{"id":708,"date":"2013-11-27T12:07:34","date_gmt":"2013-11-27T17:07:34","guid":{"rendered":"http:\/\/haleyai.com\/wordpress\/?p=708"},"modified":"2018-07-14T17:19:15","modified_gmt":"2018-07-14T22:19:15","slug":"deep-parsing-vs-deep-learning","status":"publish","type":"post","link":"http:\/\/haleyai.com\/wordpress\/2013\/11\/27\/deep-parsing-vs-deep-learning\/","title":{"rendered":"Deep Parsing vs. Deep Learning"},"content":{"rendered":"<p>For those of us that enjoy the intersection of machine learning and natural language, including &#8220;deep learning&#8221;, which is all the rage, here is an interesting paper on generalizing vector space models of words to broader semantics of English by Jayant Krishnamurthy, a PhD student of Tom Mitchell at Carnegie Mellon University:<\/p>\n<ul>\n<li> <a href=\"http:\/\/www.aclweb.org\/anthology\/W\/W13\/W13-32.pdf#page=11\">Krishnamurthy, Jayant, and Tom M. Mitchell. &#8220;Vector Space Semantic Parsing: A Framework for Compositional Vector Space Models.&#8221; ACL 2013 (2013): 1.<\/a><\/li>\n<\/ul>\n<p>Essentially, the paper demonstrates how the features of high-precision lexicalized grammars allow machines to learn the compositional semantics of English.\u00a0 More specifically, the paper demonstrates learning of compositional semantics beyond the capabilities of recurrent neural networks (RNN).\u00a0 In summary, the paper suggests that deep parsing is better than deep learning for understanding the meaning of natural language.<\/p>\n<p>For more information and a different perspective, I recommend the following paper, too:<\/p>\n<div id=\"gs_cit0\">\n<ul>\n<li><a href=\"http:\/\/www.robotics.stanford.edu\/~ang\/papers\/emnlp12-SemanticCompositionalityRecursiveMatrixVectorSpaces.pdf\">Socher, Richard, et al. &#8220;Semantic compositionality through recursive matrix-vector spaces.&#8221; <em>Proceedings  of the 2012 Joint Conference on Empirical Methods in Natural Language  Processing and Computational Natural Language Learning<\/em>. Association for Computational Linguistics, 2012.<\/a><\/li>\n<\/ul>\n<\/div>\n<p>Note that the authors use Combinatory Categorial Grammar (CCG) while our work uses head-driven phrase structure grammar (HPSG), but this is a minor distinction.\u00a0 For example, compare the logical forms in the <a href=\"http:\/\/gmb.let.rug.nl\/about.php\">Groningen Meaning Bank<\/a> with the logic produced by the <a href=\"http:\/\/haleyai.com\/wordpress\/2013\/06\/06\/acquring-rich-logical-knowledge-from-text-semantic-technology-2013\/\">Linguist<\/a>.\u00a0 The former uses CCG to produce lambda calculus while the latter uses HPSG to produce predicate calculus (ignoring vagaries of under-specified representation which are useful for hypothetical reasoning and textual entailment).<\/p>\n","protected":false},"excerpt":{"rendered":"<p>For those of us that enjoy the intersection of machine learning and natural language, including &#8220;deep learning&#8221;, which is all the rage, here is an interesting paper on generalizing vector space models of words to broader semantics of English by Jayant Krishnamurthy, a PhD student of Tom Mitchell at Carnegie Mellon University: Krishnamurthy, Jayant, and &hellip; <\/p>\n<p class=\"link-more\"><a href=\"http:\/\/haleyai.com\/wordpress\/2013\/11\/27\/deep-parsing-vs-deep-learning\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Deep Parsing vs. Deep Learning&#8221;<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[14,16],"tags":[640,638,642,635,636,643,639,530,527,895,214,637,641,634,644],"class_list":["post-708","post","type-post","status-publish","format-standard","hentry","category-learning","category-natural-language","tag-ccg","tag-comibinatory-categorial-grammar","tag-compositional-semantics","tag-deep-learning","tag-deep-parsing","tag-groningen-meaning-bank","tag-head-driven-phrase-structure-grammar","tag-hpsg","tag-linguist","tag-machine-learning","tag-nlp","tag-recurrent-neural-network","tag-rnn","tag-tom-mitchell","tag-vector-space-models"],"_links":{"self":[{"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/posts\/708","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/comments?post=708"}],"version-history":[{"count":7,"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/posts\/708\/revisions"}],"predecessor-version":[{"id":1513,"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/posts\/708\/revisions\/1513"}],"wp:attachment":[{"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/media?parent=708"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/categories?post=708"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/haleyai.com\/wordpress\/wp-json\/wp\/v2\/tags?post=708"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}