Filters








39 Hits in 8.0 sec

LSTM vs. BM25 for Open-domain QA

Sosuke Kato, Riku Togashi, Hideyuki Maeda, Sumio Fujita, Tetsuya Sakai
<span title="">2017</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ibcfmixrofb3piydwg5wvir3t4" style="color: black;">Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR &#39;17</a> </i> &nbsp;
In this demonstration, we provide the attendees of SIGIR 2017 an opportunity to experience a live comparison of two open-domain QA systems, one based on a long short-term memory (LSTM) architecture with  ...  Answers) questions and over 27.4 million answers for training, and the other based on BM25. Both systems use the same Q&A knowledge source for answer retrieval.  ...  How will LSTM and BM25 compare in terms of effectiveness and efficiency?  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3077136.3084147">doi:10.1145/3077136.3084147</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/sigir/KatoTMFS17.html">dblp:conf/sigir/KatoTMFS17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/g5t3wx4y2rfqrbm7osvg2qhhgm">fatcat:g5t3wx4y2rfqrbm7osvg2qhhgm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190218135804/https://static.aminer.org/pdf/20170130/pdfs/sigir/tz0kbssyqja8o7rglyvnp5fn4cwd6pej.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/45/26/4526452fe7f8b2b3d1d819e17398b459a89da224.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3077136.3084147"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Pruning the Index Contents for Memory Efficient Open-Domain QA [article]

Martin Fajcik, Martin Docekal, Karel Ondrej, Pavel Smrz
<span title="2021-04-09">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This work presents a simple approach for pruning the contents of a massive index such that the open-domain QA system altogether with index, OS, and library components fits into 6GiB docker image while  ...  retaining only 8% of original index contents and losing only 3% EM accuracy.  ...  The computation used the infrastructure supported by the Czech Ministry of Education, Youth and Sports from the Large Infrastructures for Research, Experimental Development and Innovations project "IT4Innovations  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.10697v2">arXiv:2102.10697v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rbkfghoainb37asci2etnhyzse">fatcat:rbkfghoainb37asci2etnhyzse</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210414051034/https://arxiv.org/pdf/2102.10697v2.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/34/87/3487bc2e520245aaf3c735f553cafa62d3ca6851.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.10697v2" 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>

Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting [article]

Sheng-Chieh Lin, Jheng-Hong Yang, Rodrigo Nogueira, Ming-Feng Tsai, Chuan-Ju Wang, Jimmy Lin
<span title="2021-03-11">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Moreover, to leverage the strengths of both CQR methods, we propose combining their output with reciprocal rank fusion, yielding state-of-the-art retrieval effectiveness, 30% improvement in terms of NDCG  ...  Detailed analyses of the two CQR methods are provided quantitatively and qualitatively, explaining their advantages, disadvantages, and distinct behaviors.  ...  Most QA research [26, 40, 50, 56, 59] , including conversational QA studies [10, 41] , focuses on a restricted version of the open-domain QA problem posed in [8, 18, 20] : returning answers from a finite  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.02230v2">arXiv:2005.02230v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/prof2i6vrnfwnbjk3aa6qickra">fatcat:prof2i6vrnfwnbjk3aa6qickra</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200528040752/https://arxiv.org/pdf/2005.02230v1.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/2005.02230v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Deep Look into Neural Ranking Models for Information Retrieval [article]

Jiafeng Guo, Yixing Fan, Liang Pang, Liu Yang, Qingyao Ai, Hamed Zamani, Chen Wu, W. Bruce Croft, Xueqi Cheng
<span title="2019-06-27">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The power of neural ranking models lies in the ability to learn from the raw text inputs for the ranking problem to avoid many limitations of hand-crafted features.  ...  Ranking models lie at the heart of research on information retrieval (IR).  ...  Empirical Comparison on QA In order to understand the performance of different neural ranking models reviewed in this paper for the QA task, we survey the previously published results on three QA data  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1903.06902v3">arXiv:1903.06902v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/j22ic7foibcurp45b4amdiwfhu">fatcat:j22ic7foibcurp45b4amdiwfhu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200906184217/https://arxiv.org/pdf/1903.06902v1.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/53/4e/534e33f6f2de91865277443ac2f22d951d872ad6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1903.06902v3" 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>

Open-Domain Question Answering Goes Conversational via Question Rewriting [article]

Raviteja Anantha, Svitlana Vakulenko, Zhucheng Tu, Shayne Longpre, Stephen Pulman, Srinivas Chappidi
<span title="2021-04-14">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We report the effectiveness of a strong baseline approach that combines the state-of-the-art model for question rewriting, and competitive models for open-domain QA.  ...  Our results set the first baseline for the QReCC dataset with F1 of 19.10, compared to the human upper bound of 75.45, indicating the difficulty of the setup and a large room for improvement.  ...  The standard approach to end-to-end open-domain QA is (1) use an efficient filtering approach to reduce the number of candidate passages to the top-k of the most relevant ones (usually BM25 based on the  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.04898v3">arXiv:2010.04898v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/r357s67rcrcjjkb7efe3cji3mu">fatcat:r357s67rcrcjjkb7efe3cji3mu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210419235009/https://arxiv.org/pdf/2010.04898v2.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/d6/a6/d6a6b5f99b486148a663de94df16279d15beb5f3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.04898v3" 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>

Improving Biomedical Information Retrieval with Neural Retrievers [article]

Man Luo, Arindam Mitra, Tejas Gokhale, Chitta Baral
<span title="2022-01-19">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Although neural retrievers have surpassed traditional IR approaches such as TF-IDF and BM25 in standard open-domain question answering tasks, they are still found lacking in the biomedical domain.  ...  We show that BM25 and our method can complement each other, and a simple hybrid model leads to further gains in the large corpus setting.  ...  Any opinions, findings, or recommendations expressed in this material are those of the authors and do not necessarily reflect the views of the supporting agencies.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.07745v1">arXiv:2201.07745v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/u4x346mylvhjbcuvezdgkitkky">fatcat:u4x346mylvhjbcuvezdgkitkky</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220122093040/https://arxiv.org/pdf/2201.07745v1.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/15/03/15031e6a94f9d6d19f74740c224a5523ec64d975.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.07745v1" 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 More Robust Natural Language Understanding [article]

Xinliang Frederick Zhang
<span title="2022-02-27">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
On the contrary, most of existing NLU systems fail to achieve desirable performance on out-of-domain data or struggle on handling challenging items (e.g., inherently ambiguous items, adversarial items)  ...  doesn't know a priori of users' inputs.  ...  Out-of-Domain Test Set Unlike open domain, there are very few publicly available QA datasets in the clinical domain.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.02992v2">arXiv:2112.02992v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5pbszflxkbdibanpcvaqfzv67a">fatcat:5pbszflxkbdibanpcvaqfzv67a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211208132950/https://arxiv.org/pdf/2112.02992v1.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/c5/a6/c5a6ff64f491f56ce6cc1a399780e2d7153e6f93.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.02992v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Comparison of Supervised Learning to Match Methods for Product Search [article]

Fatemeh Sarvi, Nikos Voskarides, Lois Mooiman, Sebastian Schelter, Maarten de Rijke
<span title="2020-07-20">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We compare both effectiveness and efficiency of these methods in a product search setting and analyze their performance on two product search datasets, with 50,000 queries each.  ...  This comparison is conducted towards a better understanding of trade-offs in choosing a preferred model for this task.  ...  We would also like to thank the reviewers for their thoughtful comments and efforts towards improving our work.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.10296v1">arXiv:2007.10296v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/v7mdrxipcvfszarvwfhhedhn3a">fatcat:v7mdrxipcvfszarvwfhhedhn3a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200828120327/https://arxiv.org/pdf/2007.10296v1.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/14/01/14016ad3f041cf60a5b16cf9a179c1ca491afd88.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.10296v1" 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>

Neural Information Retrieval: A Literature Review [article]

Ye Zhang, Md Mustafizur Rahman, Alex Braylan, Brandon Dang, Heng-Lu Chang, Henna Kim, Quinten McNamara, Aaron Angert, Edward Banner, Vivek Khetan, Tyler McDonnell, An Thanh Nguyen (+3 others)
<span title="2017-03-03">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
While deep NNs have yet to achieve the same level of success in IR as seen in other areas, the recent surge of interest and work in NNs for IR suggest that this state of affairs may be quickly changing  ...  A recent "third wave" of Neural Network (NN) approaches now delivers state-of-the-art performance in many machine learning tasks, spanning speech recognition, computer vision, and natural language processing  ...  Additional Authors The following additional students at the University of Texas at Austin contributed indirectly to the writing of this literature review: Manu Agarwal, Edward Babbe, Anuparna Banerjee,  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1611.06792v3">arXiv:1611.06792v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/i2eqfj5l25epjcytgvifta4y4i">fatcat:i2eqfj5l25epjcytgvifta4y4i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200824161408/https://arxiv.org/pdf/1611.06792v3.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/a1/42/a14257975c4bf728bc99fefab8818211fa89ca71.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1611.06792v3" 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>

R2-D2: A Modular Baseline for Open-Domain Question Answering [article]

Martin Fajcik, Martin Docekal, Karel Ondrej, Pavel Smrz
<span title="2021-09-08">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We demonstrate its strength across three open-domain QA datasets: NaturalQuestions, TriviaQA and EfficientQA, surpassing state-of-the-art on the first two.  ...  This work presents a novel four-stage open-domain QA pipeline R2-D2 (Rank twice, reaD twice).  ...  The computation used the infrastructure supported by the Ministry of Education, Youth and Sports of the Czech Republic through the e-INFRA CZ (ID:90140).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.03502v1">arXiv:2109.03502v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ftrfppesmvfo3ku5zuszbbncf4">fatcat:ftrfppesmvfo3ku5zuszbbncf4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210915025631/https://arxiv.org/pdf/2109.03502v1.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/d8/2c/d82c779e316aebf0a6b08904dff9cd26ba57219b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.03502v1" 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>

Neural Ranking Models for Document Retrieval [article]

Mohamed Trabelsi, Zhiyu Chen, Brian D. Davison, Jeff Heflin
<span title="2021-02-23">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
A variety of deep learning models have been proposed, and each model presents a set of neural network components to extract features that are used for ranking.  ...  Ranking models are the main components of information retrieval systems. Several approaches to ranking are based on traditional machine learning algorithms using a set of hand-crafted features.  ...  Effective user interaction for high-recall retrieval: Less is more. In Proceedings of the 27th ACM International Conference on .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.11903v1">arXiv:2102.11903v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zc2otf456rc2hj6b6wpcaaslsa">fatcat:zc2otf456rc2hj6b6wpcaaslsa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211113132836/https://arxiv.org/ftp/arxiv/papers/2102/2102.11903.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/e9/aa/e9aa703d07e945d3e59b86786bd01f721e54caa8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.11903v1" 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>

MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale [article]

Andreas Rücklé, Jonas Pfeiffer, Iryna Gurevych
<span title="2020-10-02">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We also demonstrate that considering a broad selection of source domains is crucial for obtaining the best zero-shot transfer performances, which contrasts the standard procedure that merely relies on  ...  We study the zero-shot transfer capabilities of text matching models on a massive scale, by self-supervised training on 140 source domains from community question answering forums in English.  ...  Acknowledgements This work was supported by the German Federal Ministry of Education and Research (BMBF) and the Hessen State Ministry for Higher Education, Research and the Arts within their joint support  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.00980v1">arXiv:2010.00980v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lggd7px4j5cotj4nkfx4a6raqi">fatcat:lggd7px4j5cotj4nkfx4a6raqi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201006002937/https://arxiv.org/pdf/2010.00980v1.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/2010.00980v1" 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>

Pretrained Transformers for Text Ranking: BERT and Beyond [article]

Jimmy Lin, Rodrigo Nogueira, Andrew Yates
<span title="2021-08-19">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this survey, we provide a synthesis of existing work as a single point of entry for practitioners who wish to gain a better understanding of how to apply transformers to text ranking problems and researchers  ...  (i.e., result quality) and efficiency (e.g., query latency, model and index size).  ...  We'd like to thank the following people for comments on earlier drafts of this work: Chris Buckley, Danqi Chen, Maura Grossman, Sebastian Hofstätter, Kenton Lee, Sheng-Chieh Lin, Xueguang Ma, Bhaskar  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.06467v3">arXiv:2010.06467v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/obla6reejzemvlqhvgvj77fgoy">fatcat:obla6reejzemvlqhvgvj77fgoy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210826080042/https://arxiv.org/pdf/2010.06467v3.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/2c/95/2c953a3c378b40dadf2e3fb486713c8608b8e282.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.06467v3" 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>

Pretrained Transformers for Text Ranking: BERT and Beyond

Andrew Yates, Rodrigo Nogueira, Jimmy Lin
<span title="2021-03-08">2021</span> <i title="ACM"> Proceedings of the 14th ACM International Conference on Web Search and Data Mining </i> &nbsp;
The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in response to a query for a particular task.  ...  In the context of text ranking, these models produce high quality results across many domains, tasks, and settings.  ...  We'd like to thank the following people for comments on earlier drafts of this work: Maura Grossman, Sebastian Hofstätter, Xueguang Ma, and Bhaskar Mitra.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3437963.3441667">doi:10.1145/3437963.3441667</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6teqmlndtrgfvk5mneq5l7ecvq">fatcat:6teqmlndtrgfvk5mneq5l7ecvq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210716210049/https://pure.mpg.de/rest/items/item_3287344_1/component/file_3287345/content" 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/6f/1f/6f1fdd10b2db028d7695d3b3c9748f030b201888.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3437963.3441667"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Generating Instructive Questions from Multiple Articles to Guide Reading in E-Bibliotherapy

Yunxing Xin, Lei Cao, Xin Wang, Xiaohao He, Ling Feng
<span title="2021-05-06">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/taedaf6aozg7vitz5dpgkojane" style="color: black;">Sensors</a> </i> &nbsp;
For model training and testing, we construct a novel large-scale QA dataset named TeenQA, which is specific to adolescent stress.  ...  Such a question shall (a) attract teens' attention; (b) convey the essential message of the reading materials so as to improve teens' active comprehension; and most importantly (c) highlight teens' stress  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/s21093223">doi:10.3390/s21093223</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/34066519">pmid:34066519</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hch5o7y5svfpdezmobttntgj4a">fatcat:hch5o7y5svfpdezmobttntgj4a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210509022440/https://res.mdpi.com/d_attachment/sensors/sensors-21-03223/article_deploy/sensors-21-03223-v2.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/e2/67/e267a4c5cfbe81cfd4018e29bee7f83092e7c079.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/s21093223"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 39 results