Filters








24,410 Hits in 4.5 sec

Fast Learning from Distributed Datasets without Entity Matching [article]

Giorgio Patrini, Richard Nock, Stephen Hardy, Tiberio Caetano
<span title="2016-03-13">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Traditionally, the problem is approached by first addressing entity matching and subsequently learning the classifier in a standard manner.  ...  Consider the following data fusion scenario: two datasets/peers contain the same real-world entities described using partially shared features, e.g. banking and insurance company records of the same customer  ...  Conclusion The key message of our paper is that Entity Matching addresses a very general but difficult problem, and in the comparatively restricted context of supervised learning from distributed datasets  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1603.04002v1">arXiv:1603.04002v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jzvwqzxnbncb7nvziezejrjqaq">fatcat:jzvwqzxnbncb7nvziezejrjqaq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201001080358/https://arxiv.org/pdf/1603.04002v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ba/cf/bacf2af6a684f1097a947c90508b001422450251.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1603.04002v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

MICK: A Meta-Learning Framework for Few-shot Relation Classification with Little Training Data [article]

Xiaoqing Geng, Xiwen Chen, Kenny Q. Zhu
<span title="2020-04-26">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We also propose a few-shot learning framework for relation classification, which is particularly powerful when the training data is very small.  ...  Additionally, we construct a brand new dataset: the TinyRel-CM dataset, a few-shot relation classification dataset in health domain with limited training data and challenging relation classes.  ...  The slow learner learns parameters of the context encoder (line 11) with objective function: L slow = L sup + L match , (4) Algorithm 1 Meta-learning with Support Classifier Require: distribution over  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.14164v1">arXiv:2004.14164v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/u65ygi6ahjekrbdx35pomhtqqe">fatcat:u65ygi6ahjekrbdx35pomhtqqe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200504201631/https://arxiv.org/pdf/2004.14164v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.14164v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Representation Learning Models for Entity Search [article]

Shijia E, Yang Xiang, Mohan Zhang
<span title="2017-01-15">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We focus on the problem of learning distributed representations for entity search queries, named entities, and their short descriptions.  ...  We analyze the strengths and weaknesses of each learning strategy and validate our methods on public datasets which contain four kinds of named entities, i.e., movies, TV shows, restaurants and celebrities  ...  The entity search task is to automatically obtain at least one entity that matches the entity search query from all the available entities.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1610.09091v3">arXiv:1610.09091v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4i42ubnb4bekjf6wffa7wnbd7a">fatcat:4i42ubnb4bekjf6wffa7wnbd7a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200911131108/https://arxiv.org/pdf/1610.09091v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/1c/db/1cdbb7a24e64ce665092421b50727b74553b1509.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1610.09091v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learning to Control Latent Representations for Few-Shot Learning of Named Entities [article]

Omar U. Florez, Erik Mueller
<span title="2019-11-19">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We experimentally show that our system obtains accurate results for few-shot learning of entity recognition in the Stanford Task-Oriented Dialogue dataset.  ...  Humans excel in continuously learning with small data without forgetting how to solve old problems.  ...  We use the Stanford Named Entity Recognizer (NER) 1 to augment the STDO dataset with 7 classes (Location, Person, Organization, Money, Percent, Date, Time) and a non-entity class.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.08542v1">arXiv:1911.08542v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sakqs7lmsze6vpvwezkz3pml5q">fatcat:sakqs7lmsze6vpvwezkz3pml5q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827114240/https://arxiv.org/pdf/1911.08542v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/fe/bf/febff7371748973c87a31c3093ccc125fd0342a7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.08542v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Extensive Error Analysis and a Learning-Based Evaluation of Medical Entity Recognition Systems to Approximate User Experience [article]

Isar Nejadgholi, Kathleen C. Fraser, Berry De Bruijn
<span title="2020-06-09">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We demonstrated the results of applying the proposed evaluation metric for a variety of deep learning medical entity recognition models trained with two datasets.  ...  Here we focus on span mismatch and show that its severity can vary from a serious error to a fully acceptable entity extraction due to the subjectivity of span annotations.  ...  Although the full context of the sentence helps the NER model to learn a better representation of the entity, many entities can be classified without seeing the full sentence and this is what the entity  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.05281v1">arXiv:2006.05281v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/czhc6u2bybarposcqgofscapwm">fatcat:czhc6u2bybarposcqgofscapwm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200624034847/https://arxiv.org/pdf/2006.05281v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.05281v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Evaluation of entity resolution approaches on real-world match problems

Hanna Köpcke, Andreas Thor, Erhard Rahm
<span title="2010-09-01">2010</span> <i title="VLDB Endowment"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/p6rqwwpkkjbcldejepcehaalby" style="color: black;">Proceedings of the VLDB Endowment</a> </i> &nbsp;
We consider approaches both with and without using machine learning to find suitable parameterization and combination of similarity functions.  ...  We also find that some challenging resolution tasks such as matching product entities from online shops are not sufficiently solved with conventional approaches based on the similarity of attribute values  ...  Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.14778/1920841.1920904">doi:10.14778/1920841.1920904</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yxmus33jcnhs5kf6hqsara44ye">fatcat:yxmus33jcnhs5kf6hqsara44ye</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20101009060703/http://dbs.uni-leipzig.de:80/file/EvaluationOfEntityResolutionApproaches_vldb2010_CameraReady.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/cf/6c/cf6c8ce4ec5bbbae9be4b9076c41d49a8eaad7b3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.14778/1920841.1920904"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Fast Record Linkage for Company Entities [article]

Thomas Gschwind, Christoph Miksovic, Julian Minder, Katsiaryna Mirylenka, Paolo Scotton
<span title="2019-09-27">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work we focus on company entity matching, where company name, location and industry are taken into account.  ...  Record linkage is an essential part of nearly all real-world systems that consume structured and unstructured data coming from different sources.  ...  To this extent, several approaches have been envisaged ranging from feature matching or rule-based to machine learning approaches.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.08667v3">arXiv:1907.08667v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wd252crxcve6xecb2vlyme567a">fatcat:wd252crxcve6xecb2vlyme567a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200824194618/https://arxiv.org/pdf/1907.08667v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/06/bf/06bfc0506f44ab71d423ef2df5589caa05ec582d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.08667v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Memory, Show the Way: Memory Based Few Shot Word Representation Learning

Jingyuan Sun, Shaonan Wang, Chengqing Zong
<span title="">2018</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/u3ideoxy4fghvbsstiknuweth4" style="color: black;">Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</a> </i> &nbsp;
Distributional semantic models (DSMs) generally require sufficient examples for a word to learn a high quality representation.  ...  In this paper, we propose Mem2Vec, a memory based embedding learning method capable of acquiring high quality word representations from fairly limited context.  ...  The fast adaption phase occurs when we need to learn a new word from minimal context.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/d18-1173">doi:10.18653/v1/d18-1173</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/emnlp/SunWZ18.html">dblp:conf/emnlp/SunWZ18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/skgqcydy2zbbnlmvjufwels6mq">fatcat:skgqcydy2zbbnlmvjufwels6mq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200505062820/https://www.aclweb.org/anthology/D18-1173.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/cb/9a/cb9a176b7021eb8a577631a38f08aacf54eb6bf6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/d18-1173"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

DIVINE: A Generative Adversarial Imitation Learning Framework for Knowledge Graph Reasoning

Ruiping Li, Xiang Cheng
<span title="">2019</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/u3ideoxy4fghvbsstiknuweth4" style="color: black;">Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</a> </i> &nbsp;
Experimental results on two benchmark datasets show that our framework improves the performance of existing RL-based methods without extra reward engineering.  ...  However, existing RL-based methods require numerous trials for path-finding and rely heavily on meticulous reward engineering to fit specific dataset, which is inefficient and laborious to apply to fast-evolving  ...  learn reasoning policies and reward functions self-adaptively to adapt the fast evolutions of real-world KGs.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/d19-1266">doi:10.18653/v1/d19-1266</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/emnlp/LiC19.html">dblp:conf/emnlp/LiC19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6ptaa4qdc5fuhcr5s2adzifkke">fatcat:6ptaa4qdc5fuhcr5s2adzifkke</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200821144225/https://www.aclweb.org/anthology/D19-1266.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/10/eb/10eb3ac22efc24eb84e64b6ee08b4362a78f292c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/d19-1266"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Relational Kernel-Based Grasping with Numerical Features [chapter]

Laura Antanas, Plinio Moreno, Luc De Raedt
<span title="">2016</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
We evaluate our relational kernel-based approach on a realistic dataset with 8 objects.  ...  This paper proposes a new statistical relational learning approach to recognize graspable points in object point clouds.  ...  From the SRL perspective, purely relational learning techniques have been previously used to learn from point clouds.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-40566-7_1">doi:10.1007/978-3-319-40566-7_1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/usvtysa54bawjb4l46i2s5ixny">fatcat:usvtysa54bawjb4l46i2s5ixny</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20171127083925/https://core.ac.uk/download/pdf/34655776.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9e/59/9e593a6013fa251e6bd62e04b07085536dd13d18.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-40566-7_1"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Robust and Scalable Entity Alignment in Big Data [article]

James Flamino, Christopher Abriola, Ben Zimmerman, Zhongheng Li, Joel Douglas
<span title="2020-04-19">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, with millions of nodes and billions of edges, the idea of alignment between a myriad of graphs of similar scale using features extracted from potentially sparse or incomplete datasets becomes  ...  In particular, the concept of matching entities across networks has grown in significance in the world of social science as communicative networks such as social media have expanded in scale and popularity  ...  Ultimately, entity alignment faces the difficult problem of matching unique nodes across ever-growing datasets.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.08991v1">arXiv:2004.08991v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fsq5zpot2fa2tcyrdidvrdbtr4">fatcat:fsq5zpot2fa2tcyrdidvrdbtr4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826215029/https://arxiv.org/ftp/arxiv/papers/2004/2004.08991.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/0e/d8/0ed8c01c0053ca439f09ca28ac0654d736596595.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.08991v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Question Answering by Reasoning Across Documents with Graph Convolutional Networks [article]

Nicola De Cao, Wilker Aziz, Ivan Titov
<span title="2019-04-07">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Our Entity-GCN method is scalable and compact, and it achieves state-of-the-art results on a multi-document question answering dataset, WikiHop (Welbl et al., 2018).  ...  Mentions of entities are nodes of this graph while edges encode relations between different mentions (e.g., within- and cross-document co-reference).  ...  Our Entity-GCN outperforms recent prior work without learning any language model to process the input but relying on a pretrained one (ELMo -without fine-tunning it) and applying R-GCN to reason among  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1808.09920v3">arXiv:1808.09920v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pdd4mc5tkjgezeduqouky2yrba">fatcat:pdd4mc5tkjgezeduqouky2yrba</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200905032259/https://arxiv.org/pdf/1808.09920v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/2f/f7/2ff7e357cb80c6b6dbfe614a9dc336d220d12e62.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1808.09920v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

WOO

Kedar Bellare, Carlo Curino, Ashwin Machanavajihala, Peter Mika, Mandar Rahurkar, Aamod Sane
<span title="2013-08-27">2013</span> <i title="VLDB Endowment"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/p6rqwwpkkjbcldejepcehaalby" style="color: black;">Proceedings of the VLDB Endowment</a> </i> &nbsp;
The new battleground revolves around technologies for the ingestion, disambiguation and enrichment of entities from a variety of structured and unstructured data sources -we refer to this process as knowledge  ...  ), (ii) the architecture and technical solutions we devised, and (iii) an evaluation on real-world production datasets.  ...  A machine-learned model also requires a "golden" data set (GDS) consisting of matching and non-matching entity pairs.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.14778/2536222.2536236">doi:10.14778/2536222.2536236</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2nlyamewibe7rl6s22dkhqy5xq">fatcat:2nlyamewibe7rl6s22dkhqy5xq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170812230416/http://vldb.org/pvldb/vol6/p1114-rahurkar.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/68/57/6857346e57e49509dd6d8bf9f95d2dcca378903c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.14778/2536222.2536236"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Big Data and Named Entity Recognition Approaches for Urdu Language

Qudsia Jamil, Muhammad Rehman Zafar
<span title="2018-04-13">2018</span> <i title="European Alliance for Innovation n.o."> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/y4l63sf5djh4zowjsurq6fija4" style="color: black;">EAI Endorsed Transactions on Scalable Information Systems</a> </i> &nbsp;
It is difficult task to extract useful information from Big data efficiently. From unstructured text Information extraction is a technique which used to extract information.  ...  Named Entity Recognition (NER) is an essential component of information extraction in the field of Natural Language Processing (NLP).  ...  Later on system is made to learn all of these clusters and is able to identify the matching entities as in learned clusters.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.4108/eai.13-4-2018.154469">doi:10.4108/eai.13-4-2018.154469</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xwhafqzyfjbs3a2g3olholwp5e">fatcat:xwhafqzyfjbs3a2g3olholwp5e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180507173120/http://eudl.eu/pdf/10.4108/eai.13-4-2018.154469" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/bf/17/bf17c5f2e8b3c7abf7641417c3e6ce3af238d4dc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.4108/eai.13-4-2018.154469"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

POLYGLOT-NER: Massive Multilingual Named Entity Recognition [article]

Rami Al-Rfou, Vivek Kulkarni, Bryan Perozzi, Steven Skiena
<span title="2014-10-14">2014</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Then, we automatically generate datasets from Wikipedia link structure and Freebase attributes.  ...  Our method learns distributed word representations (word embeddings) which encode semantic and syntactic features of words in each language.  ...  Oversampling To overcome the effect of missing annotations, we correct the label distribution by oversampling from the entity classes.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1410.3791v1">arXiv:1410.3791v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kqkxgidkgzf2lp4iuh4twuicnm">fatcat:kqkxgidkgzf2lp4iuh4twuicnm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191014213329/https://arxiv.org/pdf/1410.3791v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/af/5f/af5f309a261154077ce8a01f3a4453d8ebc2dbe8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1410.3791v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 24,410 results