{"id":236,"date":"2016-06-28T16:34:03","date_gmt":"2016-06-28T16:34:03","guid":{"rendered":"http:\/\/uscictdialdev.wpenginepowered.com\/?page_id=236"},"modified":"2017-07-19T13:28:01","modified_gmt":"2017-07-19T13:28:01","slug":"easysrl","status":"publish","type":"page","link":"https:\/\/dialport.ict.usc.edu\/index.php\/resources\/parsers\/easysrl\/","title":{"rendered":"EasySRL"},"content":{"rendered":"<p><strong><a class=\"ext-link\" href=\"https:\/\/github.com\/mikelewis0\/EasySRL\">EasySRL<\/a><\/strong> a java neural network CCG parser. Generates a logical form for a given utterance.<\/p>\n<p>EasySRL builds logical forms for natural language sentences, by jointly modelling CCG and semantic role labelling. It uses an efficient A* parsing algorithm, meaning it can be used to process large corpora. A demo is online here:<a href=\"http:\/\/lil.cs.washington.edu\/easysrl\/demo.cgi\">http:\/\/lil.cs.washington.edu\/easysrl\/demo.cgi<\/a><\/p>\n<p>If you use the parser for research, please cite the following paper:<\/p>\n<p>@inproceedings{lewis:2015, title={Joint A* CCG Parsing and Semantic Role Labelling}, author={Lewis, Mike and He, Luheng and Zettlemoyer, Luke}, booktitle={Empirical Methods in Natural Language Processing}, year={2015} }<\/p>\n<p>A pretrained model is available here: <a href=\"https:\/\/drive.google.com\/file\/d\/0B7AY6PGZ8lc-R1E3aTA5WG54bWM\/view?usp=sharing\">https:\/\/drive.google.com\/file\/d\/0B7AY6PGZ8lc-R1E3aTA5WG54bWM\/view?usp=sharing<\/a><\/p>\n<p>If parsing questions, use this model instead: <a href=\"https:\/\/drive.google.com\/file\/d\/0B7AY6PGZ8lc-bVZXSTM0RWlrVTg\/view?usp=sharing\">https:\/\/drive.google.com\/file\/d\/0B7AY6PGZ8lc-bVZXSTM0RWlrVTg\/view?usp=sharing<\/a><\/p>\n<p>Basic usage: java -jar easysrl.jar &#8211;model modelFolder<\/p>\n<p>For CCG syntactic output, use: java -jar easysrl.jar &#8211;model modelFolder &#8211;outputFormat ccgbank<\/p>\n<p>For semantic role labelling output, use: java -jar easysrl.jar &#8211;model modelFolder &#8211;outputFormat srl<\/p>\n<p>To get n-best parses: java -jar easysrl.jar &#8211;model modelFolder &#8211;nbest 10 &#8211;supertaggerbeam 0.001<\/p>\n<p>Please contact Mike Lewis with any questions or feature requests (email address in the paper).<\/p>\n","protected":false},"excerpt":{"rendered":"<p>EasySRL a java neural network CCG parser. Generates a logical form for a given utterance. EasySRL builds logical forms for natural language sentences, by jointly modelling CCG and semantic role labelling. It uses an efficient A* parsing algorithm, meaning it can be used to process large corpora. A demo is online here:http:\/\/lil.cs.washington.edu\/easysrl\/demo.cgi If you use [&hellip;]<\/p>\n","protected":false},"author":19,"featured_media":0,"parent":74,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-236","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/pages\/236","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/users\/19"}],"replies":[{"embeddable":true,"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/comments?post=236"}],"version-history":[{"count":0,"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/pages\/236\/revisions"}],"up":[{"embeddable":true,"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/pages\/74"}],"wp:attachment":[{"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/media?parent=236"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}