Filters








2,493 Hits in 3.3 sec

Desiderata for Vector-Space Word Representations [article]

Leon Derczynski
<span title="2016-08-06">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper details desiderata for the design of vector space representations of words.  ...  A plethora of vector-space representations for words is currently available, which is growing. These consist of fixed-length vectors containing real values, which represent a word.  ...  Conclusion This proposal identified desiderata for future vector-space representations of words.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1608.02094v1">arXiv:1608.02094v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zscml52jlfbnxp6sxijm7g2n7i">fatcat:zscml52jlfbnxp6sxijm7g2n7i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191020172245/https://arxiv.org/pdf/1608.02094v1.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/1a/47/1a4761486b1266b5d3b9145932b7fd99fa4dda6e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1608.02094v1" 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>

Neuro-Symbolic VQA: A review from the perspective of AGI desiderata [article]

Ian Berlot-Attwell
<span title="2021-04-13">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We see how well these systems meet these desiderata, and how the desiderata often pull the scientist in opposing directions.  ...  It is my hope that through this work we can temper model evaluation on benchmarks with a discussion of the properties of these systems and their potential for future extension.  ...  The execution engine's learned components are: i) networks for projecting an object's feature vector into an attribute space, and ii) a vector in said attribute space for each concept specified by the  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.06365v1">arXiv:2104.06365v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/y35ddxgaujgttbeiemcanvk2fy">fatcat:y35ddxgaujgttbeiemcanvk2fy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210415011512/https://arxiv.org/pdf/2104.06365v1.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/17/0a/170a2dbf41a5edfa07fac26e493b962ded40d4bf.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.06365v1" 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>

Multilingual Neural Machine Translation With Soft Decoupled Encoding [article]

Xinyi Wang, Hieu Pham, Philip Arthur, Graham Neubig
<span title="2019-02-09">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, there are still significant challenges in efficiently learning word representations in the face of paucity of data.  ...  SDE represents a word by its spelling through a character encoding, and its semantic meaning through a latent embedding space shared by all languages.  ...  Acknowledgements: The authors thank David Mortensen for helpful comments, and Amazon for providing GPU credits.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.03499v1">arXiv:1902.03499v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mgumlrzvizcozcb3h7hd5h5i2m">fatcat:mgumlrzvizcozcb3h7hd5h5i2m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826012541/https://arxiv.org/pdf/1902.03499v1.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/47/5d/475dc60aba62f287c34090567a21e0a67c9a7ded.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.03499v1" 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>

MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit [article]

John Palowitch, Bryan Perozzi
<span title="2020-02-25">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This bias implies an inability to control for important covariates in real-world applications, such as recommendation systems.  ...  To solve these issues, we introduce the Metadata-Orthogonal Node Embedding Training (MONET) unit, a general model for debiasing embeddings of nodes in a graph.  ...  Analysis which proves that addressing desiderata D1 alone -partitioning a metadata embedding space -still produces a biased topology embedding space, and that the MONET unit corrects this. 3.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.11793v2">arXiv:1909.11793v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nuwlhmjhxvendfbvtothgfuany">fatcat:nuwlhmjhxvendfbvtothgfuany</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321132352/https://arxiv.org/pdf/1909.11793v2.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/1909.11793v2" 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>

Detecting Asymmetric Semantic Relations in Context: A Case-Study on Hypernymy Detection

Yogarshi Vyas, Marine Carpuat
<span title="">2017</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/62lejef5rzghbafcrd6wj6pc7u" style="color: black;">Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017)</a> </i> &nbsp;
WHIC lets us analyze complementary properties of two approaches of inducing vector representations of word meaning in context.  ...  We introduce WHIC 1 , a challenging testbed for detecting hypernymy, an asymmetric relation between words.  ...  We also thank Vered Shwartz for help with data and code for CONTEXT-PPDB, and Stephen Roller for help with the H-Feature detector code.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/s17-1004">doi:10.18653/v1/s17-1004</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/starsem/VyasC17.html">dblp:conf/starsem/VyasC17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7dj7yzg2nfhdzejgjnjerm7pfe">fatcat:7dj7yzg2nfhdzejgjnjerm7pfe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200309080759/https://www.aclweb.org/anthology/S17-1004.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/b8/98/b898092842e2670ef8e38715395304a7454f0979.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/s17-1004"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Risk-Averse Trust Region Optimization for Reward-Volatility Reduction

Lorenzo Bisi, Luca Sabbioni, Edoardo Vittori, Matteo Papini, Marcello Restelli
<span title="">2020</span> <i title="International Joint Conferences on Artificial Intelligence Organization"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vfwwmrihanevtjbbkti2kc3nke" style="color: black;">Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence</a> </i> &nbsp;
Then we reduce the vocabulary by taking the union of the most probable 100 words from each topic, which results in 2,173 bag-of-word features. Flickr is an image and video sharing service.  ...  This function maps the features and the adjacency matrix of the network structure into a d-dimensional representation space to approximate the confounders.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2020/625">doi:10.24963/ijcai.2020/625</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ijcai/GuoLLCRL20.html">dblp:conf/ijcai/GuoLLCRL20</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fcb7igw2dnacbeqc7onx6phxri">fatcat:fcb7igw2dnacbeqc7onx6phxri</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201104084321/https://www.ijcai.org/Proceedings/2020/0625.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/d0/f9/d0f9e26f9462621da91c5de98d7117dc684da370.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2020/625"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

OrBEAGLE: Integrating Orthography into a Holographic Model of the Lexicon [chapter]

George Kachergis, Gregory E. Cox, Michael N. Jones
<span title="">2011</span> <i title="Springer Berlin Heidelberg"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
Using a holographic, distributed representation of visual word-forms in BEAGLE [12], a corpustrained model of semantics and word order, we show that free association data is better explained with the addition  ...  However, we find that orthography plays a minor role in accounting for cue-target strengths in free association data.  ...  However, using independent representations for each word, BEAGLE better accounts for this data, and does so primarily due to its context vectors.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-21735-7_38">doi:10.1007/978-3-642-21735-7_38</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yzhinbjjw5ha7mkobafdukgumi">fatcat:yzhinbjjw5ha7mkobafdukgumi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170922003749/http://www.kachergis.com/docs/icann11_orbeagle_freeassoc.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/6a/3d6a247dd46a41c14b02c529eb764b85d2f90869.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-21735-7_38"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Knowledge Graph Embedding in E-commerce Applications: Attentive Reasoning, Explanations, and Transferable Rules [article]

Wen Zhang, Shumin Deng, Mingyang Chen, Liang Wang, Qiang Chen, Feiyu Xiong, Xiangwen Liu, Huajun Chen
<span title="2021-12-16">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Knowledge Graph Embeddings (KGEs) embedding entities and relations of a KG into continuous vector spaces, have been proposed for these reasoning tasks and proven to be efficient and robust.  ...  We first identity three important desiderata for e-commerce KG systems: 1) attentive reasoning, reasoning over a few target relations of more concerns instead of all; 2) explanation, providing explanations  ...  and relations of a KG into continuous vector spaces, have been proposed for these reasoning tasks and proven to be efficient and robust.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.08589v1">arXiv:2112.08589v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/eafahakuyrc55no23pk2htbmz4">fatcat:eafahakuyrc55no23pk2htbmz4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211225193247/https://arxiv.org/pdf/2112.08589v1.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/57/6e/576e956f755d5c353066739bfbe82334a388ea4f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.08589v1" 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 Text Similarity with Siamese Recurrent Networks

Paul Neculoiu, Maarten Versteegh, Mihai Rotaru
<span title="">2016</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/d5l3zg54ozfqjkdv3bwmxct5zu" style="color: black;">Proceedings of the 1st Workshop on Representation Learning for NLP</a> </i> &nbsp;
This paper presents a deep architecture for learning a similarity metric on variablelength character sequences.  ...  The model learns a representation that is selective to differences in the input that reflect semantic differences (e.g., "Java developer" vs.  ...  Representation learning through neural networks has received interest since autoencoders (Hinton and Salakhutdinov, 2006) have been shown to produce features that satisfy the two desiderata of representations  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w16-1617">doi:10.18653/v1/w16-1617</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/rep4nlp/NeculoiuVR16.html">dblp:conf/rep4nlp/NeculoiuVR16</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ke4erxiytjcuznt2yvi6tmm2l4">fatcat:ke4erxiytjcuznt2yvi6tmm2l4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200508233443/https://www.aclweb.org/anthology/W16-1617.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/35/b1/35b11ac652646c70a559f7ae29295e1d5de09a80.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w16-1617"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Page 648 of Behavior Research Methods Vol. 41, Issue 3 [page]

<span title="">2009</span> <i title="Psychonomic Society, Inc."> <a target="_blank" rel="noopener" href="https://archive.org/details/pub_behavior-research-methods" style="color: black;">Behavior Research Methods</a> </i> &nbsp;
Another challenge for LSA is a lack of incrementality: an inability to update semantic representations incremen¬ tally in response to a continual accumulation of language input.  ...  If co-occurrence information plays a significant role in shaping humans’ lexical semantic representations over time, one would expect our represen¬ tations of word meaning to be shaped by co-occurrences  ... 
<span class="external-identifiers"> </span>
<a target="_blank" rel="noopener" href="https://archive.org/details/sim_behavior-research-methods_2009-08_41_3/page/648" title="read fulltext microfilm" 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> Archive [Microfilm] <div class="menu fulltext-thumbnail"> <img src="https://archive.org/serve/sim_behavior-research-methods_2009-08_41_3/__ia_thumb.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a>

Probing for Semantic Classes: Diagnosing the Meaning Content of Word Embeddings

Yadollah Yaghoobzadeh, Katharina Kann, T. J. Hazen, Eneko Agirre, Hinrich Schütze
<span title="">2019</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5n6volmnonf5tn6xputi5f2t3e" style="color: black;">Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</a> </i> &nbsp;
This is the basis for novel diagnostic tests for an embedding's content: we probe word embeddings for semantic classes and analyze the embedding space by classifying embeddings into semantic classes.  ...  Word embeddings typically represent different meanings of a word in a single conflated vector.  ...  Acknowledgments We are grateful for the support of the European Research Council (ERC #740516) and UPV/EHU (excellence research group) for this work.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/p19-1574">doi:10.18653/v1/p19-1574</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/acl/YaghoobzadehKHA19.html">dblp:conf/acl/YaghoobzadehKHA19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4v7fc7vwczeslpwr55se2wcqii">fatcat:4v7fc7vwczeslpwr55se2wcqii</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200505062824/https://www.aclweb.org/anthology/P19-1574.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/e4/0d/e40d3a5c0ff65ad66f47bfd3f2d6b999a12771d3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/p19-1574"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem [article]

Ryoma Sato
<span title="2022-05-04">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To achieve the challenging goal, we propose a decomposition of the desiderata of word embeddings into two parts, completeness and soundness, and focus on soundness in this paper.  ...  Word embeddings are one of the most fundamental technologies used in natural language processing. Existing word embeddings are high-dimensional and consume considerable computational resources.  ...  The algorithm searches for a potential vector for a tight lower bound by gradient ascent.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.01954v1">arXiv:2205.01954v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pyvvqkdhw5fxfieo6tvtfboahe">fatcat:pyvvqkdhw5fxfieo6tvtfboahe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220507075412/https://arxiv.org/pdf/2205.01954v1.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/b3/e4/b3e46af40bbcc9786bea6b3c80971ac73de238f2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.01954v1" 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>

Sketching Word Vectors Through Hashing [article]

Behrang QasemiZadeh, Laura Kallmeyer
<span title="2018-08-30">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a new fast word embedding technique using hash functions.  ...  ., preserving pairwise distances in a particular normed space), our solution exploits extremely sparse non-negative random projections.  ...  Introduction Random patterns are helpful for learning word representations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.04253v2">arXiv:1705.04253v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/oy7alfjatneqtdwcgy7fceqb5m">fatcat:oy7alfjatneqtdwcgy7fceqb5m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826173159/https://arxiv.org/pdf/1705.04253v2.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/e0/42/e042acca58b7215929451bde302be160c71778aa.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.04253v2" 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>

Named Entity Recognition using Word Embedding as a Feature

Miran Seok, Hye-Jeong Song, Chan-Young Park, Jong-Dae Kim, Yu-seop Kim
<span title="2016-02-28">2016</span> <i title="Science and Engineering Research Support Society"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/kx4szfp7xvfn7laozkx3mc4iqe" style="color: black;">International Journal of Software Engineering and Its Applications</a> </i> &nbsp;
Word embedding is helpful in many learning algorithms of NLP, indicating that words in a sentence are mapped by a real vector in a low-dimension space.  ...  This study applied word embedding to feature for named entity recognition (NER) training, and used CRF as a learning algorithm.  ...  The purpose and usefulness of Word2vec is to group the vectors of similar words together in vector-space.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.14257/ijseia.2016.10.2.08">doi:10.14257/ijseia.2016.10.2.08</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/iiw52cv5f5cv5a5nxuym6cqrdq">fatcat:iiw52cv5f5cv5a5nxuym6cqrdq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180602231633/http://www.sersc.org/journals/IJSEIA/vol10_no2_2016/8.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/e4/62/e4625b1616be1b05fa0fe3427ca4e6d3a8ba9b74.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.14257/ijseia.2016.10.2.08"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Distributed Vector Representations of Words in the Sigma Cognitive Architecture [chapter]

Volkan Ustun, Paul S. Rosenbloom, Kenji Sagae, Abram Demski
<span title="">2014</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;
Recently reported results with distributed-vector word representations in natural language processing make them appealing for incorporation into a general cognitive architecture like Sigma.  ...  This paper describes a new algorithm for learning such word representations from large, shallow information resources, and how this algorithm can be implemented via small modifications to Sigma.  ...  vector space.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-09274-4_19">doi:10.1007/978-3-319-09274-4_19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4jzccyppnragfbvl4viovvbtca">fatcat:4jzccyppnragfbvl4viovvbtca</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809073924/http://pollux.usc.edu/~rosenblo/Pubs/VectorRepresentation_AGI2014_Final.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/15/a5/15a550808eda008a069c6d5ccc08fd9ab352fbd0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-09274-4_19"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 2,493 results