Filters








3,263 Hits in 8.2 sec

Feature Interaction-aware Graph Neural Networks [article]

Kaize Ding, Yichuan Li, Jundong Li, Chenghao Liu, Huan Liu
<span title="2020-01-22">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose Feature Interaction-aware Graph Neural Networks (FI-GNNs), a plug-and-play GNN framework for learning node representations encoded with informative feature interactions.  ...  Specifically, the proposed framework is able to highlight informative feature interactions in a personalized manner and further learn highly expressive node representations on feature-sparse graphs.  ...  Table 1 reports brief statistics for each dataset. Note that the node features of all the above datasets are generated by the bag-of-words model, yielding highdimensional and sparse node features.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.07110v2">arXiv:1908.07110v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fk76u5vxorfljom5s3ivwhk6ku">fatcat:fk76u5vxorfljom5s3ivwhk6ku</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321024827/https://arxiv.org/pdf/1908.07110v2.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/1908.07110v2" 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>

Propositionalization and Embeddings: Two Sides of the Same Coin [article]

Nada Lavrač and BlažŠkrlj and Marko Robnik-Šikonja
<span title="2020-06-08">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present two efficient implementations of the unifying methodology: an instance-based PropDRM approach, and a feature-based PropStar approach to data transformation and learning, together with their  ...  In addition to the unifying framework, the novelty of this paper is a unifying methodology combining propositionalization and embeddings, which benefits from the advantages of both in solving complex data  ...  We wish to thank Jan Kralj for his insightful comments on the formulation of the proposed framework and for mathematical proofreading.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.04410v1">arXiv:2006.04410v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/idpgnam52jdnbbpv32qhm7o3im">fatcat:idpgnam52jdnbbpv32qhm7o3im</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200928152433/https://arxiv.org/pdf/2006.04410v1.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/c8/0ec80c29b7e9a8da1e4dcd7333a6d9a8e9873fc2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.04410v1" 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>

Semantic Relations and Deep Learning [article]

Vivi Nastase, Stan Szpakowicz
<span title="2021-04-15">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
A new Chapter 5 of the book, by Vivi Nastase and Stan Szpakowicz, discusses relation classification/extraction in the deep-learning paradigm which arose after the first edition appeared.  ...  The second edition of "Semantic Relations Between Nominals" by Vivi Nastase, Stan Szpakowicz, Preslav Nakov and Diarmuid \'O S\'eaghdha has been published in April 2021 by Morgan & Claypool (www.morganclaypoolpublishers.com  ...  ., 2011] which used paths in knowledge graphs for link prediction.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.05426v4">arXiv:2009.05426v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rmzoalfwcza4nex7pd4u6w7kbe">fatcat:rmzoalfwcza4nex7pd4u6w7kbe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201003212127/https://arxiv.org/pdf/2009.05426v2.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> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.05426v4" 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>

Propositionalization and embeddings: two sides of the same coin

Nada Lavrač, Blaž Škrlj, Marko Robnik-Šikonja
<span title="2020-06-28">2020</span> <i title="Springer Science and Business Media LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/h4nnd7sxwzcwhetu5qkjbcdh6u" style="color: black;">Machine Learning</a> </i> &nbsp;
We present two efficient implementations of the unifying methodology: an instance-based PropDRM approach, and a feature-based PropStar approach to data transformation and learning, together with their  ...  In addition to the unifying framework, the novelty of this paper is a unifying methodology combining propositionalization and embeddings, which benefits from the advantages of both in solving complex data  ...  For example, for text, given a word, the word-2vec embedding method (Mikolov et al. 2013 ) predicts words in its neighborhood.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10994-020-05890-8">doi:10.1007/s10994-020-05890-8</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/32704202">pmid:32704202</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC7366599/">pmcid:PMC7366599</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/byyvqrplkrdvbcqvfctswm3ncu">fatcat:byyvqrplkrdvbcqvfctswm3ncu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108161235/https://link.springer.com/content/pdf/10.1007/s10994-020-05890-8.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/7e/f9/7ef93b8c3537ec612657bd4d8ac39ed637424354.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10994-020-05890-8"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> springer.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7366599" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

World Knowledge Representation [chapter]

Zhiyuan Liu, Yankai Lin, Maosong Sun
<span title="">2020</span> <i title="Springer Singapore"> Representation Learning for Natural Language Processing </i> &nbsp;
With the well-structured united knowledge representation, KGs are widely used in a variety of applications to enhance their system performance.  ...  KGs are usually constructed from existing Semantic Web datasets in Resource Description Framework (RDF) with the help of manual annotation, while it can also be automatically enriched by extracting knowledge  ...  Then it follows a recent state-of-the-art entity-oriented search framework, the word-entity duet [86] , and matches documents to queries with both bag-of-words and bag-of-entities.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-981-15-5573-2_7">doi:10.1007/978-981-15-5573-2_7</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nzn3gdsjozh4jfzqu6ux345uci">fatcat:nzn3gdsjozh4jfzqu6ux345uci</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200709104413/https://link.springer.com/content/pdf/10.1007%2F978-981-15-5573-2_7.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/a8/f8/a8f8fc84dc6703c9d8cc2010a7ac26cc4c5f6125.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-981-15-5573-2_7"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> springer.com </button> </a>

Personalized Entity Resolution with Dynamic Heterogeneous Knowledge Graph Representations [article]

Ying Lin, Han Wang, Jiangning Chen, Tong Wang, Yue Liu, Heng Ji, Yang Liu, Premkumar Natarajan
<span title="2021-04-14">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The growing popularity of Virtual Assistants poses new challenges for Entity Resolution, the task of linking mentions in text to their referent entities in a knowledge base.  ...  After that, we incorporate product, customer, and history representations into a neural reranking model to predict which candidate is most likely to be purchased for a specific customer.  ...  Introduction Given an entity mention as a query, the goal of entity resolution (or entity linking) (Ji and Grishman, 2011) is to link the mention to its corresponding entry in a target knowledge base  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.02667v2">arXiv:2104.02667v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xg2c62znkzcenihuuv6hsg2uw4">fatcat:xg2c62znkzcenihuuv6hsg2uw4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210416001405/https://arxiv.org/pdf/2104.02667v2.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/d1/8e/d18ebaf39cd27aa65c1bcf3748f1824d668709b5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.02667v2" 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>

Prediction of News Popularity Based on Deep Neural Network

Yan Cai, Zhiqiang Zheng, Baiyuan Ding
<span title="2022-03-31">2022</span> <i title="Hindawi Limited"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/fw4azkpu65d2thmrwfkoawyxse" style="color: black;">Scientific Programming</a> </i> &nbsp;
This paper proposes a news popularity prediction method based on GRU deep neural network.  ...  Establish a GRU neural network regression prediction model to predict hot news on the Internet.  ...  Traditional text representations are based on bag-ofwords models. e shortest answer is the one-hot model, which arranges all the words in the corpus in a column.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2022/8280036">doi:10.1155/2022/8280036</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cqwaf65bwnfidhttdceurqgyay">fatcat:cqwaf65bwnfidhttdceurqgyay</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220401122949/https://downloads.hindawi.com/journals/sp/2022/8280036.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/fb/71/fb71f9f39e9a13e69b4c48f8c851b58a863adf8b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2022/8280036"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> hindawi.com </button> </a>

Hybrid Attention-Based Transformer Block Model for Distant Supervision Relation Extraction [article]

Yan Xiao, Yaochu Jin, Ran Cheng, Kuangrong Hao
<span title="2020-03-26">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
of our model for the DSRE task.  ...  To address this issue, we propose a new framework using hybrid attention-based Transformer block with multi-instance learning to perform the DSRE task.  ...  BGWA [20] : A Bi-GRU based model with word and sentence level attention.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.11518v2">arXiv:2003.11518v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zfbdpeyglfdnbdtlfu645nrz6y">fatcat:zfbdpeyglfdnbdtlfu645nrz6y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200327111658/https://arxiv.org/vc/arxiv/papers/2003/2003.11518v1.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/19/49/194985d2b92696c4a061e27e060901532cd6934c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.11518v2" 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>

A review of various semi-supervised learning models with a deep learning and memory approach

Jamshid Bagherzadeh, Hasan Asil
<span title="2018-12-06">2018</span> <i title="Springer Science and Business Media LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/b4iekbmgnbaw5gr4hjudn7j6ca" style="color: black;">Iran Journal of Computer Science</a> </i> &nbsp;
A research solution for future studies is to benefit from memory to increase such an effect. Memory-based neural networks are new models of neural networks which can be used in this area.  ...  In addition, deep neural networks are used to extract data features using a multilayer model.  ...  A highly well-known example of sparse autoencoders is a nine-layer model with a local link to the pooling layer and contrast normalization.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s42044-018-00027-6">doi:10.1007/s42044-018-00027-6</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nccifurxyzc33fa5xfprrlupxq">fatcat:nccifurxyzc33fa5xfprrlupxq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190504014357/https://link.springer.com/content/pdf/10.1007%2Fs42044-018-00027-6.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/7d/1f/7d1f7763d875795011b481e3c49461474bd08ae5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s42044-018-00027-6"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Representation learning of knowledge graphs using convolutional neural networks

Wang Gao, Yuan Fang, Fan Zhang, Zhifeng Yang
<span title="">2020</span> <i title="Czech Technical University in Prague - Central Library"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/pdm5r35z65fkvamed4nxpeyqqy" style="color: black;">Neural Network World</a> </i> &nbsp;
We first propose a novel neural model to encode the text descriptions of entities based on Convolutional Neural Networks (CNN).  ...  Experimental results on two datasets show that our models obtain state-of-the-art results on link prediction and triplet classification tasks, and achieve the best performance on the relation classification  ...  Acknowledgement We would like to thank the anonymous reviewers for their valuable comments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.14311/nnw.2020.30.011">doi:10.14311/nnw.2020.30.011</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pciojuzzibgefipsf56ol5fgwy">fatcat:pciojuzzibgefipsf56ol5fgwy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201209114332/http://nnw.cz/doi/2020/NNW.2020.30.011.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/70/21/7021fca57e84632e98b1273321de7f642267cd5c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.14311/nnw.2020.30.011"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Discriminative Information Retrieval for Knowledge Discovery [article]

Tongfei Chen, Benjamin Van Durme
<span title="2016-10-06">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a framework for discriminative Information Retrieval (IR) atop linguistic features, trained to improve the recall of tasks such as answer candidate passage retrieval, the initial step in text-based  ...  We formalize this as an instance of linear feature-based IR (Metzler and Croft, 2007), illustrating how a variety of knowledge discovery tasks are captured under this approach, leading to a 44% improvement  ...  showed improved performance in retrieval as compared with a bag-of-words baseline IR system, the model was proof-of-concept, employing a simple linear interpolation between bag-of-words and NE features  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1610.01901v1">arXiv:1610.01901v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ikglxj5lf5c2dfrjfjewwuyq74">fatcat:ikglxj5lf5c2dfrjfjewwuyq74</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200901104036/https://arxiv.org/pdf/1610.01901v1.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/3d/c8/3dc8f5a7dcdfbdfad4a14bd9a4587de1fb1c2c22.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1610.01901v1" 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>

Ensemble deep learning: A review [article]

M.A. Ganaie and Minghui Hu and A.K. Malik and M. Tanveer and P.N. Suganthan
<span title="2022-03-08">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Application of deep ensemble models in different domains is also briefly discussed. Finally, we conclude this paper with some future recommendations and research directions.  ...  This paper reviews the state-of-art deep ensemble models and hence serves as an extensive summary for the researchers.  ...  For predicting the short term load forecasting, an ensemble of bagging with neural networks [52] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.02395v2">arXiv:2104.02395v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lq73jqso5vadvnqfnnmw4zul4q">fatcat:lq73jqso5vadvnqfnnmw4zul4q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220310001435/https://arxiv.org/pdf/2104.02395v2.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/d1/f2/d1f2e8928e44a91636ff554e39ddd5feeb7889ce.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.02395v2" 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>

Benchmarking Performance of Document Level Classification and Topic Modeling

Abid. A. Memon, M. Asif Memon, Kaleemullah Bhatti, Kamsing Nonlaopon, Ilyas Khan
<span title="">2022</span> <i title="Computers, Materials and Continua (Tech Science Press)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/amujz7fcqna6do727z6ev3ueo4" style="color: black;">Computers Materials &amp; Continua</a> </i> &nbsp;
TFIDF matrix and cosine similarity measure have been used to identify similar documents in a collection and find the semantic meaning of words in a document FastText model has been applied.  ...  Finally, we trained Multinomial Naïve Bayes, XGBoost, Bagging, and Deep dense neural network. Bagging and deep dense neural network outperformed the other algorithms.  ...  It fits N-base estimators on a random subset of the original data. And it aggregates their scores(predictions) to form a final score(prediction).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.32604/cmc.2022.020083">doi:10.32604/cmc.2022.020083</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vigwicqncrf6zobmu4otxvho2m">fatcat:vigwicqncrf6zobmu4otxvho2m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220613024423/https://www.techscience.com/cmc/v71n1/45375/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/52/7a/527a58f28dba757afe577cd62b66dbbce26e321e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.32604/cmc.2022.020083"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Graph Clustering with Dynamic Embedding [article]

Carl Yang, Mengxiong Liu, Zongyi Wang, Liyuan Liu, Jiawei Han
<span title="2017-12-21">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To provide more insight, we theoretically analyze our interpretation of network clusters and find its underlying connections with two widely applied approaches for network modeling.  ...  Recent literature on this topic has reached a consensus that node contents and link structures should be integrated for reliable graph clustering, especially in an unsupervised setting.  ...  model for link analysis and a discriminative model for content analysis. • CP [33]: a series of state-of-the-art community detection methods based on content propagation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1712.08249v1">arXiv:1712.08249v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wkll4bj4xrfsxew2dys3jefowu">fatcat:wkll4bj4xrfsxew2dys3jefowu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191024093432/https://arxiv.org/pdf/1712.08249v1.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/b1/8f/b18f628cb949750036fff7bc66e50765532ac2fe.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1712.08249v1" 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>

Semantic indexing with deep learning: a case study

Yan Yan, Xu-Cheng Yin, Bo-Wen Zhang, Chun Yang, Hong-Wei Hao
<span title="2016-08-30">2016</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/agmh2gzkhvashbstejvq4mfexi" style="color: black;">Big Data Analytics</a> </i> &nbsp;
Next, we construct a high-dimensional space representation with Wikipedia category extension, which contains more semantic information than bag-of-words.  ...  In particular, convolutional neural networks (CNNs) [15] are a flexible neural network framework that can be used to reduce variations and exploit spatial correlations using weight sharing and local connectivity  ...  Endnotes Fig. 1 1 A hierarchical CNNs-based framework with multi-label classification for semantic indexing (HC) Fig. 2 2 Words mapping with Wikipedia the number of true positives, FN is the number  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s41044-016-0007-z">doi:10.1186/s41044-016-0007-z</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zs6zrrrdm5abnfdg2rabohc5dm">fatcat:zs6zrrrdm5abnfdg2rabohc5dm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20171014002114/http://publisher-connector.core.ac.uk/resourcesync/data/Springer-OA/pdf/6aa/aHR0cDovL2xpbmsuc3ByaW5nZXIuY29tLzEwLjExODYvczQxMDQ0LTAxNi0wMDA3LXoucGRm.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/bf/a7/bfa7c7088ac187358461f8572c8254827742497c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s41044-016-0007-z"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> springer.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 3,263 results