Filters








17,517 Hits in 5.3 sec

Self-Supervised Similarity Learning for Digital Pathology [article]

Jacob Gildenblat, Eldad Klaiman
<span title="2020-01-13">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We show that our method yields better retrieval task results than existing ImageNet based and generic self-supervised feature extraction methods.  ...  We apply the method on digital pathology WSIs from the Camelyon16 train set and assess and compare our method by measuring image retrieval of tumor tiles and descriptor pair distance ratio for distant/  ...  Acknowledgements The authors would like to thank Amal Lahiani for her invaluable insights and constructive review.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1905.08139v3">arXiv:1905.08139v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vr3yot4kzjdkrgved3zysl3ysq">fatcat:vr3yot4kzjdkrgved3zysl3ysq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930033159/https://arxiv.org/pdf/1905.08139v3.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/82/2a/822a21375f3e60103d31c23410cea184f6f3b2f2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1905.08139v3" 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>

Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever [article]

Libo Qin, Yijia Liu, Wanxiang Che, Haoyang Wen, Yangming Li, Ting Liu
<span title="2019-09-18">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Two methods are proposed to make the training feasible without labeled retrieval data, which include distant supervision and Gumbel-Softmax technique.  ...  Querying the knowledge base (KB) has long been a challenge in the end-to-end task-oriented dialogue system.  ...  Acknowledgments We thank the anonymous reviewers for their helpful comments and suggestions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.06762v2">arXiv:1909.06762v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uq55owghu5dirbg64uazityz7y">fatcat:uq55owghu5dirbg64uazityz7y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200901134256/https://arxiv.org/pdf/1909.06762v2.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/1d/e1/1de10051743f8faf1bad1b8aeaf5dae27ca71a2d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.06762v2" 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>

Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever

Libo Qin, Yijia Liu, Wanxiang Che, Haoyang Wen, Yangming Li, Ting Liu
<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;
Two methods are proposed to make the training feasible without labeled retrieval data, which include distant supervision and Gumbel-Softmax technique.  ...  Querying the knowledge base (KB) has long been a challenge in the end-to-end taskoriented dialogue system.  ...  Acknowledgments We thank the anonymous reviewers for their helpful comments and suggestions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/d19-1013">doi:10.18653/v1/d19-1013</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/emnlp/QinLCWLL19.html">dblp:conf/emnlp/QinLCWLL19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sqk2wqv6vrd3fb6foil22pmojq">fatcat:sqk2wqv6vrd3fb6foil22pmojq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191203111155/https://www.aclweb.org/anthology/D19-1013.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/be/ae/beae3ba45ea57e69696f4ded5a971dcbb9301da3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/d19-1013"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Effective Slot Filling Based on Shallow Distant Supervision Methods [article]

Benjamin Roth, Tassilo Barth, Michael Wiegand, Mittul Singh, Dietrich Klakow
<span title="2014-01-06">2014</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Important factors for effective extraction are the training and tuning scheme for distant supervision classifiers, and the query expansion by a translation model based on Wikipedia links.  ...  Improvements mainly have been obtained by a feature representation focusing on surface skip n-grams and improved scoring for extracted distant supervision patterns.  ...  The LSV 2013 English slot filling system Re-lationFactory is a distant supervision system for query-based relation extraction.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1401.1158v1">arXiv:1401.1158v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qr4u2zmtp5cd7kb7wvnntpmyoa">fatcat:qr4u2zmtp5cd7kb7wvnntpmyoa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191016133505/https://arxiv.org/pdf/1401.1158v1.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/40/62/4062a185b0aeb76626b13a59814128dd2a26ddc3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1401.1158v1" 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>

Factoid Question Answering with Distant Supervision

Hongzhi Zhang, Xiao Liang, Guangluan Xu, Kun Fu, Feng Li, Tinglei Huang
<span title="2018-06-05">2018</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/4d3elkqvznfzho6ki7a35bt47u" style="color: black;">Entropy</a> </i> &nbsp;
Experimental results show that the model solely trained on generated data via the distant supervision and mined paraphrases could answer real-world questions with the accuracy of 49.34%.  ...  Recent years have witnessed the development of QA methods based on deep learning.  ...  Acknowledgments: We would like to thank the anonymous reviewers for their insightful comments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/e20060439">doi:10.3390/e20060439</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33265529">pmid:33265529</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5efyksdxzzb5deamamqcnamukq">fatcat:5efyksdxzzb5deamamqcnamukq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190302191954/http://pdfs.semanticscholar.org/a0c9/ccf3672f8e2ad0b76bd753d6242c1aafb07f.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/a0/c9/a0c9ccf3672f8e2ad0b76bd753d6242c1aafb07f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/e20060439"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

When Retriever-Reader Meets Scenario-Based Multiple-Choice Questions [article]

Zixian Huang, Ao Wu, Yulin Shen, Gong Cheng, Yuzhong Qu
<span title="2021-09-05">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Since a scenario contains both keyphrases for retrieval and much noise, retrieval for SQA is extremely difficult.  ...  Moreover, it can hardly be supervised due to the lack of relevance labels of paragraphs for SQA.  ...  It significantly outperformed existing unsupervised, distant supervision based, and transfer learning based retrievers.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.13875v2">arXiv:2108.13875v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fj7uxyufyvbcdovwcuwoy62yj4">fatcat:fj7uxyufyvbcdovwcuwoy62yj4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210908193120/https://arxiv.org/pdf/2108.13875v2.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/c5/3b/c53b77645811a78b25d6b41feff37170811f7b88.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.13875v2" 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>

Unsupervised Cross-Media Hashing with Structure Preservation [article]

Xiangyu Wang, Alex Yong-Sang Chia
<span title="2016-03-18">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The need for effective and accurate data retrieval from heterogeneous data sources has attracted much research interest in cross-media retrieval.  ...  These hash codes empower the similarity between data of different media types to be evaluated directly.  ...  [14] proposed a kernel-based supervised hashing method which sequentially trains the hash functions based on similar and dissimilar pairs.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1603.05782v1">arXiv:1603.05782v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2kdhbs3qcjfatost6nqydfsxtq">fatcat:2kdhbs3qcjfatost6nqydfsxtq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200829215109/https://arxiv.org/pdf/1603.05782v1.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/1c/b8/1cb81ebdb0ee02fb270e3b985886fe03a52ca577.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1603.05782v1" 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>

Supervision and Source Domain Impact on Representation Learning: A Histopathology Case Study [article]

Milad Sikaroudi, Amir Safarpoor, Benyamin Ghojogh, Sobhan Shafiei, Mark Crowley, H.R. Tizhoosh
<span title="2020-05-10">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We investigated the notion of similarity and dissimilarity in pathology whole-slide images and compared different setups from unsupervised and semi-supervised to supervised learning in our experiments.  ...  Although supervised techniques using deep neural networks have boosted the performance of representation learning, the need for a large set of labeled data limits the application of such methods.  ...  (a) (b) (c) (d) In this study, we aim to address shortcomings such as the definition of the similarity, investigation of the impact of the source and target domain datasets, and the level of supervision  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.08629v1">arXiv:2005.08629v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/k4gvu3dja5gbdmquypquyrsomm">fatcat:k4gvu3dja5gbdmquypquyrsomm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200520015522/https://arxiv.org/pdf/2005.08629v1.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/2005.08629v1" 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>

Supervision and Source Domain Impact on Representation Learning: A Histopathology Case Study

Milad Sikaroudi, Amir Safarpoor, Benyamin Ghojogh, Sobhan Shafiei, Mark Crowley, H.R. Tizhoosh
<span title="">2020</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/lhepmwuwpjhuvaie6zkwbkjaae" style="color: black;">2020 42nd Annual International Conference of the IEEE Engineering in Medicine &amp; Biology Society (EMBC)</a> </i> &nbsp;
We investigated the notion of similarity and dissimilarity in pathology whole-slide images and compared different setups from unsupervised and semi-supervised to supervised learning in our experiments.  ...  Although supervised techniques using deep neural networks have boosted the performance of representation learning, the need for a large sets of labeled data limits the application of such methods.  ...  (a) (b) (c) (d) In this study, we aim to address shortcomings such as the definition of the similarity, investigation of the impact of the source and target domain datasets, and the level of supervision  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/embc44109.2020.9176279">doi:10.1109/embc44109.2020.9176279</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33018251">pmid:33018251</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pctrq4kujfdplhlphw7dfd4asa">fatcat:pctrq4kujfdplhlphw7dfd4asa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200829163921/https://ieeexplore.ieee.org/ielx7/9167168/9175149/09176279.pdf?tp=&amp;arnumber=9176279&amp;isnumber=9175149&amp;ref=" 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/d3/40/d340a6478807103558d7b78d3f9183ed3a3730de.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/embc44109.2020.9176279"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Weakly-Supervised Concept-based Adversarial Learning for Cross-lingual Word Embeddings [article]

Haozhou Wang, James Henderson, Paola Merlo
<span title="2019-04-20">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a concept-based adversarial training method which for most languages improves the performance of previous unsupervised adversarial methods, especially for typologically distant language pairs  ...  In this paper, we propose a weakly-supervised adversarial training method to overcome this limitation, based on the intuition that mapping across languages is better done at the concept level than at the  ...  Table We provide our definition of similar and distant in section 5. We use uniform sampling for the target words because the distribution of the sampled sub-vocabulary is very small.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.09446v1">arXiv:1904.09446v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dholqshw6fhxlbnxdokwtx2uzu">fatcat:dholqshw6fhxlbnxdokwtx2uzu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930212155/https://arxiv.org/pdf/1904.09446v1.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/ab/a8ab44231b65379dd4d025b76961b14cbc8a2feb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.09446v1" 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>

Reading Wikipedia to Answer Open-Domain Questions

Danqi Chen, Adam Fisch, Jason Weston, Antoine Bordes
<span title="">2017</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5n6volmnonf5tn6xputi5f2t3e" style="color: black;">Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</a> </i> &nbsp;
Our experiments on multiple existing QA datasets indicate that (1) both modules are highly competitive with respect to existing counterparts and (2) multitask learning using distant supervision on their  ...  Our approach combines a search component based on bigram hashing and TF-IDF matching with a multi-layer recurrent neural network model trained to detect answers in Wikipedia paragraphs.  ...  Acknowledgments The authors thank Pranav Rajpurkar for testing Document Reader on the test set of SQuAD.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/p17-1171">doi:10.18653/v1/p17-1171</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/acl/ChenFWB17.html">dblp:conf/acl/ChenFWB17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/eibwd4tyjnh3xc76jafk32y5re">fatcat:eibwd4tyjnh3xc76jafk32y5re</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170613105130/http://cs.stanford.edu/people/danqi/papers/acl2017.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/2e/50/2e50800a2bfc2d05a697340535853592d9d1f656.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/p17-1171"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Reading Wikipedia to Answer Open-Domain Questions [article]

Danqi Chen, Adam Fisch, Jason Weston, Antoine Bordes
<span title="2017-04-28">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Our experiments on multiple existing QA datasets indicate that (1) both modules are highly competitive with respect to existing counterparts and (2) multitask learning using distant supervision on their  ...  Our approach combines a search component based on bigram hashing and TF-IDF matching with a multi-layer recurrent neural network model trained to detect answers in Wikipedia paragraphs.  ...  Acknowledgments The authors thank Pranav Rajpurkar for testing Document Reader on the test set of SQuAD.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1704.00051v2">arXiv:1704.00051v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4eyc5giekzhg3eaa5jvgrmqvdu">fatcat:4eyc5giekzhg3eaa5jvgrmqvdu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191026120600/https://arxiv.org/pdf/1704.00051v2.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/45/2f450cced44cdfd4251a35e006a0ef75f84d7a70.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1704.00051v2" 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>

Aligning Open IE Relations and KB Relations using a Siamese Network Based on Word Embedding

Rifki Afina Putri, Giwon Hong, Sung-Hyon Myaeng
<span title="">2019</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/7twswtvlirhelozfpw7mm74sga" style="color: black;">Proceedings of the 13th International Conference on Computational Semantics - Long Papers</a> </i> &nbsp;
In order to make the approach practical, we automatically generate a training dataset using a distant supervision approach instead of relying on a hand-labeled dataset.  ...  Although relations from an Open IE system are more extensible than those used in a traditional Information Extraction system and a Knowledge Base (KB) such as Knowledge Graphs, the former lacks in semantics  ...  Moreover, since the rule-based model predictions are made with the distant supervision rule, we can also infer the quality of our distant supervision dataset based on the scores of the model (64.5% alignments  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w19-0412">doi:10.18653/v1/w19-0412</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/iwcs/PutriHM19.html">dblp:conf/iwcs/PutriHM19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dwskqes2tzhrjlof56rduzeibu">fatcat:dwskqes2tzhrjlof56rduzeibu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191015102654/https://www.aclweb.org/anthology/W19-0412.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/b8/52/b852827858be9fcca1f8c82ba1c50a0b5c7b6c9d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w19-0412"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Weakly-supervised Contextualization of Knowledge Graph Facts

Nikos Voskarides, Edgar Meij, Ridho Reinanda, Abhinav Khaitan, Miles Osborne, Giorgio Stefanoni, Prabhanjan Kambadur, Maarten de Rijke
<span title="">2018</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ibcfmixrofb3piydwg5wvir3t4" style="color: black;">The 41st International ACM SIGIR Conference on Research &amp; Development in Information Retrieval - SIGIR &#39;18</a> </i> &nbsp;
In order to obtain the annotations required to train the learning to rank model at scale, we generate training data automatically using distant supervision on a large entity-tagged text corpus.  ...  The ranking model combines features that we automatically learn from data and that represent the query-candidate facts with a set of hand-crafted features we devised or adjusted for this task.  ...  Acknowledgements The authors would like to thank the anonymous reviewers (and especially reviewer #1) for their useful and constructive feedback.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3209978.3210031">doi:10.1145/3209978.3210031</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/sigir/VoskaridesMRKOS18.html">dblp:conf/sigir/VoskaridesMRKOS18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kmcewxfyazgizdmn6fhdtibxle">fatcat:kmcewxfyazgizdmn6fhdtibxle</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200928130216/https://arxiv.org/pdf/1805.02393v1.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/85/ac/85ac50d8438beb1b569987456108432bc201902b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3209978.3210031"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Knowledge Efficient Deep Learning for Natural Language Processing [article]

Hai Wang
<span title="2020-08-28">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In particular, we apply KRDL built on Markov logic networks to denoise weak supervision.  ...  Third, we investigate the knowledge transfer techniques in multilingual setting, where we proposed a method that can improve pre-trained multilingual BERT based on the bilingual dictionary.  ...  Distant supervision The potential function for distant supervision is similar to that for direct supervision.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.12878v1">arXiv:2008.12878v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vhcxrhydyfcsnh3iu5t3g5goky">fatcat:vhcxrhydyfcsnh3iu5t3g5goky</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200910173403/https://arxiv.org/pdf/2008.12878v1.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/2008.12878v1" 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 17,517 results