Internet Archive Scholar
Filters
























2,063 Hits in 5.2 sec

Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering

Yi Tay, Luu Anh Tuan, Siu Cheung Hui
<span title="">2018</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/puezkhxc3rggrgb456avsvxi34" style="color: black;">Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining - WSDM &#39;18</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.2 MB)
https://web.archive.org/web/20200929065449/https://arxiv.org/pdf/1707.07847v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1707.07847v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

<span title="2017-07-27">2017</span> <span class="release-stage" >pre-print</span> <span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1707.07847v2">arXiv:1707.07847v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/iei5q6i665cdtlyehbro5dxary">fatcat:iei5q6i665cdtlyehbro5dxary</a> </span>

Other Versions

<span title="2017-07-25">2017</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1707.07847v1">arXiv:1707.07847v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jchysshc25acfjk4xgt62nw2gy">fatcat:jchysshc25acfjk4xgt62nw2gy</a> </span>
<span title="2017-11-23">2017</span> <span class="release-stage">accepted</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1707.07847v3">arXiv:1707.07847v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/f6nfijpttfeyzje5shllopborm">fatcat:f6nfijpttfeyzje5shllopborm</a> </span>
We propose a simple but novel deep learning architecture for fast and efficient question-answer ranking and retrieval.  ...  This empowers our model with a self-organizing ability and enables automatic discovery of latent hierarchies while learning embeddings of questions and answers.  ...  Hyperbolic Representations of QA Pairs Neural ranking models are mainly characterized by the interaction function between question and answer representations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3159652.3159664">doi:10.1145/3159652.3159664</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/wsdm/TayTH18.html">dblp:conf/wsdm/TayTH18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ebv4xtt4jzgdnmpbld4i535xpi">fatcat:ebv4xtt4jzgdnmpbld4i535xpi</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929065449/https://arxiv.org/pdf/1707.07847v2.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/f5/93/f593cdc9fc6931b699a0adc951f6596de9f296a5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3159652.3159664"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>
Citation

Yi Tay, Luu Anh Tuan, Siu Cheung Hui. "Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering." Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining - WSDM '18 (2018) 583-591

HyperText: Endowing FastText with Hyperbolic Geometry [article]

Yudong Zhu, Di Zhou, Jinghui Xiao, Xin Jiang, Xiao Chen, Qun Liu
<span title="2021-12-17">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (587.7 kB)
https://web.archive.org/web/20211228234459/https://arxiv.org/pdf/2010.16143v3.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2010.16143v3.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2021-05-17">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.16143v2">arXiv:2010.16143v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3zc5qaibdbg7zbbvj7f3awjhza">fatcat:3zc5qaibdbg7zbbvj7f3awjhza</a> </span>
<span title="2020-10-30">2020</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.16143v1">arXiv:2010.16143v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3kddxkjd4nazba46slmkhrbrdu">fatcat:3kddxkjd4nazba46slmkhrbrdu</a> </span>
Considering that hyperbolic space is naturally suitable for modeling tree-like hierarchical data, we propose a new model named HyperText for efficient text classification by endowing FastText with hyperbolic  ...  FastText, as the state-of-the-art text classifier based on shallow neural network in Euclidean space, may not model such hierarchies precisely with limited representation capacity.  ...  There are some applications based on hyperbolic geometry, such as question answering system (Tay et al., 2018 ), recommendation system (Chamberlain et al., 2019) and image embedding (Khrulkov et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.16143v3">arXiv:2010.16143v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lr6q7r2yq5eghnvlwtxvihag6u">fatcat:lr6q7r2yq5eghnvlwtxvihag6u</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211228234459/https://arxiv.org/pdf/2010.16143v3.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/ae/afaed4a9296df7e22476ccce545b647a40b73262.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.16143v3" 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>
Citation

Yudong Zhu, Di Zhou, Jinghui Xiao, Xin Jiang, Xiao Chen, Qun Liu. "HyperText: Endowing FastText with Hyperbolic Geometry." arXiv (2021)

Understanding in Artificial Intelligence [article]

Stefan Maetschke and David Martinez Iraola and Pieter Barnard and Elaheh ShafieiBavani and Peter Zhong and Ying Xu and Antonio Jimeno Yepes
<span title="2021-01-17">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (490.3 kB)
https://web.archive.org/web/20210120105313/https://arxiv.org/pdf/2101.06573v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2101.06573v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

To answer these questions, we have analysed existing benchmarks and their understanding capabilities, defined by a set of understanding capabilities, and current research streams.  ...  The progress of these AI methods is measured using benchmarks designed to solve challenging tasks, such as visual question answering.  ...  A required capability for understanding is to learn from example data a (partially) symbolic knowledge representation that allows reasoning and question answering.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.06573v1">arXiv:2101.06573v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nlp6h5toh5f6lpwjsafn6gulbq">fatcat:nlp6h5toh5f6lpwjsafn6gulbq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210120105313/https://arxiv.org/pdf/2101.06573v1.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/a7/ef/a7ef6b6e94090993d08f824f3254e5420a71b3ed.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.06573v1" 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>
Citation

Stefan Maetschke and David Martinez Iraola and Pieter Barnard and Elaheh ShafieiBavani and Peter Zhong and Ying Xu and Antonio Jimeno Yepes. "Understanding in Artificial Intelligence." arXiv (2021)

Hyperbolic Deep Neural Networks: A Survey [article]

Wei Peng, Tuomas Varanka, Abdelrahman Mostafa, Henglin Shi, Guoying Zhao
<span title="2021-02-17">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.0 MB)
https://web.archive.org/web/20210221070435/https://arxiv.org/pdf/2101.04562v3.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2101.04562v3.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2021-01-14">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.04562v2">arXiv:2101.04562v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kcbvum3yvnginda6l3jlzfxodi">fatcat:kcbvum3yvnginda6l3jlzfxodi</a> </span>
<span title="2021-01-12">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.04562v1">arXiv:2101.04562v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gaevqiczkzfp7b4lrpn6pkwoze">fatcat:gaevqiczkzfp7b4lrpn6pkwoze</a> </span>
Recently, there has been a rising surge of momentum for deep representation learning in hyperbolic spaces due to theirhigh capacity of modeling data like knowledge graphs or synonym hierarchies, possessing  ...  We refer to the model as hyperbolic deep neural network in this paper.  ...  This work is supported by the Academy of Finland for ICT 2023 project (grant 328115) and project MiGA (grant 316765) and Infotech Oulu.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.04562v3">arXiv:2101.04562v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yqj4zohrqjbplpsdy5f5uglnbu">fatcat:yqj4zohrqjbplpsdy5f5uglnbu</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span> <span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210221070435/https://arxiv.org/pdf/2101.04562v3.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/1f/f8/1ff80e03af01e5fcadeee7ce6970d7620353f171.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.04562v3" 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>
Citation

Wei Peng, Tuomas Varanka, Abdelrahman Mostafa, Henglin Shi, Guoying Zhao. "Hyperbolic Deep Neural Networks: A Survey." arXiv (2021)

Learning to update Auto-associative Memory in Recurrent Neural Networks for Improving Sequence Memorization [article]

Wei Zhang, Bowen Zhou
<span title="2017-10-03">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (505.8 kB)
https://web.archive.org/web/20200910073025/https://arxiv.org/pdf/1709.06493v3.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1709.06493v3.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2017-09-29">2017</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1709.06493v2">arXiv:1709.06493v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hl7qxcfkvrfuvaaia74xmsbmti">fatcat:hl7qxcfkvrfuvaaia74xmsbmti</a> </span>
<span title="2017-09-19">2017</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1709.06493v1">arXiv:1709.06493v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ee3njf3wyfcnhjddvcg7wkxtqm">fatcat:ee3njf3wyfcnhjddvcg7wkxtqm</a> </span>
Learning to remember long sequences remains a challenging task for recurrent neural networks.  ...  Register memory and attention mechanisms were both proposed to resolve the issue with either high computational cost to retain memory differentiability, or by discounting the RNN representation learning  ...  Acknowledgements We thank Gerry Tesauro, Kazi Hassan, Matt Reimer, Mo Yu, Tim Klinger, Yang Yu for the help to this paper.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1709.06493v3">arXiv:1709.06493v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m27gm4w6mbghxk4kqrd5qjqkyi">fatcat:m27gm4w6mbghxk4kqrd5qjqkyi</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200910073025/https://arxiv.org/pdf/1709.06493v3.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/71/b7/71b77ce0c0b36ae64c82ea0ba901db2e997fbb3c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1709.06493v3" 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>
Citation

Wei Zhang, Bowen Zhou. "Learning to update Auto-associative Memory in Recurrent Neural Networks for Improving Sequence Memorization." arXiv (2017)

Practice in Synonym Extraction at Large Scale [article]

Liangliang Cao, Chang Wang
<span title="2015-06-01">2015</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (400.3 kB)
https://web.archive.org/web/20200901202730/https://arxiv.org/pdf/1412.2197v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1412.2197v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

<span title="2014-12-18">2014</span> <span class="release-stage" >pre-print</span> <span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1412.2197v2">arXiv:1412.2197v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/e4pr2ny2svgyrhevnxeoqxmzae">fatcat:e4pr2ny2svgyrhevnxeoqxmzae</a> </span>

Other Versions

<span title="2014-12-06">2014</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1412.2197v1">arXiv:1412.2197v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ebjri7yi6fbkrhag2iztrsdqky">fatcat:ebjri7yi6fbkrhag2iztrsdqky</a> </span>
Synonym extraction is an important task in natural language processing and often used as a submodule in query expansion, question answering and other applications.  ...  We compare several different approaches based on SVMs and neural networks, and find out a novel feature learning based neural network outperforms the methods with hand-assigned features.  ...  Moreover, clinical text may change over time, and it is important to recognize synonyms from historical records. • Question Answering: Question Answering (QA) aims to automatically answer questions posed  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1412.2197v3">arXiv:1412.2197v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6dtwvekn6vd2hbtevfdnuo4qhu">fatcat:6dtwvekn6vd2hbtevfdnuo4qhu</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200901202730/https://arxiv.org/pdf/1412.2197v2.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/ad/86/ad866a285d4e4bc199e0a23d68f2f571b3bb5421.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1412.2197v3" 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>
Citation

Liangliang Cao, Chang Wang. "Practice in Synonym Extraction at Large Scale." arXiv (2015)

An Approach to Detect Sentence Level Sarcasm Using Deep Learning Techniques

Amruta K. Chimote
<span title="2020-12-25">2020</span> <i title="Society for Science and Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/lnzsyf5hs5hltpkbpddbyynpxe" style="color: black;">Bioscience Biotechnology Research Communications</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (530.1 kB)
https://web.archive.org/web/20210123024422/https://bbrc.in/wp-content/uploads/2021/01/13_14-SPL-Galley-proof-030.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://bbrc.in/wp-content/uploads/2021/01/13_14-SPL-Galley-proof-030.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Use of conversation Agent gives real time experience to user/customer to get answers very fast.  ...  This paper gives a combined approach by extracting pragmatic features like emoticons, use of hyperbole, punctuations and special words used in sentence to detect sentence level sarcasm using deep learning  ...  machine learning and deep learning techniques are more efficient. rule based approach depends on occurrences.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21786/bbrc/13.14/30">doi:10.21786/bbrc/13.14/30</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6caaenvcfzhunaf7yzwqcqccja">fatcat:6caaenvcfzhunaf7yzwqcqccja</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210123024422/https://bbrc.in/wp-content/uploads/2021/01/13_14-SPL-Galley-proof-030.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/56/32/56325f86ef43b56fcd4d65d6dd69d242b18abc53.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21786/bbrc/13.14/30"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
Citation

Amruta K. Chimote. "An Approach to Detect Sentence Level Sarcasm Using Deep Learning Techniques." Bioscience Biotechnology Research Communications 13.14 (2020) 125-128

Convolutional Neural Networks vs. Convolution Kernels: Feature Engineering for Answer Sentence Reranking

Kateryna Tymoshenko, Daniele Bonadiman, Alessandro Moschitti
<span title="">2016</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/d5ex6ucxtrfz3clshlkh3f6w2q" style="color: black;">Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (596.5 kB)
https://web.archive.org/web/20210428032654/https://iris.unitn.it/retrieve/handle/11572/169987/123532/Convolutional%20Neural%20Networks.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://iris.unitn.it/retrieve/handle/11572/169987/123532/Convolutional%20Neural%20Networks.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

In this paper, we study, compare and combine two state-of-the-art approaches to automatic feature engineering: Convolution Tree Kernels (CTKs) and Convolutional Neural Networks (CNNs) for learning to rank  ...  When dealing with QA, the key aspect is to encode relational information between the constituents of question and answer in learning algorithms.  ...  Many thanks to the anonymous reviewers for their valuable suggestions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/n16-1152">doi:10.18653/v1/n16-1152</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/naacl/TymoshenkoBM16.html">dblp:conf/naacl/TymoshenkoBM16</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/waljh76i3vgpxgcunyjmkao7fy">fatcat:waljh76i3vgpxgcunyjmkao7fy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210428032654/https://iris.unitn.it/retrieve/handle/11572/169987/123532/Convolutional%20Neural%20Networks.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/75/57/75572fb6acc1953f7cc945d722af4e8e4762e20c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/n16-1152"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
Citation

Kateryna Tymoshenko, Daniele Bonadiman, Alessandro Moschitti. "Convolutional Neural Networks vs. Convolution Kernels: Feature Engineering for Answer Sentence Reranking." Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2016) 1268-1278

Visual Question Answering as a Meta Learning Task [chapter]

Damien Teney, Anton van den Hengel
<span title="">2018</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;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (864.5 kB)
https://web.archive.org/web/20180922013800/http://openaccess.thecvf.com:80/content_ECCV_2018/papers/Damien_Teney_Visual_Question_Answering_ECCV_2018_paper.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit <a rel="external noopener" href="http://openaccess.thecvf.com:80/content_ECCV_2018/papers/Damien_Teney_Visual_Question_Answering_ECCV_2018_paper.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

We propose instead to approach VQA as a meta learning task, thus separating the question answering method from the information required.  ...  In comparison to the existing state of the art, the proposed method produces qualitatively distinct results with higher recall of rare answers, and a better sample efficiency that allows training with  ...  We proposed a deep learning model that takes advantage of the meta learning scenario, and demonstrated a range of benefits: improved recall of rare answers, better sample efficiency, and a unique capability  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01267-0_14">doi:10.1007/978-3-030-01267-0_14</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bo4dcgqvzfc7xkv2wquv57q3em">fatcat:bo4dcgqvzfc7xkv2wquv57q3em</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180922013800/http://openaccess.thecvf.com:80/content_ECCV_2018/papers/Damien_Teney_Visual_Question_Answering_ECCV_2018_paper.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/93/43/934350482f3f19d431f35960a14dc249bd069303.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01267-0_14"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>
Citation

Damien Teney, Anton van den Hengel. "Visual Question Answering as a Meta Learning Task." Lecture Notes in Computer Science (2018) 229-245

Extracting Event Temporal Relations via Hyperbolic Geometry [article]

Xingwei Tan, Gabriele Pergola, Yulan He
<span title="2021-09-12">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.9 MB)
https://web.archive.org/web/20210919054846/https://arxiv.org/pdf/2109.05527v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2109.05527v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

In the second one, we devise an end-to-end architecture composed of hyperbolic neural units tailored for the temporal relation extraction task.  ...  We introduce two approaches to encode events and their temporal relations in hyperbolic spaces.  ...  YH is supported by a Turing AI Fellowship funded by the UK Research and Innovation (grant no. EP/V020579/1).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.05527v1">arXiv:2109.05527v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kddtvp4agzfq5h5bv4javqdzm4">fatcat:kddtvp4agzfq5h5bv4javqdzm4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210919054846/https://arxiv.org/pdf/2109.05527v1.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/8c/4e/8c4e9f559367fbbf731e97f66cad5559373863b0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.05527v1" 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>
Citation

Xingwei Tan, Gabriele Pergola, Yulan He. "Extracting Event Temporal Relations via Hyperbolic Geometry." arXiv (2021)

Ranking Kernels for Structures and Embeddings: A Hybrid Preference and Classification Model

Kateryna Tymoshenko, Daniele Bonadiman, Alessandro Moschitti
<span title="">2017</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/u3ideoxy4fghvbsstiknuweth4" style="color: black;">Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (243.7 kB)
https://web.archive.org/web/20200309095641/https://www.aclweb.org/anthology/D17-1093.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://www.aclweb.org/anthology/D17-1093.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

We show that our approach produces better results on two well-known and rather different datasets: WikiQA for answer sentence selection and SemEval cQA for comment selection in Community Question Answering  ...  Recent work has shown that Tree Kernels (TKs) and Convolutional Neural Networks (CNNs) obtain the state of the art in answer sentence reranking.  ...  We would like to thank Raniero Romagnoli for helping us to review an early draft of this paper. Many thanks to the anonymous reviewers for their professional work and valuable suggestions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/d17-1093">doi:10.18653/v1/d17-1093</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/emnlp/TymoshenkoBM17.html">dblp:conf/emnlp/TymoshenkoBM17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/aj3vtiqiurei3kcnfviuxw7hay">fatcat:aj3vtiqiurei3kcnfviuxw7hay</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200309095641/https://www.aclweb.org/anthology/D17-1093.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/f4/2ff4e186b9d419fd99bba5955c808dc72d9b1ba5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/d17-1093"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
Citation

Kateryna Tymoshenko, Daniele Bonadiman, Alessandro Moschitti. "Ranking Kernels for Structures and Embeddings: A Hybrid Preference and Classification Model." Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (2017) 897-902

An Attentive Survey of Attention Models [article]

Sneha Chaudhari, Varun Mithal, Gungor Polatkan, Rohan Ramanath
<span title="2021-07-12">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (9.3 MB)
https://web.archive.org/web/20210719211047/https://arxiv.org/pdf/1904.02874v3.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1904.02874v3.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2019-04-05">2019</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.02874v1">arXiv:1904.02874v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kbxlqrnmqrfcbat5h6u2vkbfwm">fatcat:kbxlqrnmqrfcbat5h6u2vkbfwm</a> </span>
<span title="2020-12-15">2020</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.02874v2">arXiv:1904.02874v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kqlaqrxrzrgele4xtfzfobc7uu">fatcat:kqlaqrxrzrgele4xtfzfobc7uu</a> </span>
We hope this survey will provide a succinct introduction to attention models and guide practitioners while developing approaches for their applications.  ...  We review salient neural architectures in which attention has been incorporated, and discuss applications in which modeling attention has shown a significant impact.  ...  [Lu et al. 2016 ] used a coattention model for visual question answering.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.02874v3">arXiv:1904.02874v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fyqgqn7sxzdy3efib3rrqexs74">fatcat:fyqgqn7sxzdy3efib3rrqexs74</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span> <span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210719211047/https://arxiv.org/pdf/1904.02874v3.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/6e/d7/6ed7d4cd503e7c82372b8a6bace11b3b58af98d5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.02874v3" 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>
Citation

Sneha Chaudhari, Varun Mithal, Gungor Polatkan, Rohan Ramanath. "An Attentive Survey of Attention Models." arXiv (2021)

Visual Question Answering as a Meta Learning Task [article]

Damien Teney, Anton van den Hengel
<span title="2017-11-22">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.1 MB)
https://web.archive.org/web/20200922143615/https://arxiv.org/pdf/1711.08105v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1711.08105v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

We propose instead to approach VQA as a meta learning task, thus separating the question answering method from the information required.  ...  In comparison to the existing state of the art, the proposed method produces qualitatively distinct results with higher recall of rare answers, and a better sample efficiency that allows training with  ...  We proposed a deep learning model that takes advantage of the meta learning scenario, and demonstrated a range of benefits: improved recall of rare answers, better sample efficiency, and a unique capability  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1711.08105v1">arXiv:1711.08105v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uhzfflwro5dshmpa22w74kknaq">fatcat:uhzfflwro5dshmpa22w74kknaq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200922143615/https://arxiv.org/pdf/1711.08105v1.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/ec/d1/ecd1f2c6cac41c887f4314cb25974c2082944068.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1711.08105v1" 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>
Citation

Damien Teney, Anton van den Hengel. "Visual Question Answering as a Meta Learning Task." arXiv (2017)

Learning to Reason with Third-Order Tensor Products [article]

Imanol Schlag, Jürgen Schmidhuber
<span title="2019-01-08">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.9 MB)
https://web.archive.org/web/20200826171858/https://arxiv.org/pdf/1811.12143v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1811.12143v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2018-11-29">2018</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.12143v1">arXiv:1811.12143v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/i3hr3fw3rzfh3mvpvpqiw3lkve">fatcat:i3hr3fw3rzfh3mvpvpqiw3lkve</a> </span>
We combine Recurrent Neural Networks with Tensor Product Representations to learn combinatorial representations of sequential data.  ...  This improves symbolic interpretation and systematic generalisation.  ...  Acknowledgments We thank Paulo Rauber, Klaus Greff, and Filipe Mutz for helpful comments and helping hands.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.12143v2">arXiv:1811.12143v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/f77xc6qvqze3zn2dalp45ta7oq">fatcat:f77xc6qvqze3zn2dalp45ta7oq</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span> <span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826171858/https://arxiv.org/pdf/1811.12143v2.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/13/a2/13a225306bbe49e3015b765770bce194d5b2ada5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.12143v2" 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>
Citation

Imanol Schlag, Jürgen Schmidhuber. "Learning to Reason with Third-Order Tensor Products." arXiv (2019)

Deep Learning Based Text Classification: A Comprehensive Review [article]

Shervin Minaee, Nal Kalchbrenner, Erik Cambria, Narjes Nikzad, Meysam Chenaghlu, Jianfeng Gao
<span title="2021-01-04">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

Web Archive Capture PDF (3.6 MB)
https://web.archive.org/web/20200415221309/https://arxiv.org/pdf/2004.03705v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2004.03705v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

<span title="2020-04-06">2020</span> <span class="release-stage" >pre-print</span> <span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.03705v1">arXiv:2004.03705v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2jhz46jj6zbctidnhtsfv5fioq">fatcat:2jhz46jj6zbctidnhtsfv5fioq</a> </span>

Other Versions

<span title="2020-11-17">2020</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.03705v2">arXiv:2004.03705v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4tgtfhijyjctxoe3wjqnjicexu">fatcat:4tgtfhijyjctxoe3wjqnjicexu</a> </span>
Deep learning based models have surpassed classical machine learning based approaches in various text classification tasks, including sentiment analysis, news categorization, question answering, and natural  ...  In this paper, we provide a comprehensive review of more than 150 deep learning based models for text classification developed in recent years, and discuss their technical contributions, similarities,  ...  ACKNOWLEDGMENTS The authors would like to thank Richard Socher, Kristina Toutanova, and Brooke Cowan for reviewing this work, and providing very insightful comments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.03705v3">arXiv:2004.03705v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/al5hstylsbhfpldvokuvlpomam">fatcat:al5hstylsbhfpldvokuvlpomam</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200415221309/https://arxiv.org/pdf/2004.03705v1.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/2004.03705v3" 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>
Citation

Shervin Minaee, Nal Kalchbrenner, Erik Cambria, Narjes Nikzad, Meysam Chenaghlu, Jianfeng Gao. "Deep Learning Based Text Classification: A Comprehensive Review." arXiv (2021)

&laquo; Previous Showing results 1 &mdash; 15 out of 2,063 results