Filters








3,507 Hits in 6.4 sec

Bridging the gap: Incorporating a semantic similarity measure for effectively mapping PubMed queries to documents

Sun Kim, Nicolas Fiorini, W. John Wilbur, Zhiyong Lu
<span title="">2017</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/p4kk6lusgrhyxecgig72iasi5q" style="color: black;">Journal of Biomedical Informatics</a> </i> &nbsp;
Furthermore, for a real-world dataset collected from the PubMed search logs, we combine the semantic measure with BM25 using a learning to rank method, which leads to improved ranking scores by up to 25%  ...  This process helps identify related words when no direct matches are found between a query and a document. Our method is efficient and straightforward to implement.  ...  Acknowledgments Funding This research was supported by the Intramural Research Program of the NIH, National Library of Medicine.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.jbi.2017.09.014">doi:10.1016/j.jbi.2017.09.014</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/28986328">pmid:28986328</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC5687891/">pmcid:PMC5687891</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ggwow2lctrcyxe2s742nfjaqfu">fatcat:ggwow2lctrcyxe2s742nfjaqfu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200206144052/http://europepmc.org/backend/ptpmcrender.fcgi?accid=PMC5687891&amp;blobtype=pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/68/4d/684de8e0dc81c849dbf24b0a1643e71b20e89e43.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.jbi.2017.09.014"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5687891" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

From Semantic Retrieval to Pairwise Ranking: Applying Deep Learning in E-commerce Search [article]

Rui Li, Yunjiang Jiang, Wenyun Yang, Guoyu Tang, Songlin Wang, Chaoyi Ma, Wei He, Xi Xiong, Yun Xiao, Eric Yihong Zhao
<span title="2021-03-24">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Specifically, we outline the design of a deep learning system that retrieves semantically relevant items to a query within milliseconds, and a pairwise deep re-ranking system, which learns subtle user  ...  Compared to traditional search systems, the proposed approaches are better at semantic retrieval and personalized ranking, achieving significant improvements.  ...  Table 3 shows a few sample queries to better illustrate the power of DSR at bridging semantic gaps between queries and relevant items.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.12982v1">arXiv:2103.12982v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3w4gbvnu4nestkjb2ta6g2idke">fatcat:3w4gbvnu4nestkjb2ta6g2idke</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210330052114/https://arxiv.org/pdf/2103.12982v1.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/34/c4/34c4c9f702c75b8eac24163a1c1d16bd1e9fbec6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.12982v1" 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>

Mend The Learning Approach, Not the Data: Insights for Ranking E-Commerce Products [article]

Muhammad Umer Anwaar, Dmytro Rybalko, Martin Kleinsteuber
<span title="2020-07-09">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In the literature, it is proposed to employ user feedback (such as clicks, add-to-basket (AtB) clicks and orders) to generate relevance judgments.  ...  In this paper, we advocate counterfactual risk minimization (CRM) approach which circumvents the need of relevance judgements, data aggregation and is better suited for learning from logged data, i.e.  ...  Acknowledgments We would like to thank Alan Schelten, Till Brychcy and Rudolf Sailer for insightful discussions which helped in improving the quality of this work.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.10409v8">arXiv:1907.10409v8</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ccxgf4vrarfxrnj6n3gkoqjk5i">fatcat:ccxgf4vrarfxrnj6n3gkoqjk5i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929051351/https://arxiv.org/pdf/1907.10409v8.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/c0/4d/c04d73b04b48bb02b92c1a95fb8748157bcbbb86.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.10409v8" 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>

Click-boosted graph ranking for image retrieval

Jun Wu, Yu He, Xiaohong Qin, Na Zhao, Yingpeng Sang
<span title="">2017</span> <i title="National Library of Serbia"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rhtuh2ifczhapmhplqzald63za" style="color: black;">Computer Science and Information Systems</a> </i> &nbsp;
To bridge this gap, one of the current trends is to leverage the click-through data associated with images to facilitate the graph-based image ranking.  ...  Graph ranking is one popular and successful technique for image retrieval, but its effectiveness is often limited by the well-known semantic gap.  ...  The authors would like to thank the anonymous reviewers for their constructive suggestions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2298/csis170212020j">doi:10.2298/csis170212020j</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ja4vi6bhqjg3fftoauvbrmg2ja">fatcat:ja4vi6bhqjg3fftoauvbrmg2ja</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200310151247/http://www.doiserbia.nb.rs/img/doi/1820-0214/2017/1820-02141700020W.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/73/ea/73ea88db6c62ff5d990e1bb641616455fb74e519.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2298/csis170212020j"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Click-through-based cross-view learning for image search

Yingwei Pan, Ting Yao, Tao Mei, Houqiang Li, Chong-Wah Ngo, Yong Rui
<span title="">2014</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ibcfmixrofb3piydwg5wvir3t4" style="color: black;">Proceedings of the 37th international ACM SIGIR conference on Research &amp; development in information retrieval - SIGIR &#39;14</a> </i> &nbsp;
Specifically, we propose a novel cross-view learning method for image search, named Click-through-based Crossview Learning (CCL), by jointly minimizing the distance between the mappings of query and image  ...  Existing search engines highly depend on surrounding texts for ranking images, or leverage the query-image pairs annotated by human labelers to train a series of ranking functions.  ...  Moreover, we consider exploring user click-through data, aiming to bridge the user intention gap for image search.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2600428.2609568">doi:10.1145/2600428.2609568</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/sigir/PanYMLNR14.html">dblp:conf/sigir/PanYMLNR14</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/677byckxt5gihd6z4s3epm3bva">fatcat:677byckxt5gihd6z4s3epm3bva</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170813081540/http://vireo.cs.cityu.edu.hk/papers/fp072-pan.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/f3/17f3de3c51a323e081c384504a54d33d8ceb57c7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2600428.2609568"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Modeling Relevance Ranking under the Pre-training and Fine-tuning Paradigm [article]

Lin Bo, Liang Pang, Gang Wang, Jun Xu, XiuQiang He, Ji-Rong Wen
<span title="2021-08-12">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
More importantly, the pre-trained representations, are fine-tuned together with handcrafted learning-to-rank features under a wide and deep network architecture.  ...  Specifically, to model the user's view of relevance, Pre-Rank pre-trains the initial query-document representations based on large-scale user activities data such as the click log.  ...  The neural information retrieval models can automatically learn the query-document features from the raw data, which bridge the gap between query and document vocabulary.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.05652v1">arXiv:2108.05652v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hiafpiym2jeqtdsanl52zfnrq4">fatcat:hiafpiym2jeqtdsanl52zfnrq4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210816050720/https://arxiv.org/pdf/2108.05652v1.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/ef/b1/efb10842822a80eb864ad6021b3c729179d77571.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.05652v1" 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>

Guest editorial: web multimedia semantic inference using multi-cues

Yahong Han, Yi Yang, Xiaofang Zhou
<span title="2015-06-23">2015</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/tdniohqnfvcqrpinoqffpwlpgq" style="color: black;">World wide web (Bussum)</a> </i> &nbsp;
The paper proposes to utilize active learning and domain adaptation to minimize the required amount of labeled data for model training.  ...  Feature construction or feature learning is a fundamental problem in Web multimedia semantic analysis, as it can help bridge the semantic gap between low-level features and high-level semantic.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11280-015-0360-2">doi:10.1007/s11280-015-0360-2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vc4plge5qvg7hfmza3dffmawki">fatcat:vc4plge5qvg7hfmza3dffmawki</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190503052304/https://link.springer.com/content/pdf/10.1007%2Fs11280-015-0360-2.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/62/b2/62b26a58e32ae56dcbfb723b7a5776c565ba3a99.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11280-015-0360-2"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Learning to Rewrite Queries

Yunlong He, Jiliang Tang, Hua Ouyang, Changsung Kang, Dawei Yin, Yi Chang
<span title="">2016</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/6g37zvjwwrhv3dizi6ffue642m" style="color: black;">Proceedings of the 25th ACM International on Conference on Information and Knowledge Management - CIKM &#39;16</a> </i> &nbsp;
It is widely known that there exists a semantic gap between web documents and user queries and bridging this gap is crucial to advance information retrieval systems.  ...  In this paper, we propose a learning to rewrite framework that consists of a candidate generating phase and a candidate ranking phase.  ...  A follow-up work [4] combines various click-based, topic-based and session based ranking strategies and uses supervised learning in order to maximize the semantic similarity between the query and the  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2983323.2983835">doi:10.1145/2983323.2983835</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cikm/HeTOKYC16.html">dblp:conf/cikm/HeTOKYC16</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nwvlype7yvcvhcat6guccu274i">fatcat:nwvlype7yvcvhcat6guccu274i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180722104558/http://www.yichang-cs.com/yahoo/CIKM2016_rewrite.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/95/75/9575990d9a8aad68fd5b39a6fa6dc3f95b9dfff2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2983323.2983835"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Pre-trained Language Model based Ranking in Baidu Search [article]

Lixin Zou, Shengqiang Zhang, Hengyi Cai, Dehong Ma, Suqi Cheng, Daiting Shi, Zhifan Zhu, Weiyue Su, Shuaiqiang Wang, Zhicong Cheng, Dawei Yin
<span title="2021-06-25">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Then we endow an innovative paradigm to finely exploit the large-scale noisy and biased post-click behavioral data for relevance-oriented pre-training.  ...  pre-training objectives and the ad-hoc retrieval scenarios that demand comprehensive relevance modeling is another main barrier for improving the online ranking system;(3) a real-world search engine typically  ...  High-relevance documents are usually overwhelmed for hot queries but extremely scarce for tail ones, posing challenges for the ranking model to perceive such cross-query relevance gap between documents  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.11108v3">arXiv:2105.11108v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dbvj65ugovaani4hsiwtl6bcdi">fatcat:dbvj65ugovaani4hsiwtl6bcdi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210630064956/https://arxiv.org/pdf/2105.11108v3.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/39/6b/396ba5b07b9a863fd1e595d77ed29a3e5a546197.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.11108v3" 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>

Transitive Hashing Network for Heterogeneous Multimedia Retrieval [article]

Zhangjie Cao, Mingsheng Long, Qiang Yang
<span title="2016-08-15">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We craft a hybrid deep architecture to simultaneously learn the cross-modal correlation from the auxiliary dataset, and align the dataset distributions between the auxiliary dataset and the query/database  ...  Hashing has been widely applied to large-scale multimedia retrieval due to the storage and retrieval efficiency.  ...  For text network, we employ a three-layer MLP with the numbers of hidden units set to 1000, 500, and b, respectively.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1608.04307v1">arXiv:1608.04307v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/l2xakppke5b5vgwcgs7wwliufq">fatcat:l2xakppke5b5vgwcgs7wwliufq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200825140013/https://arxiv.org/pdf/1608.04307v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/cf/5d/cf5d3cdbecd8d209854bf88b062e331448c8a0b3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1608.04307v1" 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>

An Overview of Cross-media Retrieval: Concepts, Methodologies, Benchmarks and Challenges [article]

Yuxin Peng, Xin Huang, Yunzhen Zhao
<span title="2017-07-01">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, the requirements of users are highly flexible, such as retrieving the relevant audio clips with one query of image.  ...  Cross-media retrieval is designed for the scenarios where the queries and retrieval results are of different media types.  ...  Learning to Rank Methods Learning to rank methods take the ranking information as training data, and directly optimize the ranking of retrieved results, instead of the similarities between pairwise data  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1704.02223v4">arXiv:1704.02223v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/z7ez63kodvejpfrodeszdtkccy">fatcat:z7ez63kodvejpfrodeszdtkccy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200831045243/https://arxiv.org/pdf/1704.02223v4.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/db/55/db553a82475bed5bbaab673784c3fbb773bd793b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1704.02223v4" 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>

Reusing historical interaction data for faster online learning to rank for IR

Katja Hofmann, Anne Schuth, Shimon Whiteson, Maarten de Rijke
<span title="">2013</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/puezkhxc3rggrgb456avsvxi34" style="color: black;">Proceedings of the sixth ACM international conference on Web search and data mining - WSDM &#39;13</a> </i> &nbsp;
Online learning to rank for information retrieval (IR) holds promise for allowing the development of "self-learning" search engines that can automatically adjust to their users.  ...  With the large amount of e.g., click data that can be collected in web search settings, such techniques could enable highly scalable ranking optimization.  ...  However, the recently developed Probabilistic Interleave (PI) method bridges this gap [9, 11] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2433396.2433419">doi:10.1145/2433396.2433419</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/wsdm/HofmannSWR13.html">dblp:conf/wsdm/HofmannSWR13</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5gi2fsuy35gvbjtvp5sso3p6lq">fatcat:5gi2fsuy35gvbjtvp5sso3p6lq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190426173829/https://pure.uva.nl/ws/files/1556425/166850_hofmannwsdm13.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/92/af927a1e97c0bf9179f6fdc43993c50341092715.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2433396.2433419"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Video Summarization by Learning Deep Side Semantic Embedding

Yitian Yuan, Tao Mei, Peng Cui, Wenwu Zhu
<span title="">2018</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jqw2pm7kwvhchpdxpcm5ryoic4" style="color: black;">IEEE transactions on circuits and systems for video technology (Print)</a> </i> &nbsp;
a) Video and its key frames selected by human annotator Title: How to lock your bike. The RIGHT way!  ...  Comment: Instead of using a cable with your D lock, just use a second lock, the thief will have to cut two locks instead of only one.  ...  Besides considering the ranking relationship in different video thumbnails by hinge loss in L * rel , the click numbers further quantify the semantic relevance between queries and thumbnails, and can help  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tcsvt.2017.2771247">doi:10.1109/tcsvt.2017.2771247</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/j3sae3zl7fglhlcxvmevgw2dlm">fatcat:j3sae3zl7fglhlcxvmevgw2dlm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200320184148/https://www.microsoft.com/en-us/research/wp-content/uploads/2017/11/TCSVT-01549-2017-doublecolumn.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/da/f2/daf255b25a30f053259a71a0ed84f257002a21fc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tcsvt.2017.2771247"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Unbiased Top-k Learning to Rank with Causal Likelihood Decomposition [article]

Haiyuan Zhao, Jun Xu, Xiao Zhang, Guohao Cai, Zhenhua Dong, Ji-Rong Wen
<span title="2022-04-02">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Unbiased learning to rank has been proposed to alleviate the biases in the search ranking, making it possible to train ranking models with user interaction data.  ...  Advantages of CLD include theoretical soundness and a unified framework for pointwise and pairwise unbiased top-k learning to rank.  ...  Based on Assumption (3), the relationship between click and relevance is bridged. Since the variable 𝐸 is still unobserved, Pr(𝐶 = 1|𝐸 = 1, x) cannot be identified.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.00815v1">arXiv:2204.00815v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vfdx4xdvtfet7cg2ujfrihtg7a">fatcat:vfdx4xdvtfet7cg2ujfrihtg7a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220406203005/https://arxiv.org/pdf/2204.00815v1.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/c6/1ac67065c7b271afd131245becc85ba942cc3094.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.00815v1" 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>

Towards Personalized and Semantic Retrieval: An End-to-End Solution for E-commerce Search via Embedding Learning [article]

Han Zhang, Songlin Wang, Kang Zhang, Zhiling Tang, Yunjiang Jiang, Yun Xiao, Weipeng Yan, Wen-Yun Yang
<span title="2020-06-05">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
to different users for the same search query.  ...  Based on offline evaluations and online A/B test with live traffics, we show that DPSR model outperforms existing models, and DPSR system can retrieve more personalized and semantically relevant items  ...  of the infrastructure, and Chen Zheng, Rui Li and Eric Zhao for their help at the early stage of this project.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.02282v3">arXiv:2006.02282v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ql3gtc5bwnb27p7l7vnmqgmpcm">fatcat:ql3gtc5bwnb27p7l7vnmqgmpcm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827174352/https://arxiv.org/pdf/2006.02282v3.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/f8/43/f843d0469d7558ee78f0254f21e8b16c27948fd9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.02282v3" 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 3,507 results