Filters








2,021,806 Hits in 5.5 sec

On the Similarity of Task Contexts

Walid Maalej, Mathias Ellmann
<span title="">2015</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wvv27s77dvd5flktsj246kcxwu" style="color: black;">2015 IEEE/ACM 2nd International Workshop on Context for Software Development</a> </i> &nbsp;
Moreover, knowing similar tasks of other developers might also save coordination effort. This paper studies the concept of tasks similarity based on the similarity of task contexts.  ...  We define task context as set or vector of the artifacts used in the task and apply popular similarity measures to compare the sets or vectors corresponding to the tasks.  ...  In this paper, we study the concept of task similarity based on the similarity of the task contexts. The main idea is simple: two tasks are similar if "their most relevant artifacts" are similar.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/csd.2015.9">doi:10.1109/csd.2015.9</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icse/MaalejE15.html">dblp:conf/icse/MaalejE15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sxh3ltduujh6jnosexmhaxlkv4">fatcat:sxh3ltduujh6jnosexmhaxlkv4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200322123724/https://mast.informatik.uni-hamburg.de/wp-content/uploads/2015/02/CSD2015.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/e5/7e/e57e33a9b0e96f72bcf9a6303f68f5f717fdbe5d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/csd.2015.9"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Citius at SemEval-2017 Task 2: Cross-Lingual Similarity from Comparable Corpora and Dependency-Based Contexts

Pablo Gamallo
<span title="">2017</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/aa3ggf3tbjarfj2zylzuxxqvdi" style="color: black;">Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)</a> </i> &nbsp;
Even though the team participated in two subtasks, namely monolingual and crosslingual word similarity, the article is mainly focused on the cross-lingual subtask.  ...  This article describes the distributional strategy submitted by the Citius team to the SemEval 2017 Task 2.  ...  , Educación e Ordenación Universitaria (accreditation 2016-2019, ED431G/08) and the European Regional Development Fund (ERDF).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/s17-2034">doi:10.18653/v1/s17-2034</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/semeval/Gamallo17.html">dblp:conf/semeval/Gamallo17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/t2bml5rn75dqpibygfet67ky7a">fatcat:t2bml5rn75dqpibygfet67ky7a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190227113112/http://pdfs.semanticscholar.org/8e83/ab4acbe353a18b70d231668533554feeb4f2.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/8e/83/8e83ab4acbe353a18b70d231668533554feeb4f2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/s17-2034"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

AlexU-AUX-BERT at SemEval-2020 Task 3: Improving BERT Contextual Similarity Using Multiple Auxiliary Contexts

Somaia Mahmoud, Marwan Torki
<span title="">2020</span> <i title="International Committee for Computational Linguistics"> Proceedings of the Fourteenth Workshop on Semantic Evaluation </i> &nbsp; <span class="release-stage">unpublished</span>
This paper describes the system we built for SemEval-2020 task 3. That is predicting the scores of similarity for a pair of words within two different contexts.  ...  Our system is based on both BERT embeddings and WordNet. We simply use cosine similarity to find the closest synset of the target words.  ...  By using our technique, the score increased from 0.573 when we use the BERT embedding baseline to 0.723 when evaluated on SemEval dataset.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/2020.semeval-1.33">doi:10.18653/v1/2020.semeval-1.33</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sapkgg4rlzbs5l3ba44fsafpuu">fatcat:sapkgg4rlzbs5l3ba44fsafpuu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210815034518/https://aclanthology.org/2020.semeval-1.33.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/8f/4d/8f4d67edaa56646aaeb4f2ab280ac8afbe85c70b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/2020.semeval-1.33"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

BRUMS at SemEval-2020 Task 3: Contextualised Embeddings for Predicting the (Graded) Effect of Context in Word Similarity

Hansi Hettiarachchi, Tharindu Ranasinghe
<span title="">2020</span> <i title="International Committee for Computational Linguistics"> Proceedings of the Fourteenth Workshop on Semantic Evaluation </i> &nbsp; <span class="release-stage">unpublished</span>
This paper presents the team BRUMS submission to SemEval-2020 Task 3: Graded Word Similarity in Context.  ...  The system utilises state-of-the-art contextualised word embeddings, which have some task-specific adaptations, including stacked embeddings and average embeddings.  ...  the similarity of same word pair within two different contexts ( This task is more similar to the traditional task which evaluates the similarity of words based on their contexts ) As the evaluation data  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/2020.semeval-1.16">doi:10.18653/v1/2020.semeval-1.16</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/r5awrlguy5g57ik3472rcl3rva">fatcat:r5awrlguy5g57ik3472rcl3rva</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210816020225/https://aclanthology.org/2020.semeval-1.16.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/62/d0/62d05c54fc325d2f45320ee153218ff8552301ab.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/2020.semeval-1.16"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Will_Go at SemEval-2020 Task 3: An Accurate Model for Predicting the (Graded) Effect of Context in Word Similarity Based on BERT

Wei Bao, Hongshu Che, Jiandong Zhang
<span title="">2020</span> <i title="International Committee for Computational Linguistics"> Proceedings of the Fourteenth Workshop on Semantic Evaluation </i> &nbsp; <span class="release-stage">unpublished</span>
Our paper mainly discusses a methodology to analyze the effect that context has on human perception of similar words, which is the third task of SemEval 2020.  ...  Our team will go won the 1st place in Finnish language track of subtask1, the second place in English track of subtask1.  ...  We approach this task as one of tasks that calculates the similarity between two words. In our model, context data would be firstly added into BERT like the following Figure 2 .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/2020.semeval-1.38">doi:10.18653/v1/2020.semeval-1.38</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vn5jsez55bgt3ab7easewxnusm">fatcat:vn5jsez55bgt3ab7easewxnusm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210816000743/https://aclanthology.org/2020.semeval-1.38.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/49/2b/492b48215cb850ff756c1f4c13c735588fbbe977.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/2020.semeval-1.38"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

JUSTMasters at SemEval-2020 Task 3: Multilingual Deep Learning Model to Predict the Effect of Context in Word Similarity

Nour Al-khdour, Mutaz Bni Younes, Malak Abdullah, Mohammad AL-Smadi
<span title="">2020</span> <i title="International Committee for Computational Linguistics"> Proceedings of the Fourteenth Workshop on Semantic Evaluation </i> &nbsp; <span class="release-stage">unpublished</span>
The SemEval-2020 workshop has provided a shared task (Task 3: Predicting the (Graded) Effect of Context in Word Similarity).  ...  Therefore, this paper investigates the effect of the context in word similarity.  ...  Task 3 in SemEval 2020 (Armendariz et al., 2020a) is about finding the context effect on word meanings by giving two similar words in a different context.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/2020.semeval-1.37">doi:10.18653/v1/2020.semeval-1.37</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cjzrtf4csjcrni6kggi5ncvy3q">fatcat:cjzrtf4csjcrni6kggi5ncvy3q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210815233246/https://aclanthology.org/2020.semeval-1.37.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/41/38/41388a7961f0c7fd4bc18b61dffe1f334228d1f6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/2020.semeval-1.37"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Ferryman at SemEval-2020 Task 3: Bert with TFIDF-Weighting for Predicting the Effect of Context in Word Similarity

Weilong Chen, Xin Yuan, Sai Zhang, Jiehui Wu, Yanru Zhang, Yan Wang
<span title="">2020</span> <i title="International Committee for Computational Linguistics"> Proceedings of the Fourteenth Workshop on Semantic Evaluation </i> &nbsp; <span class="release-stage">unpublished</span>
Our team Ferryman wins the the first position for English task and the second position for Finnish in the subtask 1. * All the corresponding to Yan Wang.  ...  Our system is based on the Bidirectional Encoder Representations from Transformers (BERT) model combined with term frequency-inverse document frequency (TF-IDF), applying the method on the provided datasets  ...  CoSimLex is built on the familiar pairwise, graded similarity task of SimLex-999, and provides similarity measures dependent on context.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/2020.semeval-1.35">doi:10.18653/v1/2020.semeval-1.35</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jdzpcfm24vgcbipwfrfercztdm">fatcat:jdzpcfm24vgcbipwfrfercztdm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210816024145/https://aclanthology.org/2020.semeval-1.35.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/45/e8/45e892c3238dd4d2a9edfdbb5107b85cdc791c70.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/2020.semeval-1.35"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Exploiting Language Model Prompts Using Similarity Measures: A Case Study on the Word-in-Context Task

Mohsen Tabasi, Kiamehr Rezaee, Mohammad Taher Pilehvar
<span title="">2022</span> <i title="Association for Computational Linguistics"> Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) </i> &nbsp; <span class="release-stage">unpublished</span>
However, despite proving competitive on most tasks in the GLUE and SuperGLUE benchmarks, existing prompt-based techniques fail on the semantic distinction task of the Word-in-Context (WiC) dataset.  ...  Trying to fill this gap, we propose a new prompting technique, based on similarity metrics, which boosts few-shot performance to the level of fully supervised methods.  ...  However, surprisingly, the Word-in-Context task (Pilehvar and Camacho-Collados, 2019) -one of the tasks in the SuperGLUE benchmark )-is one exception on which these methods fail to stay on par with their  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/2022.acl-short.36">doi:10.18653/v1/2022.acl-short.36</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2x4jdfiwxzaopmepac3i4znloe">fatcat:2x4jdfiwxzaopmepac3i4znloe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220516055649/https://aclanthology.org/2022.acl-short.36.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/0a/0e/0a0e48c469b124c9a03d4bc841311f59424e97f2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/2022.acl-short.36"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Towards context-aware task recommendation

Chuong Cong Vo, Torab Torabi, Seng W. Loke
<span title="">2009</span> <i title="IEEE"> 2009 Joint Conferences on Pervasive Computing (JCPC) </i> &nbsp;
This paper formalises the problem of task recommendation, presents a system architecture for TASKREC, and an early prototype implementation.  ...  Finally, we suggest open opportunities for future research on adaptation techniques for context-aware systems.  ...  Furthermore, the conflicts of recommendations in multiuser environments bring up challenges that we are also aware of.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/jcpc.2009.5420173">doi:10.1109/jcpc.2009.5420173</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/67smdvjchzh6nm7kr3cjr6nlby">fatcat:67smdvjchzh6nm7kr3cjr6nlby</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20110301130150/http://homepage.cs.latrobe.edu.au/sloke/papers/ChuongICPCA2009-4pages.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/77/93/779366d841f19f059433740329017608f60ec44a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/jcpc.2009.5420173"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Leveraging medical context to recommend semantically similar terms for chart reviews

Cheng Ye, Bradley A. Malin, Daniel Fabbri
<span title="2021-12-18">2021</span> <i title="Springer Science and Business Media LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/bnylrk2y7bfnrn7u2f2vjkx7ta" style="color: black;">BMC Medical Informatics and Decision Making</a> </i> &nbsp;
Conclusions The set of preferred similar terms that are relevant to a chart review task can be learned by leveraging the medical context of the task.  ...  In this study, we present new methods that provide similar terms dynamically by adjusting with the context of the chart review task.  ...  Acknowledgements The data for this study was based on the VUMC data repositories, which are supported by institutional funding and by the Vanderbilt CTSA Grant ULTR000445 from NCATS/NIH.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s12911-021-01724-2">doi:10.1186/s12911-021-01724-2</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/34922536">pmid:34922536</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC8684266/">pmcid:PMC8684266</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/d75mir6euvh3hey3fgqqxsgy6i">fatcat:d75mir6euvh3hey3fgqqxsgy6i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220131202533/https://bmcmedinformdecismak.biomedcentral.com/track/pdf/10.1186/s12911-021-01724-2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/07/67/0767eb5ab61d25920bc4046b3baab6ee5c6d5cfa.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s12911-021-01724-2"> <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/PMC8684266" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

An analysis of context-based similarity tasks in textbooks from Brazil and the United States

Rúbia Barcelos Amaral, Karen Hollebrands
<span title="2017-05-24">2017</span> <i title="Informa UK Limited"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/hu2vpvocijectbmjgcbjyp35bq" style="color: black;">International Journal of Mathematical Education in Science and Technology</a> </i> &nbsp;
Although books in the United States included more tasks, the proportion of tasks focused on similarity were about the same.  ...  Context-based similarity tasks accounted for 9%-29% of the similarity tasks, and many of these contextual tasks were of low cognitive demand.  ...  Disclosure statement No potential conflict of interest was reported by the authors. Funding This study was supported by Coordenação de Aperfeiçoamento de Pessoal de Nível Superior.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1080/0020739x.2017.1315188">doi:10.1080/0020739x.2017.1315188</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lkdlbbpecvdvhhofd4rml4fzky">fatcat:lkdlbbpecvdvhhofd4rml4fzky</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200312175733/https://repositorio.unesp.br/bitstream/handle/11449/169749/2-s2.0-85019602945.pdf;jsessionid=C714733400395FAA46E5D3EB1FC656C6?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/95/c7/95c7ad7dbf1fed5dcb5d069034e36b80429e7515.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1080/0020739x.2017.1315188"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> tandfonline.com </button> </a>

Recommending a starting point for a programming task: an initial investigation

C. Albert Thompson, Gail C. Murphy
<span title="">2014</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wvv27s77dvd5flktsj246kcxwu" style="color: black;">Proceedings of the 4th International Workshop on Recommendation Systems for Software Engineering - RSSE 2014</a> </i> &nbsp;
In this paper, we consider how we might recommend one resource as an initial starting point, saving the developer the effort of having to search or use other means to find the point.  ...  When starting a new task, a software developer must typically find one or more starting points amongst many resources (e.g., source code and other files) forming the software system.  ...  ACKNOWLEDGMENTS This work was funded in part by IBM and in part by NSERC through the NECSIS project.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2593822.2593824">doi:10.1145/2593822.2593824</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icse/ThompsonM14.html">dblp:conf/icse/ThompsonM14</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/x5n75gxk7vgehbm5trzzxy3aym">fatcat:x5n75gxk7vgehbm5trzzxy3aym</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20150314045132/http://c.albert-thompson.com:80/papers/files/rsse14.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/16/1c/161c57dc13817bf18787060e4501c32de6dc14b6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2593822.2593824"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Investigating Different Syntactic Context Types and Context Representations for Learning Word Embeddings

Bofang Li, Tao Liu, Zhe Zhao, Buzhou Tang, Aleksandr Drozd, Anna Rogers, Xiaoyong Du
<span title="">2017</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/u3ideoxy4fghvbsstiknuweth4" style="color: black;">Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</a> </i> &nbsp;
The number of word embedding models is growing every year. Most of them are based on the co-occurrence information of words and their contexts.  ...  However, it is still an open question what is the best definition of context.  ...  Their work systematically investigated the effects of different hyper-parameters on various word embedding models, which directly influenced us a lot. This work is supported by National  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/d17-1257">doi:10.18653/v1/d17-1257</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/emnlp/LiLZTDRD17.html">dblp:conf/emnlp/LiLZTDRD17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/u2qrr7ygynetbacas5kfxvyjcy">fatcat:u2qrr7ygynetbacas5kfxvyjcy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200305083535/https://www.aclweb.org/anthology/D17-1257.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/71/a0/71a0b59b16d834f457d13457665b5bc47a5ebc15.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/d17-1257"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

The Role of Context Types and Dimensionality in Learning Word Embeddings [article]

Oren Melamud, David McClosky, Siddharth Patwardhan, Mohit Bansal
<span title="2017-07-19">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We provide the first extensive evaluation of how using different types of context to learn skip-gram word embeddings affects performance on a wide range of intrinsic and extrinsic NLP tasks.  ...  for most of the extrinsic tasks that we considered.  ...  Acknowledgments We thank Do Kook Choe for providing us the jackknifed version of WSJ. We also wish to thank the IBM Watson team for helpful discussions and our anonymous reviewers for their comments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1601.00893v2">arXiv:1601.00893v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ecxmyhmv5fbhjiczaqlugyj3im">fatcat:ecxmyhmv5fbhjiczaqlugyj3im</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200928195330/https://arxiv.org/pdf/1601.00893v2.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/53/05/5305b40d39d682854e4daa350e7619dacfd887ea.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1601.00893v2" 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>

Tempo-Lexical Context Driven Word Embedding for Cross-Session Search Task Extraction

Procheta Sen, Debasis Ganguly, Gareth Jones
<span title="">2018</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/d5ex6ucxtrfz3clshlkh3f6w2q" style="color: black;">Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)</a> </i> &nbsp;
Most existing research on search task extraction has focused on identifying tasks within a single session, where the notion of a session is defined by a fixed length time window.  ...  leveraging the temporal and templexical contexts of queries.  ...  Acknowledgement This work was supported by Science Foundation Ireland as part of the ADAPT Centre (Grant No. 13/RC/2106) (www.adaptcentre.ie).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/n18-1026">doi:10.18653/v1/n18-1026</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/naacl/SenGJ18.html">dblp:conf/naacl/SenGJ18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/52tzitqxija6pfil52mrokq7de">fatcat:52tzitqxija6pfil52mrokq7de</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200309050800/https://www.aclweb.org/anthology/N18-1026.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/f3/03/f303f7f7189dce018eed01dcd53655e026775c0f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/n18-1026"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 2,021,806 results