{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T17:38:25Z","timestamp":1719941905821},"reference-count":70,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Speech & Language"],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.1016\/j.csl.2019.03.006","type":"journal-article","created":{"date-parts":[[2019,3,28]],"date-time":"2019-03-28T06:58:22Z","timestamp":1553756302000},"page":"51-75","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Making sense of kernel spaces in neural learning"],"prefix":"10.1016","volume":"58","author":[{"given":"D.","family":"Croce","sequence":"first","affiliation":[]},{"given":"S.","family":"Filice","sequence":"additional","affiliation":[]},{"given":"R.","family":"Basili","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.csl.2019.03.006_bib0001","series-title":"Proceedings of the SemEval@NAACL-HLT","first-page":"497","article-title":"Semeval-2016 task 1: semantic textual similarity, monolingual and cross-lingual evaluation","author":"Agirre","year":"2016"},{"key":"10.1016\/j.csl.2019.03.006_bib0002","series-title":"Proceedings of the CIKM","article-title":"Semantic compositionality in tree kernels","author":"Annesi","year":"2014"},{"issue":"7","key":"10.1016\/j.csl.2019.03.006_bib0003","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pone.0130140","article-title":"On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation","volume":"10","author":"Bach","year":"2015","journal-title":"PLoS ONE"},{"key":"10.1016\/j.csl.2019.03.006_sbref0004","series-title":"Proceedings of the COLING-ACL","article-title":"The Berkeley FrameNet project","author":"Baker","year":"1998"},{"key":"10.1016\/j.csl.2019.03.006_bib0005","series-title":"Proceedings of the Twentieth Italian Workshop on Neural Nets","article-title":"Bridging the gap between neural network and kernel methods: applications to drug discovery","author":"Baldi","year":"2011"},{"key":"10.1016\/j.csl.2019.03.006_bib0006","series-title":"Proceedings of the SemEval-2016","article-title":"ConvKN at SemEval-2016 task 3: answer and question selection for question answering on arabic and english fora","author":"Barr\u00f3n-Cede\u00f1o","year":"2016"},{"issue":"8","key":"10.1016\/j.csl.2019.03.006_bib0007","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","article-title":"Representation learning: a review and new perspectives","volume":"35","author":"Bengio","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.csl.2019.03.006_bib0008","series-title":"Proceedings of the Tenth International Workshop on Semantic Evaluation (SemEval-2016)","first-page":"588","article-title":"Uwb at semeval-2016 task 1: semantic textual similarity using lexical, syntactic, and semantic information","author":"Brychc\u00edn","year":"2016"},{"key":"10.1016\/j.csl.2019.03.006_bib0009","first-page":"1059","article-title":"Word-sequence kernels","volume":"3","author":"Cancedda","year":"2003","journal-title":"J Mach Learn Res"},{"issue":"1","key":"10.1016\/j.csl.2019.03.006_bib0010","first-page":"1","article-title":"Complex question answering: Unsupervised learning approaches and experiments","volume":"35","author":"Chali","year":"2009","journal-title":"J Artif Intell Res (JAIR)"},{"issue":"3","key":"10.1016\/j.csl.2019.03.006_bib0011","doi-asserted-by":"crossref","first-page":"27:1","DOI":"10.1145\/1961189.1961199","article-title":"Libsvm: A library for support vector machines","volume":"2","author":"Chang","year":"2011","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"10.1016\/j.csl.2019.03.006_bib0012","series-title":"Proceedings of the Advances in Neural Information Processing Systems 22","first-page":"342","article-title":"Kernel methods for deep learning","author":"Cho","year":"2009"},{"key":"10.1016\/j.csl.2019.03.006_bib0013","series-title":"Proceedings of the Neural Information Processing Systems (NIPS\u20192001)","first-page":"625","article-title":"Convolution kernels for natural language","author":"Collins","year":"2001"},{"key":"10.1016\/j.csl.2019.03.006_bib0014","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"12","author":"Collobert","year":"2011","journal-title":"J Mach Learn Res (JAIR)"},{"issue":"3","key":"10.1016\/j.csl.2019.03.006_bib0015","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn"},{"key":"10.1016\/j.csl.2019.03.006_bib0016","series-title":"Proceedings of the ECIR 2016","article-title":"Large-scale kernel-based language learning through the ensemble Nystrom methods","author":"Croce","year":"2016"},{"key":"10.1016\/j.csl.2019.03.006_bib0017","series-title":"Proceedings of the Fifty-Fifth Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"345","article-title":"Deep learning in semantic kernel spaces","author":"Croce","year":"2017"},{"key":"10.1016\/j.csl.2019.03.006_bib0018","series-title":"Proceedings of the EMNLP \u201911","first-page":"1034","article-title":"Structured lexical similarity via convolution kernels on dependency trees","author":"Croce","year":"2011"},{"key":"10.1016\/j.csl.2019.03.006_sbref0019","series-title":"Proceedings of the Workshop: Analyzing and Interpreting Neural Networks for NLP, BlackboxNLP@EMNLP 2018","first-page":"16","article-title":"Explaining non-linear classifier decisions within kernel-based deep architectures","author":"Croce","year":"2018"},{"key":"10.1016\/j.csl.2019.03.006_bib0020","series-title":"Proceedings of the NIPS","first-page":"345","article-title":"Support vector machines on a budget","author":"Dekel","year":"2006"},{"key":"10.1016\/j.csl.2019.03.006_bib0021","first-page":"2153","article-title":"On the nystr\u00f6m method for approximating a gram matrix for improved kernel-based learning","volume":"6","author":"Drineas","year":"2005","journal-title":"J Mach Learn Res"},{"key":"10.1016\/j.csl.2019.03.006_bib0022","series-title":"Technical Report 1355","article-title":"Understanding Representations Learned in Deep Architectures","author":"Erhan","year":"2010"},{"key":"10.1016\/j.csl.2019.03.006_sbref0023","series-title":"Proceedings of the ACL: System Demonstrations","article-title":"KeLP: a kernel-based learning platform for natural language processing","author":"Filice","year":"2015"},{"issue":"191","key":"10.1016\/j.csl.2019.03.006_bib0024","first-page":"1","article-title":"Kelp: a kernel-based learning platform","volume":"18","author":"Filice","year":"2018","journal-title":"J Mach Learn Res"},{"key":"10.1016\/j.csl.2019.03.006_bib0025","series-title":"Proceedings of the SemEval \u201916","article-title":"KeLP at SemEval-2016 task 3: learning semantic relations between questions and comments","author":"Filice","year":"2016"},{"key":"10.1016\/j.csl.2019.03.006_bib0026","series-title":"Proceedings of the ACL 2015. Beijing, China","first-page":"1003","article-title":"Structural representations for learning relations between pairs of texts","author":"Filice","year":"2015"},{"issue":"2","key":"10.1016\/j.csl.2019.03.006_bib0027","first-page":"222","article-title":"Frames and the semantics of understanding","volume":"6","author":"Fillmore","year":"1985","journal-title":"Quaderni di Semantica"},{"key":"10.1016\/j.csl.2019.03.006_bib0028","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1613\/jair.4992","article-title":"A primer on neural network models for natural language processing","volume":"57","author":"Goldberg","year":"2016","journal-title":"J Artif Intell Res (JAIR)"},{"key":"10.1016\/j.csl.2019.03.006_bib0029","series-title":"The Philosophy of Linguistics","article-title":"Distributional structure","author":"Harris","year":"1964"},{"issue":"8","key":"10.1016\/j.csl.2019.03.006_bib0030","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"10.1016\/j.csl.2019.03.006_bib0031","series-title":"Proceedings of the ICML 2008","first-page":"408","article-title":"A dual coordinate descent method for large-scale linear SVM","author":"Hsieh","year":"2008"},{"key":"10.1016\/j.csl.2019.03.006_bib0032","series-title":"Proceedings of the COLING","article-title":"The effect of syntactic representation on semantic role labeling","author":"Johansson","year":"2008"},{"issue":"1","key":"10.1016\/j.csl.2019.03.006_bib0033","first-page":"1","article-title":"Using local alignments for relation recognition","volume":"38","author":"Katrenko","year":"2010","journal-title":"J Artif Intell Res (JAIR)"},{"key":"10.1016\/j.csl.2019.03.006_bib0034","series-title":"Proceedings of the EMNLP 2014. Doha, Qatar","first-page":"1746","article-title":"Convolutional neural networks for sentence classification","author":"Kim","year":"2014"},{"key":"10.1016\/j.csl.2019.03.006_bib0035","series-title":"Proceedings of the ICML","first-page":"457","article-title":"Semi-supervised graph clustering: a kernel approach","author":"Kulis","year":"2005"},{"key":"10.1016\/j.csl.2019.03.006_bib0036","first-page":"981","article-title":"Sampling methods for the Nystr\u00f6m method","volume":"13","author":"Kumar","year":"2012","journal-title":"J Mach Learn Res"},{"issue":"11","key":"10.1016\/j.csl.2019.03.006_bib0037","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc IEEE"},{"key":"10.1016\/j.csl.2019.03.006_bib0038","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1162\/tacl_a_00134","article-title":"Improving distributional similarity with lessons learned from word embeddings","volume":"3","author":"Levy","year":"2015","journal-title":"Trans. Assoc. Comput Linguist"},{"issue":"3","key":"10.1016\/j.csl.2019.03.006_bib0039","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1017\/S1351324905003955","article-title":"Learning question classifiers: the role of semantic information","volume":"12","author":"Li","year":"2006","journal-title":"Natural Lang Eng"},{"key":"10.1016\/j.csl.2019.03.006_bib0040","series-title":"Proceedings of the Advances in Neural Information Processing Systems","article-title":"Convolutional kernel networks","author":"Mairal","year":"2014"},{"key":"10.1016\/j.csl.2019.03.006_bib0041","article-title":"Efficient estimation of word representations in vector space","volume":"abs\/1301.3781","author":"Mikolov","year":"2013","journal-title":"CoRR"},{"issue":"8","key":"10.1016\/j.csl.2019.03.006_bib0042","doi-asserted-by":"crossref","first-page":"1388","DOI":"10.1111\/j.1551-6709.2010.01106.x","article-title":"Composition in distributional models of semantics","volume":"34","author":"Mitchell","year":"2010","journal-title":"Cognit Sci"},{"key":"10.1016\/j.csl.2019.03.006_sbref0043","series-title":"Proceedings of the ECML","article-title":"Efficient convolution kernels for dependency and constituent syntactic trees","author":"Moschitti","year":"2006"},{"key":"10.1016\/j.csl.2019.03.006_bib0044","series-title":"Proceedings of the ACL (Tutorial Abstracts)","first-page":"2","article-title":"State-of-the-art kernels for natural language processing","author":"Moschitti","year":"2012"},{"key":"10.1016\/j.csl.2019.03.006_bib0045","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1162\/coli.2008.34.2.193","article-title":"Tree kernels for semantic role labeling","volume":"34","author":"Moschitti","year":"2008","journal-title":"Comput Linguist"},{"issue":"2","key":"10.1016\/j.csl.2019.03.006_bib0046","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1109\/72.914517","article-title":"An introduction to kernel-based learning algorithms","volume":"12","author":"Robert M\u00fcller","year":"2001","journal-title":"IEEE Trans Neural Netw"},{"key":"10.1016\/j.csl.2019.03.006_bib0047","series-title":"Proceedings of the SemEval-2016","article-title":"SemEval-2016 task 3: community question answering","author":"Nakov","year":"2016"},{"issue":"2","key":"10.1016\/j.csl.2019.03.006_bib0048","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1162\/coli.2007.33.2.161","article-title":"Dependency-based construction of semantic space models","volume":"33","author":"Pado","year":"2007","journal-title":"Comput Linguist"},{"key":"10.1016\/j.csl.2019.03.006_bib0049","series-title":"Proceedings of the Advances in Neural Information Processing Systems 20","first-page":"1177","article-title":"Random features for large-scale kernel machines","author":"Rahimi","year":"2008"},{"key":"10.1016\/j.csl.2019.03.006_bib0050","series-title":"Proceedings of the Tenth International Workshop on Semantic Evaluation (SemEval-2016). San Diego, California","first-page":"614","article-title":"Samsung Poland NLP team at SemEval-2016 task 1: necessity for diversity; combining recursive Autoencoders, Wordnet and ensemble methods to measure semantic similarity","author":"Rychalska","year":"2016"},{"key":"10.1016\/j.csl.2019.03.006_bib0051","series-title":"The Word-Space Model (Ph.D. thesis.)","author":"Sahlgren","year":"2006"},{"issue":"5","key":"10.1016\/j.csl.2019.03.006_bib0052","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1162\/089976698300017467","article-title":"Nonlinear component analysis as a kernel eigenvalue problem","volume":"10","author":"Sch\u00f6lkopf","year":"1998","journal-title":"Neural Comput"},{"key":"10.1016\/j.csl.2019.03.006_sbref0053","series-title":"Proceedings of the Twenty-Second ACM International Conference on Information and Knowledge Management, CIKM\u201913","first-page":"969","article-title":"Building structures from classifiers for passage reranking","author":"Severyn","year":"2013"},{"key":"10.1016\/j.csl.2019.03.006_bib0054","series-title":"Kernel Methods for Pattern Analysis","author":"Shawe-Taylor","year":"2004"},{"key":"10.1016\/j.csl.2019.03.006_bib0055","unstructured":"Simonyan, K., Vedaldi, A., Zisserman, A., 2013. Deep inside convolutional networks: visualising image classification models and saliency maps. CoRRarXiv:1312.6034."},{"key":"10.1016\/j.csl.2019.03.006_bib0056","series-title":"Proceedings of the EMNLP \u201913","article-title":"Recursive deep models for semantic Compositionality over a sentiment treebank","author":"Socher","year":"2013"},{"key":"10.1016\/j.csl.2019.03.006_bib0057","series-title":"Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","first-page":"1556","article-title":"Improved semantic representations from tree-structured long short-term memory networks","author":"Tai","year":"2015"},{"key":"10.1016\/j.csl.2019.03.006_bib0058","series-title":"Proceedings of the Forty-Eighth Annual Meeting of the Association for Computational Linguistics. Uppsala, Sweden","first-page":"384","article-title":"Word representations: a simple and general method for semi-supervised learning","author":"Turian","year":"2010"},{"key":"10.1016\/j.csl.2019.03.006_bib0059","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1613\/jair.2934","article-title":"From frequency to meaning: vector space models of semantics","volume":"37","author":"Turney","year":"2010","journal-title":"J Artif Intell Res"},{"key":"10.1016\/j.csl.2019.03.006_bib0060","series-title":"Proceedings of the NAACL 2016","article-title":"Convolutional neural networks vs. convolution kernels: feature engineering for answer sentence reranking","author":"Tymoshenko","year":"2016"},{"key":"10.1016\/j.csl.2019.03.006_bib0061","series-title":"Statistical Learning Theory","author":"Vapnik","year":"1998"},{"key":"10.1016\/j.csl.2019.03.006_bib0062","series-title":"Proceedings of the Neural Information Processing Systems","first-page":"569","article-title":"Fast kernels on strings and trees","author":"Vishwanathan","year":"2002"},{"key":"10.1016\/j.csl.2019.03.006_bib0063","first-page":"908","article-title":"Online passive-aggressive algorithms on a budget","volume":"9","author":"Wang","year":"2010","journal-title":"J Mach Learn Res Proc Track"},{"key":"10.1016\/j.csl.2019.03.006_bib0064","series-title":"Proceedings of the NIPS 2000","article-title":"Using the Nystr\u00f6m method to speed up kernel machines","author":"Williams","year":"2001"},{"key":"10.1016\/j.csl.2019.03.006_bib0065","series-title":"Proceedings of the Advances in Neural Information Processing Systems 21","first-page":"1889","article-title":"Deep learning with kernel regularization for visual recognition","author":"Yu","year":"2009"},{"key":"10.1016\/j.csl.2019.03.006_bib0066","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1017\/S1351324909990143","article-title":"A machine learning approach to textual entailment recognition","volume":"15-04","author":"Zanzotto","year":"2009","journal-title":"Nat Lang Eng"},{"key":"10.1016\/j.csl.2019.03.006_bib0067","unstructured":"Zeiler, M. D., Fergus, R., 2013. Visualizing and understanding convolutional networks. CoR, abs:1311.2901."},{"key":"10.1016\/j.csl.2019.03.006_bib0068","series-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"1512","article-title":"Dependency sensitive convolutional neural networks for modeling sentences and documents","author":"Zhang","year":"2016"},{"key":"10.1016\/j.csl.2019.03.006_bib0069","unstructured":"Zhou, C., Sun, C., Liu, Z., Lau, F. C. M., 2015. A C-LSTM neural network for text classification. CoRR, abs:1511.08630."},{"key":"10.1016\/j.csl.2019.03.006_bib0070","series-title":"Proceedings of the AISTATS","first-page":"909","article-title":"Two-layer multiple kernel learning","author":"Zhuang","year":"2011"}],"container-title":["Computer Speech & Language"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230818301244?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230818301244?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,8,20]],"date-time":"2019-08-20T14:41:14Z","timestamp":1566312074000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0885230818301244"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":70,"alternative-id":["S0885230818301244"],"URL":"https:\/\/doi.org\/10.1016\/j.csl.2019.03.006","relation":{},"ISSN":["0885-2308"],"issn-type":[{"value":"0885-2308","type":"print"}],"subject":[],"published":{"date-parts":[[2019,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Making sense of kernel spaces in neural learning","name":"articletitle","label":"Article Title"},{"value":"Computer Speech & Language","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.csl.2019.03.006","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2019 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}]}}