{"id":561,"date":"2017-07-19T13:20:17","date_gmt":"2017-07-19T13:20:17","guid":{"rendered":"http:\/\/uscictdialdev.wpenginepowered.com\/?page_id=561"},"modified":"2017-07-19T13:20:17","modified_gmt":"2017-07-19T13:20:17","slug":"bllip-parser","status":"publish","type":"page","link":"https:\/\/dialport.ict.usc.edu\/index.php\/resources\/parsers\/bllip-parser\/","title":{"rendered":"BLLIP Parser"},"content":{"rendered":"<p><a href=\"https:\/\/github.com\/BLLIP\/bllip-parser\">Github<\/a><\/p>\n<p>&nbsp;<\/p>\n<p>There are several available parsing models for BLLIP Parser. This document is designed to help you determine which one will perform best for your task. Each one of the parsing models discussed includes a pair of Charniak parser and Johnson reranker models designed to work together (this is called a\u00a0<code>unified parsing model<\/code>).<\/p>\n<p>&nbsp;<\/p>\n<p>Depending on the text that you&#8217;d like to parse, there are different optimal parsing models. Here are the current recommendations:<\/p>\n<ul>\n<li><strong>News text:<\/strong>\u00a0<code>WSJ+Gigaword-v2<\/code><\/li>\n<li><strong>Web text:<\/strong>\u00a0<code>SANCL2012-Uniform<\/code><\/li>\n<li><strong>Biomedical (PubMed) text:<\/strong>\u00a0<code>GENIA+PubMed<\/code><\/li>\n<li><strong>WSJ section 23 evaluations to replicate papers:<\/strong>\u00a0For purely supervised parser or parser\/reranker results, use either\u00a0<code>WSJ-PTB3<\/code>\u00a0(for Penn Treebank WSJ) or\u00a0<code>OntoNotes-WSJ<\/code>\u00a0(for the OntoNotes version of WSJ). Use\u00a0<code>WSJ+Gigaword<\/code>\u00a0to replicate self-training results, though\u00a0<code>WSJ+Gigaword-v2<\/code>\u00a0performs slightly better.<\/li>\n<li><strong>Everything else:<\/strong>\u00a0In general, it&#8217;s probably best to use\u00a0<code>SANCL2012-Uniform<\/code>\u00a0or\u00a0<code>WSJ+Gigaword-v2<\/code>\u00a0depending on how well-formed your text is (<code>SANCL2012-Uniform<\/code>\u00a0for more informal web\/email text).<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Github &nbsp; There are several available parsing models for BLLIP Parser. This document is designed to help you determine which one will perform best for your task. Each one of the parsing models discussed includes a pair of Charniak parser and Johnson reranker models designed to work together (this is called a\u00a0unified parsing model). &nbsp; [&hellip;]<\/p>\n","protected":false},"author":18,"featured_media":0,"parent":74,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-561","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/pages\/561","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\/18"}],"replies":[{"embeddable":true,"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/comments?post=561"}],"version-history":[{"count":0,"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/pages\/561\/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=561"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}