Filters








866 Hits in 8.2 sec

A matter of words: NLP for quality evaluation of Wikipedia medical articles [article]

Vittoria Cozza and Marinella Petrocchi and Angelo Spognardi
<span title="2016-03-07">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose to leverage specific domain features to improve the results of the evaluation of Wikipedia medical articles.  ...  Automatic quality evaluation of Web information is a task with many fields of applications and of great relevance, especially in critical domains like the medical one.  ...  Blumenstock [6] inspects the relevance of the word-count feature at each quality stage, showing that it can play a very important role in the quality assessment of Wikipedia articles.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1603.01987v1">arXiv:1603.01987v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bi4mhlljbjevph6vjihnguydnu">fatcat:bi4mhlljbjevph6vjihnguydnu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200901154536/https://arxiv.org/pdf/1603.01987v1.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/33/59/335943d3d27ad7f43e420eb15308f46133be62f9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1603.01987v1" 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>

Topic Modeling with Contextualized Word Representation Clusters [article]

Laure Thompson, David Mimno
<span title="2020-10-23">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Unlike clusterings of vocabulary-level word embeddings, the resulting models more naturally capture polysemy and can be used as a way of organizing documents.  ...  Clustering token-level contextualized word representations produces output that shares many similarities with topic models for English text collections.  ...  Evaluation Metrics We evaluate the quality of "topics" produced by clustering contextualized word representations with several quantitative measures.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.12626v1">arXiv:2010.12626v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ycxu4vc6lnc2pmddb6cor4ggqy">fatcat:ycxu4vc6lnc2pmddb6cor4ggqy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201030132146/https://arxiv.org/pdf/2010.12626v1.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/7f/5a7f3719decfa4eb4dfeed9af004a5e176db0987.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.12626v1" 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>

More Than Words: Towards Better Quality Interpretations of Text Classifiers [article]

Muhammad Bilal Zafar, Philipp Schmidt, Michele Donini, Cédric Archambeau, Felix Biessmann, Sanjiv Ranjan Das, Krishnaram Kenthapadi
<span title="2021-12-23">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The large size and complex decision mechanisms of state-of-the-art text classifiers make it difficult for humans to understand their predictions, leading to a potential lack of trust by the users.  ...  We use computational metrics and human subject studies to compare the quality of sentence-based interpretations against token-based ones.  ...  Wiki: The Wikipedia article data from Kaggle (licensed under CC BY-SA 3.0). 4 The task is to predict whether a Wikipedia article is written with a promotional tone or neutral tone.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.12444v1">arXiv:2112.12444v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/p7glpcebxfbufnscwtfomrwqiq">fatcat:p7glpcebxfbufnscwtfomrwqiq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220102165007/https://arxiv.org/pdf/2112.12444v1.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/43/bb/43bb493df73db5bc407c80dddb213b6c9450083f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.12444v1" 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>

Not just about size - A Study on the Role of Distributed Word Representations in the Analysis of Scientific Publications [article]

Andres Garcia, Jose Manuel Gomez-Perez
<span title="2018-04-05">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper we present experimental results about the generation of word embeddings from scholarly publications for the intelligent processing of scientific texts extracted from SciGraph.  ...  can assist scientists over a range of knowledge-intensive tasks.  ...  We also thank Constantino Roman for his contributions to the experimental evaluation of this work.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.01772v1">arXiv:1804.01772v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3fuzesbrsfbdnaeslgbodea4n4">fatcat:3fuzesbrsfbdnaeslgbodea4n4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929150938/https://arxiv.org/pdf/1804.01772v1.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/88/86/888644070531a878b533cddcdbe47a6b76171cf0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.01772v1" 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>

Are Word Embedding Methods Stable and Should We Care About It? [article]

Angana Borah, Manash Pratim Barman, Amit Awekar
<span title="2021-04-17">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Word Embedding Methods (WEMs) are a class of representation learning methods that generate dense vector representation for each word in the given text data.  ...  The central idea of this paper is to explore the stability measurement of WEMs using intrinsic evaluation based on word similarity.  ...  It contains a subset of English Wikipedia articles from October 2017 Wikipedia dump. News articles are covered in the NewsCrawl(2007) dataset 3 .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.08433v1">arXiv:2104.08433v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hve3z426nbbfhmpyqxr6beltem">fatcat:hve3z426nbbfhmpyqxr6beltem</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210421033257/https://arxiv.org/pdf/2104.08433v1.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/bb/81/bb815c343dff7f7596c1544871183b68cf11ddbc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.08433v1" 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>

Distributional semantic modeling: a revised technique to train term/word vector space models applying the ontology-related approach [article]

Oleksandr Palagin, Vitalii Velychko, Kyrylo Malakhov, Oleksandr Shchurov
<span title="2020-03-06">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The semantic map can be represented as a graph using Vec2graph - a Python library for visualizing word embeddings (term embeddings in our case) as dynamic and interactive graphs.  ...  We design a new technique for the distributional semantic modeling with a neural network-based approach to learn distributed term representations (or term embeddings) - term vector space models as a result  ...  For example, if your goal is to build a sentiment lexicon, then using a dataset from the medical domain or even Wikipedia may not be effective.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.03350v1">arXiv:2003.03350v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/l5r5dvmqpff4liomz4tezkzcru">fatcat:l5r5dvmqpff4liomz4tezkzcru</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200320154043/https://arxiv.org/pdf/2003.03350v1.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/2003.03350v1" 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>

Inducing Embeddings for Rare and Unseen Words by Leveraging Lexical Resources

Mohammad Taher Pilehvar, Nigel Collier
<span title="">2017</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/o3r3buwoongbbjvsatp4bckpxm" style="color: black;">Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers</a> </i> &nbsp;
We put forward an approach that exploits the knowledge encoded in lexical resources in order to induce representations for words that were not encountered frequently during training.  ...  We performed evaluations in different settings, showing that the technique can provide consistent improvements on multiple benchmarks across domains.  ...  Acknowledgments The authors gratefully acknowledge the support of the MRC grant No. MR/M025160/1 for PheneBank.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/e17-2062">doi:10.18653/v1/e17-2062</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/eacl/CollierP17.html">dblp:conf/eacl/CollierP17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2x7k3t2orjgpdhy7mdr23w63fq">fatcat:2x7k3t2orjgpdhy7mdr23w63fq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200311145716/https://www.repository.cam.ac.uk/bitstream/handle/1810/263834/Pilehvar_et_al-2017-Proceedings_of_the_15th_Conference_of_the_European_Chapter_of_the%20Association_for_Computational_Linguistics-VoR.pdf;jsessionid=97D9ADAE8EEB199AE2C9B7B0B85F7E93?sequence=1" 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/a3/90/a390d79ea90116bf5d34731d9b0c851650f21f7f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/e17-2062"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Speculation detection for Chinese clinical notes: Impacts of word segmentation and embedding models

Shaodian Zhang, Tian Kang, Xingting Zhang, Dong Wen, Noémie Elhadad, Jianbo Lei
<span title="">2016</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/p4kk6lusgrhyxecgig72iasi5q" style="color: black;">Journal of Biomedical Informatics</a> </i> &nbsp;
We propose a sequence labeling based system for speculation detection, which relies on features from bag of characters, bag of words, character embedding, and word embedding.  ...  In clinical texts, identifying speculations is a critical step of natural language processing (NLP).  ...  This study was supported by the National Natural Science Foundation of China (NSFC) Grant # 81171426 and #81471756, and National Institute of General Medical Sciences Grant R01GM114355.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.jbi.2016.02.011">doi:10.1016/j.jbi.2016.02.011</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/26923634">pmid:26923634</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC5282586/">pmcid:PMC5282586</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/us6u2btb2zeqbo4d3ge7fybwwa">fatcat:us6u2btb2zeqbo4d3ge7fybwwa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20171004045031/http://publisher-connector.core.ac.uk/resourcesync/data/elsevier/pdf/d8d/aHR0cDovL2FwaS5lbHNldmllci5jb20vY29udGVudC9hcnRpY2xlL3BpaS9zMTUzMjA0NjQxNjAwMDMzMg%3D%3D.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/da/99da167c00b22d1cbb843b9fcf962799c4a17006.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.jbi.2016.02.011"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> elsevier.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5282586" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Mixed Membership Word Embeddings for Computational Social Science [article]

James Foulds
<span title="2018-02-20">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
I show how to train the model using a combination of state-of-the-art training techniques for word embeddings and topic models.  ...  Word embeddings improve the performance of NLP systems by revealing the hidden structural relationships between words.  ...  Acknowledgements I thank Eric Nalisnick and Padhraic Smyth for many helpful discussions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.07368v3">arXiv:1705.07368v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/47dyqfvxvvhqderbk2atx7bfpy">fatcat:47dyqfvxvvhqderbk2atx7bfpy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826214943/https://arxiv.org/pdf/1705.07368v3.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/ad/64/ad6486945cce19d412d30061708fd159fb2dc5da.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.07368v3" 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>

Distributional semantic modeling: a revised technique to train term/word vector space models applying the ontology-related approach

O.V. Palagin, Glushkov Institute of Cybernetics NAS of Ukraine, V.Yu. Velychko, K.S. Malakhov, O.S. Shchurov, Glushkov Institute of Cybernetics NAS of Ukraine, Glushkov Institute of Cybernetics NAS of Ukraine, Glushkov Institute of Cybernetics NAS of Ukraine
<span title="">2020</span> <i title="National Academy of Sciences of Ukraine (Co. LTD Ukrinformnauka)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/zasksg24kndafnkhcgzyei44x4" style="color: black;">PROBLEMS IN PROGRAMMING</a> </i> &nbsp;
We design a new technique for the distributional semantic modeling with a neural network-based approach to learn distributed term representations (or term embeddings) – term vector space models as a result  ...  and the semantic pre-processing of the natural language texts in Ukrainian for future training of term vector space models.  ...  For example, if your goal is to build a sentiment lexicon, then using a dataset from the medical domain or even Wikipedia may not be effective.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.15407/pp2020.02-03.341">doi:10.15407/pp2020.02-03.341</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/swnscokdengateyd7u37xb4yue">fatcat:swnscokdengateyd7u37xb4yue</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201209054827/http://pp.isofts.kiev.ua/ojs1/article/download/426/429" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/17/96/1796cb92bb0a8852636f6b646527914ca18ec7a1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.15407/pp2020.02-03.341"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Biomedical word sense disambiguation with bidirectional long short-term memory and attention-based neural networks

Canlin Zhang, Daniel Biś, Xiuwen Liu, Zhe He
<span title="2019-12-02">2019</span> <i title="Springer (Biomed Central Ltd.)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/n5zrklrhlzhtdorf4rk4rmeo3i" style="color: black;">BMC Bioinformatics</a> </i> &nbsp;
of medical word senses.  ...  That is, we concatenate the embedding of the target ambiguous word to the max-pooled vector in the universal models, acting as a "hint".  ...  Acknowledgments We are grateful to the authors of [18] . This work is based on both our previous work [17] and the encoder self-attention model in [18] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s12859-019-3079-8">doi:10.1186/s12859-019-3079-8</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/31787096">pmid:31787096</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC6886160/">pmcid:PMC6886160</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/c7gpfqu5uzffvonrhs25gnuo54">fatcat:c7gpfqu5uzffvonrhs25gnuo54</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200209091634/https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-019-3079-8" 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/10/ec/10ec3561ac0150293eb3c463efc2ce6431ca5ae6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s12859-019-3079-8"> <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/PMC6886160" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Exploring the Privacy-Preserving Properties of Word Embeddings: Algorithmic Validation Study

Mohamed Abdalla, Moustafa Abdalla, Graeme Hirst, Frank Rudzicz
<span title="2020-07-15">2020</span> <i title="JMIR Publications Inc."> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/f42mlbuaivhxrblrv2cbukmx4i" style="color: black;">Journal of Medical Internet Research</a> </i> &nbsp;
a code not billed for that patient.  ...  We also found that the distance between the word vector representation of a patient's name and a diagnostic billing code is informative and differs significantly from the distance between the name and  ...  FR is supported by a Canadian Institute for Advanced Research Chair in Artificial Intelligence.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2196/18055">doi:10.2196/18055</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/32673230">pmid:32673230</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/g5lwci76lnfevh7r7p3nhkeaxi">fatcat:g5lwci76lnfevh7r7p3nhkeaxi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200916053252/https://www.jmir.org/2020/7/e18055/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 noreferrer" href="https://doi.org/10.2196/18055"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Identification of self-admitted technical debt using enhanced feature selection based on word embedding

Jernej Flisar, Vili Podgorelec
<span title="">2019</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
We developed a new SATD identification method, which takes advantage of a large corpus of unlabeled code comments, extracted from open source projects, to train a word embedding model.  ...  After applying feature selection, the pre-trained word embedding is used for discovering semantically similar features in source code comments to enhance the original feature set.  ...  For example, although being huge, the Wikipedia may not have great word exposure to particular aspects of legal doctrine, religious texts, or source code comments for that matter, so if an application  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2019.2933318">doi:10.1109/access.2019.2933318</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qoawusj2inb3noy23ypetfrfou">fatcat:qoawusj2inb3noy23ypetfrfou</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210429135659/https://ieeexplore.ieee.org/ielx7/6287639/8600701/08790690.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/59/fe/59fe9c5443d0ed636d63caa4b960dedf7049a282.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2019.2933318"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Can We Survive without Labelled Data in NLP? Transfer Learning for Open Information Extraction

Injy Sarhan, Marco Spruit
<span title="2020-08-20">2020</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/smrngspzhzce7dy6ofycrfxbim" style="color: black;">Applied Sciences</a> </i> &nbsp;
Various tasks in natural language processing (NLP) suffer from lack of labelled training data, which deep neural networks are hungry for.  ...  First, we studied how transferable these features are from one OIE domain to another, such as from a news domain to a bio-medical domain.  ...  As a further matter, KRAKEN is able to detect completeness and correctness of the extracted facts, thus increasing the quality of the extracted information.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/app10175758">doi:10.3390/app10175758</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cylkvqnzsrcxlf2nxs2k5gwozq">fatcat:cylkvqnzsrcxlf2nxs2k5gwozq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200821070651/https://res.mdpi.com/d_attachment/applsci/applsci-10-05758/article_deploy/applsci-10-05758.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/03/03/0303d400e161bef8d443d6e0e55285b0eeb801f3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/app10175758"> <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>

Web 2.0, Language Resources and standards to automatically build a multilingual Named Entity Lexicon

Antonio Toral, Sergio Ferrández, Monica Monachini, Rafael Muñoz
<span title="2011-06-18">2011</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/qiptgj2ubngu3hrrsrkbdvpchi" style="color: black;">Language Resources and Evaluation</a> </i> &nbsp;
We present a case study in which a set of LRs for different languages (WordNet for English and Spanish and Parole-Simple-Clips for Italian) are extended with Named Entities (NE) by exploiting Wikipedia  ...  Finally, in order to check the usefulness of the constructed resource, we apply it into a state-of-the-art Question Answering system and evaluate its impact; the NE lexicon improves the system's accuracy  ...  In fact, for that experiment we set the number of occurrences per article to 100 and found such a high number for all the articles of the evaluation set.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10579-011-9148-x">doi:10.1007/s10579-011-9148-x</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4mgqrfve2vdpxbxr2ms3gdyshu">fatcat:4mgqrfve2vdpxbxr2ms3gdyshu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170921210332/http://doras.dcu.ie/16466/1/Web_2.0%2C_Language_Resources_and_standards_to_automatically_build_a_multilingual_Named_Entity_Lexicon.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/e8/aa/e8aad41d2a1948009c10ced7f11326c34bd4ecf8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10579-011-9148-x"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 866 results