Internet Archive Scholar
Filters
























2,816 Hits in 15.4 sec

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>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.3 MB)
https://web.archive.org/web/20211208132950/https://arxiv.org/pdf/2112.02992v1.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/2112.02992v1.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="2021-12-01">2021</span> <span class="release-stage" >pre-print</span> <span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.02992v1">arXiv:2112.02992v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/autoepi2kjb2bpbebov2wrxqui">fatcat:autoepi2kjb2bpbebov2wrxqui</a> </span>
As such, we argue that, to achieve robust NLU, the model architecture/training and the dataset are equally important.  ...  It's worth noting that the human ability of understanding natural language is flexible and robust.  ...  Evaluation Settings: For the scope of this chapter, we only evaluate on English nonforum FAQ items, and leave the non-English and forum ones for future research as great challenges have already been observed  ... 
<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>
<span class="ui label basic blue small">Multiple Versions</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>
Citation

Xinliang Frederick Zhang. "Towards More Robust Natural Language Understanding." arXiv (2022)

Reframing Human-AI Collaboration for Generating Free-Text Explanations [article]

Sarah Wiegreffe, Jack Hessel, Swabha Swayamdipta, Mark Riedl, Yejin Choi
<span title="2022-05-04">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.7 MB)
https://web.archive.org/web/20220507112822/https://arxiv.org/pdf/2112.08674v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2112.08674v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2021-12-16">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.08674v1">arXiv:2112.08674v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2vyzaw5kzngeneqd4abc4mq4ru">fatcat:2vyzaw5kzngeneqd4abc4mq4ru</a> </span>
We consider the task of generating free-text explanations using human-written examples in a few-shot manner.  ...  Despite the intrinsic subjectivity of acceptability judgments, we demonstrate that acceptability is partially correlated with various fine-grained attributes of explanations.  ...  We present workers with a dataset instance, its gold label, and two explanations for the instance generated under different conditions ("head-tohead").  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.08674v2">arXiv:2112.08674v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4xp6wex575cvldxkymjtbvnsha">fatcat:4xp6wex575cvldxkymjtbvnsha</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220507112822/https://arxiv.org/pdf/2112.08674v2.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/40/81/4081aeb7ff148cc4678efca4e44a72dece4542e3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.08674v2" 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

Sarah Wiegreffe, Jack Hessel, Swabha Swayamdipta, Mark Riedl, Yejin Choi. "Reframing Human-AI Collaboration for Generating Free-Text Explanations." arXiv (2022)

Challenging common interpretability assumptions in feature attribution explanations [article]

Jonathan Dinu
<span title="2020-12-04">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (3.6 MB)
https://web.archive.org/web/20201208095856/https://arxiv.org/pdf/2012.02748v1.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/2012.02748v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

We empirically evaluate the veracity of three common interpretability assumptions through a large scale human-subjects experiment with a simple "placebo explanation" control.  ...  We find that feature attribution explanations provide marginal utility in our task for a human decision maker and in certain cases result in worse decisions due to cognitive and contextual confounders.  ...  When these systems have been evaluated systematically with human subjects, the gold standard for quantifying the utility of an explanation is some self defined measure  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.02748v1">arXiv:2012.02748v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gfykfgy4xrashgqwfsnmtfs4gq">fatcat:gfykfgy4xrashgqwfsnmtfs4gq</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201208095856/https://arxiv.org/pdf/2012.02748v1.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/aa/19/aa193dd216440639590a8ddb3e98a77fca09cc2a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.02748v1" 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

Jonathan Dinu. "Challenging common interpretability assumptions in feature attribution explanations." arXiv (2020)

Accelerated learning from recommender systems using multi-armed bandit [article]

Meisam Hejazinia, Kyler Eastman, Shuqin Ye, Abbas Amirabadi, Ravi Divvela
<span title="2019-08-16">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (717.4 kB)
https://web.archive.org/web/20191222124536/https://arxiv.org/pdf/1908.06158v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1908.06158v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

The gold standard for evaluating recommendation algorithms has been the A/B test since it is an unbiased way to estimate how well one or more algorithms compare in the real world.  ...  We present the result of our experiment and compare all the offline, MAB, and online A/B tests metrics for our use case.  ...  ACKNOWLEDGMENTS The authors would like to thank Travis Brady, Pavlos Mitsoulis Ntompos, Ben Dundee, Kurt Smith, and John Meakin for their internal review of this paper and their helpful feedback.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.06158v1">arXiv:1908.06158v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7rp3l5ea25feliymdm6cyeuska">fatcat:7rp3l5ea25feliymdm6cyeuska</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191222124536/https://arxiv.org/pdf/1908.06158v1.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/b7/5c/b75c26de80ce15c103fb94c261b9b67cc4d9446e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.06158v1" 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

Meisam Hejazinia, Kyler Eastman, Shuqin Ye, Abbas Amirabadi, Ravi Divvela. "Accelerated learning from recommender systems using multi-armed bandit." arXiv (2019)

Structuring, Aggregating, and Evaluating Crowdsourced Design Critique

Kurt Luther, Jari-Lee Tolentino, Wei Wu, Amy Pavel, Brian P. Bailey, Maneesh Agrawala, Björn Hartmann, Steven P. Dow
<span title="">2015</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/shtxaejfmnag3l32zxhs3awpg4" style="color: black;">Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work &amp; Social Computing - CSCW &#39;15</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (10.9 MB)
https://web.archive.org/web/20170706061805/http://vis.berkeley.edu/papers/crowdcrit/luther-crowdcrit-cscw2015.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit <a rel="external noopener" href="http://vis.berkeley.edu/papers/crowdcrit/luther-crowdcrit-cscw2015.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

We evaluated CrowdCrit in three studies focusing on the designer's experience and benefits of the critiques.  ...  The third study showed that designers were enthusiastic about crowd critiques and used them to change their designs. We conclude with implications for the design of crowd feedback services.  ...  Financial support provided by the National Science Foundation under IIS grants 1210836, 1208382, and 1217096.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2675133.2675283">doi:10.1145/2675133.2675283</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cscw/LutherTWPBAHD15.html">dblp:conf/cscw/LutherTWPBAHD15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ynstlpzabzdrhj45t76pi4ucem">fatcat:ynstlpzabzdrhj45t76pi4ucem</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170706061805/http://vis.berkeley.edu/papers/crowdcrit/luther-crowdcrit-cscw2015.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/61/1d/611dab5573ac51e734029ee037d1bb7cdaeb3223.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2675133.2675283"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>
Citation

Kurt Luther, Jari-Lee Tolentino, Wei Wu, Amy Pavel, Brian P. Bailey, Maneesh Agrawala, Björn Hartmann, Steven P. Dow. "Structuring, Aggregating, and Evaluating Crowdsourced Design Critique." Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work & Social Computing - CSCW '15 (2015) 473-485

Hierarchical Knowledge Graphs: A Novel Information Representation for Exploratory Search Tasks [article]

Bahareh Sarrafzadeh, Adam Roegiest, Edward Lank
<span title="2020-05-04">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (12.3 MB)
https://web.archive.org/web/20200507101629/https://arxiv.org/pdf/2005.01716v1.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/2005.01716v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Alongside the above study, we perform an additional mixed methods analysis of the effect of precision and recall on the performance of hierarchical knowledge graphs for two different exploratory search  ...  We discuss the implications of our results and analyze other factors that more significantly impact exploratory search performance in our experimental tasks.  ...  While acknowledging that this benchmark may not be perfect, in this paper we leverage it as the most up-to-date standard for evaluating IE systems. System Effectiveness.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.01716v1">arXiv:2005.01716v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mqqvc2hj45ej5d6ltqvambbhwi">fatcat:mqqvc2hj45ej5d6ltqvambbhwi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200507101629/https://arxiv.org/pdf/2005.01716v1.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/dc/2a/dc2a513ee4f3cc7b826289e40ecb95bc1e5d6fe2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.01716v1" 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

Bahareh Sarrafzadeh, Adam Roegiest, Edward Lank. "Hierarchical Knowledge Graphs: A Novel Information Representation for Exploratory Search Tasks." arXiv (2020)

ARKref: a rule-based coreference resolution system [article]

Brendan O'Connor, Michael Heilman
<span title="2013-10-08">2013</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (115.0 kB)
https://web.archive.org/web/20191014235943/https://arxiv.org/pdf/1310.1975v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1310.1975v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Its architecture is based on the work of Haghighi and Klein (2009). ARKref was originally written in 2009. At the time of writing, the last released version was in March 2011.  ...  ARKref is a tool for noun phrase coreference.  ...  For evaluating on annotated ACE data, we follow previous work and use the ACE data's definitions of mentions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1310.1975v1">arXiv:1310.1975v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7dkr63d2p5divnx2bycagjidky">fatcat:7dkr63d2p5divnx2bycagjidky</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191014235943/https://arxiv.org/pdf/1310.1975v1.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/b6/73b6647a6ce5e483c89a5932ecc9abefbf65e5c5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1310.1975v1" 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

Brendan O'Connor, Michael Heilman. "ARKref: a rule-based coreference resolution system." arXiv (2013)

ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities [article]

Hongming Zhang, Xin Liu, Haojie Pan, Haowen Ke, Jiefu Ou, Tianqing Fang, Yangqiu Song
<span title="2022-01-16">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.5 MB)
https://web.archive.org/web/20220123225229/https://arxiv.org/pdf/2104.02137v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2104.02137v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2021-04-05">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.02137v1">arXiv:2104.02137v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zviphwzftreplhaboita2zo2va">fatcat:zviphwzftreplhaboita2zo2va</a> </span>
Detailed analysis is provided to demonstrate its quality. All the collected data, APIs, and tools are available at https://github.com/HKUST-KnowComp/ASER.  ...  In this paper, we propose to develop principles for collecting commonsense knowledge based on selectional preference.  ...  Acknowledgements This paper was supported by the GRF (16211520) and the RIF (R6020-19 and R6021-20) from RGC of Hong Kong, the NSFC Fund (U20B2053) from the NSFC of China, the MHKJFS (MHP/001/19) from  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.02137v2">arXiv:2104.02137v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dmb2dhqzevc2pd2vef4n5ds5ei">fatcat:dmb2dhqzevc2pd2vef4n5ds5ei</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/20220123225229/https://arxiv.org/pdf/2104.02137v2.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/92/85/9285d083e51f257905b6016955919bb0f5d0fe46.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.02137v2" 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

Hongming Zhang, Xin Liu, Haojie Pan, Haowen Ke, Jiefu Ou, Tianqing Fang, Yangqiu Song. "ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities." arXiv (2022)

Truthful AI: Developing and governing AI that does not lie [article]

Owain Evans, Owen Cotton-Barratt, Lukas Finnveden, Adam Bales, Avital Balwit, Peter Wills, Luca Righetti, William Saunders
<span title="2021-10-13">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.2 MB)
https://web.archive.org/web/20211015231548/https://arxiv.org/pdf/2110.06674v1.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/2110.06674v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

This raises the question of how we should limit the harm caused by AI "lies" (i.e. falsehoods that are actively selected for).  ...  Our initial proposals for these areas include: (1) a standard of avoiding "negligent falsehoods" (a generalisation of lies that is easier to assess); (2) institutions to evaluate AI systems before and  ...  We have also ben- We would like to thank the Future of Humanity Institute (University of Oxford) and BERI (especially Sawyer Bernath) for supporting this work.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.06674v1">arXiv:2110.06674v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yttuvho7wrd6bgbi6fijh7wy4e">fatcat:yttuvho7wrd6bgbi6fijh7wy4e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211015231548/https://arxiv.org/pdf/2110.06674v1.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/d5/1e/d51ebec3064f82ea4128fc1c3241003d4072c639.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.06674v1" 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

Owain Evans, Owen Cotton-Barratt, Lukas Finnveden, Adam Bales, Avital Balwit, Peter Wills, Luca Righetti, William Saunders. "Truthful AI: Developing and governing AI that does not lie." arXiv (2021)

A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis [article]

Samuel Budd, Emma C Robinson, Bernhard Kainz
<span title="2019-10-07">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (690.7 kB)
https://web.archive.org/web/20200831070939/https://arxiv.org/pdf/1910.02923v1.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/1910.02923v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2021-05-05">2021</span> <span class="release-stage">accepted</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.02923v2">arXiv:1910.02923v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qnbn54lpjvfobpsuwzjbyxkv74">fatcat:qnbn54lpjvfobpsuwzjbyxkv74</a> </span>
We evaluate four key areas that we consider vital for deep learning in the clinical practice: (1) Active Learning - to choose the best data to annotate for optimal model performance; (2) Interpretation  ...  Fully automatic deep learning has become the state-of-the-art technique for many tasks including image acquisition, analysis and interpretation, and for the extraction of clinically useful information  ...  Noisy Oracles Gold-standard annotations for medical image data are acquired by aggregating annotations from multiple expert oracles, but as previously discussed, this is rarely feasible to obtain for large  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.02923v1">arXiv:1910.02923v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/25caso3ybjb5fhme7zqhhmet6m">fatcat:25caso3ybjb5fhme7zqhhmet6m</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200831070939/https://arxiv.org/pdf/1910.02923v1.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/b1/95/b19590cf059226fc9d70ed19a09f6f6ace20379c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.02923v1" 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

Samuel Budd, Emma C Robinson, Bernhard Kainz. "A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis." arXiv (2019)

Architecting Real-Time Crowd-Powered Systems

Walter S Lasecki, Christopher Homan, Jeffrey P. Bigham
<span title="2014-09-07">2014</span> <i title="ThinkSplash, LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/tqlqej3n65fvhit5lvmziu2sci" style="color: black;">Human Computation</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (419.9 kB)
https://web.archive.org/web/20150926021307/http://repository.cmu.edu/cgi/viewcontent.cgi?article=1265&context=hcii

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit <a rel="external noopener" href="http://repository.cmu.edu/cgi/viewcontent.cgi?article=1265&context=hcii">the original URL</a>. The file type is <code>application/pdf</code>.

While it has primarily been used for tasks that are not time-sensitive, recent systems use crowdsourcing to get on-demand, real-time, and even interactive results.  ...  In this paper, we present techniques for building real-time crowdsourcing systems, and then discuss how and when to use them.  ...  ACKNOWLEDGEMENTS This work has been supported by the National Science Foundation (under awards #IIS-1149709, #IIS-1218209, and #SES-1111016)  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.15346/hc.v1i1.5">doi:10.15346/hc.v1i1.5</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/journals/hc/LaseckiHB14.html">dblp:journals/hc/LaseckiHB14</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mdzsgjs2cja47flzmv3wexxirq">fatcat:mdzsgjs2cja47flzmv3wexxirq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20150926021307/http://repository.cmu.edu/cgi/viewcontent.cgi?article=1265&amp;context=hcii" 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/d0/6ed0795553000af2a0bf05598260afd751d51a57.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.15346/hc.v1i1.5"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
Citation

Walter S Lasecki, Christopher Homan, Jeffrey P. Bigham. "Architecting Real-Time Crowd-Powered Systems." Human Computation 1.1 (2014) 67-93

Evaluative Language Beyond Bags of Words: Linguistic Insights and Computational Applications

Farah Benamara, Maite Taboada, Yannick Mathieu
<span title="">2017</span> <i title="MIT Press - Journals"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/e4yflo6sufcufjwloald7xudm4" style="color: black;">Computational Linguistics</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (710.1 kB)
https://web.archive.org/web/20200509130804/https://hal.archives-ouvertes.fr/hal-02540259/document

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://hal.archives-ouvertes.fr/hal-02540259/document">the original URL</a>. The file type is <code>application/pdf</code>.

We then argue that the standard computational definition of the concept of evaluative language neglects the dynamic nature of evaluation, in which the interpretation of a given evaluation depends on linguistic  ...  We end the review by outlining what we believe the future directions of sentiment analysis are, and the role that discourse and contextual information need to play. *  ...  We thank Nicholas Asher, Paola Merlo, and the two anonymous reviewers for their comments or suggestions. We take responsibility for any errors that may remain.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1162/coli_a_00278">doi:10.1162/coli_a_00278</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yphpwgzrafhgxbit55rjhyhix4">fatcat:yphpwgzrafhgxbit55rjhyhix4</a> </span>
<span class="ui label basic orange small" title="Directory of Open Access Journals">DOAJ</span> <span class="ui label basic orange small" title="Szcezepanski OA Journal List">Szczepanski</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200509130804/https://hal.archives-ouvertes.fr/hal-02540259/document" 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/f4/15/f415296740391078335ccc573c9e7dbb141e89aa.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1162/coli_a_00278"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mitpressjournals.org </button> </a>
Citation

Farah Benamara, Maite Taboada, Yannick Mathieu. "Evaluative Language Beyond Bags of Words: Linguistic Insights and Computational Applications." Computational Linguistics 43.1 (2017) 201-264

Towards Explainable Fact Checking [article]

Isabelle Augenstein
<span title="2021-12-08">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (10.0 MB)
https://web.archive.org/web/20211210174722/https://arxiv.org/pdf/2108.10274v2.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/2108.10274v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2021-08-23">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.10274v1">arXiv:2108.10274v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/a2f7y3fd5bfg3ixyml3ty4j4oe">fatcat:a2f7y3fd5bfg3ixyml3ty4j4oe</a> </span>
Its contributions go beyond fact checking, with the thesis proposing more general machine learning solutions for natural language processing in the area of learning with limited labelled data.  ...  While this has been known for some time, the issues this raises have been exacerbated by models increasing in size, and by EU legislation requiring models to be used for decision making to provide explanations  ...  As the subjectivity of annotations for existing data on claim check-worthiness detection is a known problem (Konstantinovskiy et al. 2018), we view the data as a set of positive and unlabelled (PU) data  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.10274v2">arXiv:2108.10274v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5s4an6irezcjfmvvhmiaeqarh4">fatcat:5s4an6irezcjfmvvhmiaeqarh4</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211210174722/https://arxiv.org/pdf/2108.10274v2.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/8b/9c/8b9c16fca8bdafb061420ec5ce77fef53eb35595.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.10274v2" 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

Isabelle Augenstein. "Towards Explainable Fact Checking." arXiv (2021)

A Holistic Framework for Analyzing the COVID-19 Vaccine Debate [article]

Maria Leonor Pacheco, Tunazzina Islam, Monal Mahajan, Andrey Shor, Ming Yin, Lyle Ungar, Dan Goldwasser
<span title="2022-05-03">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (3.0 MB)
https://web.archive.org/web/20220507053812/https://arxiv.org/pdf/2205.01817v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2205.01817v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

We study how to model the dependencies between the different level of analysis and incorporate human insights into the learning process.  ...  In this work we propose a holistic analysis framework connecting stance and reason analysis, and fine-grained entity level moral sentiment analysis.  ...  We also thank the anonymous reviewers of this paper for their insightful comments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.01817v1">arXiv:2205.01817v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/q7sni7qm5vhfnh5427sfywn4k4">fatcat:q7sni7qm5vhfnh5427sfywn4k4</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220507053812/https://arxiv.org/pdf/2205.01817v1.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/ce/21/ce21157159a1645a352c8fda44c9b01f5c6dbce0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.01817v1" 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

Maria Leonor Pacheco, Tunazzina Islam, Monal Mahajan, Andrey Shor, Ming Yin, Lyle Ungar, Dan Goldwasser. "A Holistic Framework for Analyzing the COVID-19 Vaccine Debate." arXiv (2022)

Masthead - Full issue pdf

<span title="2017-01-26">2017</span> <i title="Walter de Gruyter GmbH"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/u6522y7bvnd4ldizpl5yahfbmq" style="color: black;">Chemistry International</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (10.1 MB)
https://web.archive.org/web/20180730010507/https://www.degruyter.com/downloadpdf/j/ci.2017.39.issue-3/ci-2017-0300/ci-2017-0300.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="https://www.degruyter.com/downloadpdf/j/ci.2017.39.issue-3/ci-2017-0300/ci-2017-0300.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Also considered are some IUPAC digital initiatives for supporting chemistry data publication, including the International Chemical Identifier (InChI) [15] and the online Gold Book Compendium of Chemical  ...  The authors hope, through the Interdivisional project, that IUPAC will continue to lead in the critical evaluation of chemical data -no matter how 'big'!  ...  methods; and for its critical evaluation of data and the development of standards for data exchange.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1515/ci-2017-0300">doi:10.1515/ci-2017-0300</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ibp2y332gje47hx727nnwegtgi">fatcat:ibp2y332gje47hx727nnwegtgi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180730010507/https://www.degruyter.com/downloadpdf/j/ci.2017.39.issue-3/ci-2017-0300/ci-2017-0300.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/5f/03/5f032fc37575e4ab10c1b5a2e888912adb06a4c0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1515/ci-2017-0300"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> degruyter.com </button> </a>
Citation

"Masthead - Full issue pdf." Chemistry International 39.3 (2017) 1-54

&laquo; Previous Showing results 1 &mdash; 15 out of 2,816 results