Filters








8,672 Hits in 7.9 sec

Benchmark for Complex Answer Retrieval [article]

Federico Nanni, Bhaskar Mitra, Matt Magnusson, Laura Dietz
<span title="2017-05-13">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present early results from a variety of approaches -- from standard information retrieval methods (e.g., tf-idf) to complex systems that using query expansion using knowledge bases and deep neural networks  ...  The new TREC Complex Answer Retrieval (TREC CAR) track introduces a comprehensive dataset that targets this retrieval scenario.  ...  Passage retrieval models can be extended to combine terms and entity-centric knowledge [8, 11] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.04803v1">arXiv:1705.04803v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vgboyaprvzgvlevjs3xunlmhn4">fatcat:vgboyaprvzgvlevjs3xunlmhn4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929111329/https://arxiv.org/pdf/1705.04803v1.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/99/31/9931fe36ba3f5f6e80b05b67d550c7f54cf50fc7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.04803v1" 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>

Iterative Relevance Feedback for Answer Passage Retrieval with Passage-level Semantic Match [article]

Keping Bi, Qingyao Ai, W. Bruce Croft
<span title="2018-12-20">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Then we propose an iterative feedback model based on passage-level semantic match and show that it can produce significant improvements compared to both word-based iterative feedback models and those based  ...  Relevance feedback techniques assume that users provide relevance judgments for the top k (usually 10) documents and then re-rank using a new query model based on those judgments.  ...  Passage Embedding based IRF Models Word-based RF methods were initially designed for document retrieval and usually based on query expansion.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.08870v1">arXiv:1812.08870v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fwyo536aq5eyppr3vxk4cjkaie">fatcat:fwyo536aq5eyppr3vxk4cjkaie</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191019210851/https://arxiv.org/pdf/1812.08870v1.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/1b/14/1b146a389acfd0324b868e2077baf09bb5b4186b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.08870v1" 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>

Benchmark for Complex Answer Retrieval

Federico Nanni, Bhaskar Mitra, Matt Magnusson, Laura Dietz
<span title="">2017</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vdaqozbsqjanlcy7s6hphlvupi" style="color: black;">Proceedings of the ACM SIGIR International Conference on Theory of Information Retrieval - ICTIR &#39;17</a> </i> &nbsp;
We present early results from a variety of approaches -from standard information retrieval methods (e.g., TF-IDF) to complex systems that adopt query expansion, knowledge bases and deep neural networks  ...  Providing answers to complex information needs is a challenging task. e new TREC Complex Answer Retrieval (TREC CAR) track introduces a large-scale dataset where paragraphs are to be retrieved in response  ...  Acknowledgements e publication is funded in part through the scholarship of the Eliteprogramm for Postdocs of the Baden-Wür emberg Sti ung (project "Knowledge Consolidation and Organization for eryspeci  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3121050.3121099">doi:10.1145/3121050.3121099</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ictir/NanniMMD17.html">dblp:conf/ictir/NanniMMD17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wtkbphutorcmvnhdz7mvtce6vq">fatcat:wtkbphutorcmvnhdz7mvtce6vq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180721042305/https://ub-madoc.bib.uni-mannheim.de/42773/1/trec-car.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/78/7a/787a505cce232736cab9a236044bd3f3e4f0dffc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3121050.3121099"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

A reranking model for genomics aspect search

Qinmin Hu, Xiangji Huang
<span title="">2008</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ibcfmixrofb3piydwg5wvir3t4" style="color: black;">Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR &#39;08</a> </i> &nbsp;
This model iteratively computes the maximum hidden aspect for every retrieved passage and then reranks these passages from aspect subsets.  ...  The experimental results show the improvements of the aspect-level performance up to 27.14% for 2006 Genomics topics and 27.09% for 2007 Genomics topics.  ...  In the model, we build up a keyword sample space for every topic and present the passages using those keywords.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1390334.1390502">doi:10.1145/1390334.1390502</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/sigir/HuH08.html">dblp:conf/sigir/HuH08</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rrvqmplmrfdprjeuhcgbcq3v3i">fatcat:rrvqmplmrfdprjeuhcgbcq3v3i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190218073711/https://static.aminer.org/pdf/20170130/pdfs/sigir/6mvczxr2ro5n97i0m4qbqtkda3xtujfb.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/d1/d7/d1d7a6acc6bbdfd765fe50b9d143449072dbf7b2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1390334.1390502"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

A Dual Embedding Space Model for Document Ranking [article]

Bhaskar Mitra, Eric Nalisnick, Nick Craswell, Rich Caruana
<span title="2016-02-02">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
During ranking we map the query words into the input space and the document words into the output space, and compute a query-document relevance score by aggregating the cosine similarities across all the  ...  We postulate that the proposed Dual Embedding Space Model (DESM) captures evidence on whether a document is about a query term in addition to what is modelled by traditional term-frequency based approaches  ...  RELATED WORK Term based IR. For an overview of lexical matching approaches for information retrieval, such as the vector space, probabilistic and language modelling approach, see [26] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1602.01137v1">arXiv:1602.01137v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/i6p7knyn3bdmfprli2f5cmdnze">fatcat:i6p7knyn3bdmfprli2f5cmdnze</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200909150626/https://arxiv.org/pdf/1602.01137v1.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/80/a9/80a974f4797ce9f1d1280630d74eeab6d7475518.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1602.01137v1" 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>

Deep fusion of multiple term-similarity measures for biomedical passage retrieval

Andrés Rosso-Mateus, Manuel Montes-y-Gómez, Paolo Rosso, Fabio A. González
<span title="2020-06-17">2020</span> <i title="IOS Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5232pusig5eapbukawp5py2bk4" style="color: black;">Journal of Intelligent &amp; Fuzzy Systems</a> </i> &nbsp;
This paper presents a novel approach for biomedical passage retrieval which is able to combine different information sources using a similarity matrix fusion strategy based on a convolutional neural network  ...  Closed domain passage retrieval, e.g. biomedical passage retrieval presents additional challenges such as specialized terminology, more complex and elaborated queries, scarcity in the amount of available  ...  In this paper, we present a novel method for biomedical passage retrieval. The model has the ability to combine different information sources.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3233/jifs-179887">doi:10.3233/jifs-179887</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3sqkyjvkhjbt3im5airrunbcfi">fatcat:3sqkyjvkhjbt3im5airrunbcfi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210716213627/https://riunet.upv.es/bitstream/handle/10251/166829/Rosso-Mateus;jsessionid=8E77F2359291C3BE7B9C3F171F2C3C32?sequence=3" 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/61/af61f1f146f6510e4d8e1e18ba9f33bc2300358b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3233/jifs-179887"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

A robust approach to optimizing multi-source information for enhancing genomics retrieval performance

Qinmin Hu, Jimmy Huang, Jun Miao
<span title="">2011</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/n5zrklrhlzhtdorf4rk4rmeo3i" style="color: black;">BMC Bioinformatics</a> </i> &nbsp;
Results: In the proposed approach, we first consider a common scenario for a metasearch system that has access to multiple baselines with retrieving and ranking documents/passages by their own models.  ...  Based on the multiple sources of DFR, BM25 and language model, we can observe that the alliance of giants achieves the best result.  ...  model TfIdfIR passage retrieval using a vector space model with any variant of TF-IDF LmIR passage retrieval using any language model DfrIR passage retrieval using a vector space model with any  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/1471-2105-12-s5-s6">doi:10.1186/1471-2105-12-s5-s6</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/21989123">pmid:21989123</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC3226256/">pmcid:PMC3226256</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/d3gstpmdbvaf3jjqvjht5yvuga">fatcat:d3gstpmdbvaf3jjqvjht5yvuga</a> </span>
<a target="_blank" rel="noopener" href="https://archive.org/download/pubmed-PMC3226256/PMC3226256-1471-2105-12-S5-S6.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> File Archive [PDF] </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/1471-2105-12-s5-s6"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> springer.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3226256" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Semantic Models for the First-stage Retrieval: A Comprehensive Review [article]

Yinqiong Cai, Yixing Fan, Jiafeng Guo, Fei Sun, Ruqing Zhang, Xueqi Cheng
<span title="2021-08-09">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Therefore, it has been a long-term desire to build semantic models for the first-stage retrieval that can achieve high recall efficiently.  ...  In this paper, we describe the current landscape of the first-stage retrieval models under a unified framework to clarify the connection between classical term-based retrieval methods, early semantic retrieval  ...  [147] also proposed to combine word vector based query likelihood with the standard language model based query likelihood for document retrieval.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.04831v3">arXiv:2103.04831v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6qa7hvc3jve3pcmo2mo4qsiefq">fatcat:6qa7hvc3jve3pcmo2mo4qsiefq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210326172737/https://arxiv.org/pdf/2103.04831v2.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/18/c0/18c04f85d8ec3167a9933a36699abe8c74e59dd0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.04831v3" 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>

Self-supervised Answer Retrieval on Clinical Notes [article]

Paul Grundmann, Sebastian Arnold, Alexander Löser
<span title="2021-08-02">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We introduce CAPR, a rule-based self-supervision objective for training Transformer language models for domain-specific passage matching.  ...  We approach this challenge specifically in a clinical scenario, where doctors retrieve cohorts of patients based on diagnoses and other latent medical aspects.  ...  This allows the model to apply full self-attention on the combination of a specific entity and aspect in the query. The Bi-encoder uses a pretrained language model such as BERT for both encoders.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.00775v1">arXiv:2108.00775v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dku5pllocnb2xeserzsenvy7dm">fatcat:dku5pllocnb2xeserzsenvy7dm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210804150330/https://arxiv.org/pdf/2108.00775v1.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/50/01/50010fe735d0c103d49f903256fb4d2c29addc5d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.00775v1" 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>

Data-driven approaches to information access

Susan Dumais
<span title="">2003</span> <i title="Wiley"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/sjomsvi4zngnnh4gx5bz2onwye" style="color: black;">Cognitive Science</a> </i> &nbsp;
The application areas include information retrieval, text categorization, and question answering.  ...  A common theme in these applications is that practical information access problems can be solved by analyzing the statistical properties of words in large volumes of real world texts.  ...  , Edward Cutrell (for text classification), Eric Brill, and Michele Banko (for question answering).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1207/s15516709cog2703_7">doi:10.1207/s15516709cog2703_7</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/psbqizdjjvfljpj7a6bsndnt3e">fatcat:psbqizdjjvfljpj7a6bsndnt3e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160603094237/http://csjarchive.cogsci.rpi.edu/2003v27/i03/p0491p0524/00000122.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/5a/9e/5a9e4c819900c3149d5247d7880cd3c02d32b511.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1207/s15516709cog2703_7"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Data-driven approaches to information access

S Dumais
<span title="">2003</span> <i title="Wiley"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/sjomsvi4zngnnh4gx5bz2onwye" style="color: black;">Cognitive Science</a> </i> &nbsp;
The application areas include information retrieval, text categorization, and question answering.  ...  A common theme in these applications is that practical information access problems can be solved by analyzing the statistical properties of words in large volumes of real world texts.  ...  , Edward Cutrell (for text classification), Eric Brill, and Michele Banko (for question answering).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/s0364-0213(03)00013-2">doi:10.1016/s0364-0213(03)00013-2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ayz4ng2z5naxje637emcirubve">fatcat:ayz4ng2z5naxje637emcirubve</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160603094237/http://csjarchive.cogsci.rpi.edu/2003v27/i03/p0491p0524/00000122.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/5a/9e/5a9e4c819900c3149d5247d7880cd3c02d32b511.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/s0364-0213(03)00013-2"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Introducing Neural Bag of Whole-Words with ColBERTer: Contextualized Late Interactions using Enhanced Reduction [article]

Sebastian Hofstätter, Omar Khattab, Sophia Althammer, Mete Sertkan, Allan Hanbury
<span title="2022-03-24">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
For its multi-vector component, ColBERTer reduces the number of stored vectors per document by learning unique whole-word representations for the terms in each document and learning to identify and remove  ...  To this end, ColBERTer fuses single-vector retrieval, multi-vector refinement, and optional lexical matching components into one model.  ...  Specifically, we study for our ColBERTer model: RQ1 Which aggregation and training regime works best for combined retrieval and refinement capabilities of ColBERTer?  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.13088v1">arXiv:2203.13088v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pclsfdz7ufhfbbnyzw6h7kslka">fatcat:pclsfdz7ufhfbbnyzw6h7kslka</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220606082802/https://arxiv.org/pdf/2203.13088v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/82/e3/82e3a63301eeb82090bc79c6009af20a5daea15a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.13088v1" 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 Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques [article]

Jimmy Lin, Xueguang Ma
<span title="2021-06-28">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Recent developments in representational learning for information retrieval can be organized in a conceptual framework that establishes two pairs of contrasts: sparse vs. dense representations and unsupervised  ...  We present a novel technique dubbed "uniCOIL", a simple extension of COIL that achieves to our knowledge the current state-of-the-art in sparse retrieval on the popular MS MARCO passage ranking dataset  ...  This research was supported in part by the Canada First Research Excellence Fund and the Natural Sciences and Engineering Research Council (NSERC) of Canada.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.14807v1">arXiv:2106.14807v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/j7dl4vcpsfb2zdb5byjcmvlkea">fatcat:j7dl4vcpsfb2zdb5byjcmvlkea</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210730101306/https://arxiv.org/pdf/2106.14807v1.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/89/d3/89d373d61c68465fd49da1257aa959e5abefd155.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.14807v1" 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 bayesian learning approach to promoting diversity in ranking for biomedical information retrieval

Xiangji Huang, Qinmin Hu
<span title="">2009</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ibcfmixrofb3piydwg5wvir3t4" style="color: black;">Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval - SIGIR &#39;09</a> </i> &nbsp;
In this paper, we propose a Bayesian learning approach to promoting diversity for information retrieval in biomedicine and a re-ranking model to improve retrieval performance in the biomedical domain.  ...  First, the re-ranking model computes the maximum posterior probability of the hidden property corresponding to each retrieved passage.  ...  We thank four anonymous reviewers for their excellent comments on this paper.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1571941.1571995">doi:10.1145/1571941.1571995</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/sigir/HuangH09.html">dblp:conf/sigir/HuangH09</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hviqlvzdxnct7ialzoug26yjnq">fatcat:hviqlvzdxnct7ialzoug26yjnq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20110401172005/http://www.yorku.ca/jhuang/paper/sigir09.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/50/b3/50b31cc4a3d7e2742459c272237d8f00a5c92661.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1571941.1571995"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Revisiting Iterative Relevance Feedback for Document and Passage Retrieval [article]

Keping Bi, Qingyao Ai, W. Bruce Croft
<span title="2019-06-09">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This indicates that IRF for passage retrieval has huge potential.  ...  As more and more search traffic comes from mobile phones, intelligent assistants, and smart-home devices, new challenges (e.g., limited presentation space) and opportunities come up in information retrieval  ...  In general, there are three types of relevance feedback (RF) methods for ad-hoc retrieval, which are based on the vector space model (VSM) [17] , the probabilistic model [11] and the language model  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.05731v3">arXiv:1812.05731v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3biwzazarvd6ddhqjvxzttuk3y">fatcat:3biwzazarvd6ddhqjvxzttuk3y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200823161312/https://arxiv.org/pdf/1812.05731v2.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/7e/51/7e5175aec4c66449ed798bc6b3508a5399baa216.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.05731v3" 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 8,672 results