towards entities drawn from the full entity inventory of Wikipedia articles.  ...  The key algorithmic idea underlying SMAPH-2 is to first discover a candidate set of entities and then link-back those entities to their mentions occurring in the input query.  ...  NE-only detection (NE-only C2W task) In this task the goal is to identify named entities mentioned by queries of the ERD and GERDAQ datasets.  ... 
doi:10.1145/2872427.2883061 dblp:conf/www/CornoltiFCRS16 fatcat:llvnk3ivzrbjpbftuapbrwlzyi

DAI Approaches to the TAC-KBP 2011 Entity Linking Task

Danuta Ploch, Leonhard Hennig, Ernesto William De Luca, Sahin Albayrak
2011 Text Analysis Conference  
For the entity linking task, our system uses disambiguation features that are based on KB information as well as on semantic similarity relations between named entities identified in the document context  ...  and in KB entries.  ...  Candidate Generation Given a query name mention s, the task of the candidate generation component is to retrieve a set of candidate entities E(s) from the KB.  ... 
dblp:conf/tac/PlochHLA11 fatcat:xu2ly3kvireejilmh6drvvipx4

Semanticizing search engine queries

David Graus, Daan Odijk, Manos Tsagkias, Wouter Weerkamp, Maarten de Rijke
2014 Proceedings of the first international workshop on Entity recognition & disambiguation - ERD '14  
We describe how we adapt the Semanticizer-an open-source entity linking framework developed primarily at the University of Amsterdam-to the task of the ERD challenge: linking named entities in search engine  ...  context provided by search queries.  ...  In summary, the ERD challenge task is that of linking named entities in search engine queries to Wikipedia.  ... 
doi:10.1145/2633211.2634354 dblp:conf/sigir/GrausOTWR14 fatcat:ebyui5gjn5hs7ayqm4hod55iaq

Entity Linking for Queries by Searching Wikipedia Sentences [article]

Chuanqi Tan, Furu Wei, Pengjie Ren, Weifeng Lv, Ming Zhou
2017 arXiv   pre-print
The key idea is to search sentences similar to a query from Wikipedia articles and directly use the human-annotated entities in the similar sentences as candidate entities for the query.  ...  First, it can greatly reduce the number of candidate entities by filtering out irrelevant entities with the words in the query.  ...  The mainstream methods of entity linking for queries can be summed up in three steps: mention detection, candidate generation, and entity disambiguation.  ... 
arXiv:1704.02788v3 fatcat:45vk5cqd2rcjrmr7lpzonyx4ke

Entity Linking for Queries by Searching Wikipedia Sentences

Chuanqi Tan, Furu Wei, Pengjie Ren, Weifeng Lv, Ming Zhou
2017 Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing  
The key idea is to search sentences similar to a query from Wikipedia articles and directly use the human-annotated entities in the similar sentences as candidate entities for the query.  ...  First, it can greatly reduce the number of candidate entities by filtering out irrelevant entities with the words in the query.  ...  The mainstream methods of entity linking for queries can be summed up in three steps: mention detection, candidate generation, and entity disambiguation.  ... 
doi:10.18653/v1/d17-1007 dblp:conf/emnlp/TanWRLZ17 fatcat:wswe25vt7rdjpmsuwubdekn5aa

PolyUCOMP in TAC 2011 Entity Linking and Slot-Filling

Xu Jian, Zhengzhong Liu, Qin Lu, Patty Liu, Chenchen Wang, Yan Li, Xiaoning Li, Hanying Huang, Yang Song, Cheng Chang, Liaoming Zhou, Jing Xiao (+4 others)
2011 Text Analysis Conference  
In expanding person queries, name variants are produced using different rules. For organization acronym queries, an abbreviation extraction technique is employed.  ...  However, the NIL detection system brings significant loss in the final F-score. For the slot filling task, we developed a system which combines query expansion and pattern-based reasoning.  ...  LUCENE_SCORE Contextual R For candidates found in Lucene search, the search score is used.  ... 
dblp:conf/tac/JianLLLWLLHSCZX11 fatcat:skegvhfw2rhvleuglx2g6vv3yy

Combining similarities with regression based classifiers for Entity Linking at TAC 2010

César de Pablo-Sánchez, Juan Perea, Paloma Martínez
2010 Text Analysis Conference  
The UC3M team has sent three runs for each Entity Linking task proposed in the Knowledge Base Population (KBP) track at TAC 2010.  ...  for candidate filtering.  ...  Candidate retrieval For an entity to be a candidate, it needs to have some similarity in any relevant field with the name-string in the query.  ... 
dblp:conf/tac/Pablo-SanchezPM10 fatcat:bnczqm2dwffuvmhq3vhssmfb7q

USFD at KBP 2011: Entity Linking, Slot Filling and Temporal Bounding [article]

Amev Burman, Arun Jayapal, Sathish Kannan, Madhu Kavilikatta, Ayman Alhelbawy, Leon Derczynski, Robert Gaizauskas
2012 arXiv   pre-print
This paper describes the University of Sheffield's entry in the 2011 TAC KBP entity linking and slot filling tasks.  ...  We chose to participate in the monolingual entity linking task, the monolingual slot filling task and the temporal slot filling tasks.  ...  The search scheme used in this run uses the query mention and the different name variants for the query mention. 3.  ... 
arXiv:1203.5073v1 fatcat:osbnaunrovhvxi3o22t4rqy2qe
« Previous Showing results 1 — 15 out of 30,694 results