首页排名顶会必读论文热点开放数据VIP

AI帮你理解科学

AI 生成解读视频

AI抽取解析论文重点内容自动生成视频

pub
生成解读视频

AI 溯源

AI解析本论文相关学术脉络

Master Reading Tree
生成 溯源树

Context-Sensitive Statistics for Improved Grammatical Language Models

AAAI, pp.728-733, (1994)

引用：57|浏览30
EI
下载 PDF 全文
其它链接
dl.acm.orgdblp.uni-trier.deacademic.microsoft.com
引用
关键词
context-sensitive statisticpcfg inductionimproved grammatical language modelsoriginal pcfgyields significant performance gain更多(8+)

摘要

We develop a language model using probabilistic context-free grammars (PCFGs) that is ``pseudo context-sensitive'''' in that the probability that a non-terminal $N$ expands using a rule $r$ depends on $N
#x27;'s parent. We derive the equations for estimating the necessary probabilities using a variant of the inside-outside algorithm. We give ...更多

代码：

数据：

作者
Eugene Charniak
Eugene Charniak
Glenn Carroll
Glenn Carroll
0
您的评分 :

暂无评分

标签
评论
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果，我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问，可以通过电子邮件方式联系我们：report@aminer.cn
's parent. We derive the equations for estimating the necessary probabilities using a variant of the inside-outside algorithm. We give experimental results showing that, beginning with a high-performance PCFG, one can develop a pseudo PCSG that yields significant performance gains. Analysis shows that the benefits from the context-sensitive statistics are localized, suggesting that we can use them to extend the original PCFG. Experimental results confirm that this is both feasible and the resulting grammar retains the performance gains. This implies that our scheme may be useful as a novel method for PCFG induction.","abstract_zh":"","authors":[{"id":"53f56639dabfae6294f80487","name":"Eugene Charniak"},{"id":"53f43318dabfaee1c0a7bd6c","name":"Glenn Carroll"}],"doi":"","id":"53e9b9a0b7602d9704594796","is_downvoted":false,"is_starring":false,"is_upvoted":false,"issn":"","keywords":["context-sensitive statistic","pcfg induction","improved grammatical language models","original pcfg","yields significant performance gain","context-sensitive statistics","pseudo context-sensitive","inside-outside algorithm","pseudo pcsg","improved grammatical language model","high-performance pcfg","performance gain","language model"],"labels":["en_journal"],"lang":"en","num_citation":57,"num_starred":0,"num_upvoted":0,"num_viewed":30,"pages":{"end":"733","start":"728"},"pdf":"https:\u002F\u002Fstatic.aminer.cn\u002Fupload\u002Fpdf\u002Fprogram\u002F53e9b9a0b7602d9704594796_0.pdf","title":"Context-Sensitive Statistics for Improved Grammatical Language Models","urls":["http:\u002F\u002Fwww.aaai.org\u002FLibrary\u002FAAAI\u002F1994\u002Faaai94-111.php","http:\u002F\u002Fwww.webofknowledge.com\u002F"],"venue":{"id":"53a725ac20f7420be8b556b2","info":{"name":"AAAI"},"issue":"","type":0,"volume":""},"versions":[{"id":"53e24cb820f7fff6774070cb","sid":"310390","src":"msra","year":1994},{"id":"53908cde20f70186a0dced82","sid":"864432","src":"acm","year":1994},{"id":"539087c720f70186a0d588d8","sid":"199381","src":"acm","year":1994},{"id":"599c7ef3601a182cd28dbe0a","sid":"conf\u002Faaai\u002FCharniakC94","src":"dblp","vsid":"conf\u002Faaai","year":1994},{"id":"56d8158adabfae2eee6f1bd2","sid":"2115407249","src":"mag","year":1994},{"id":"619b65a01c45e57ce9a97ab1","sid":"WOS:A1994BC17T00112","src":"wos","vsid":"PROCEEDINGS OF THE TWELFTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOLS 1 AND 2","year":1994},{"id":"62376a325aee126c0f083b97","sid":"http:\u002F\u002Fwww.aaai.org\u002FLibrary\u002FAAAI\u002F1994\u002Faaai94-111.php","src":"dblp","vsid":"conf\u002Faaai","year":1994}],"year":1994,"cited_pubs":33,"total_ref":9,"total_sim":0},"bestpaper":undefined,"authorsData":[{"avatar":"https:\u002F\u002Fstatic.aminer.org\u002F0a60\u002F0004\u002F0000\u002F53afc155dabfae456ebd2d74.gif","id":"53f56639dabfae6294f80487","name":"Eugene Charniak","name_zh":"","num_followed":4},{"id":"53f43318dabfaee1c0a7bd6c","name":"Glenn Carroll","name_zh":"","num_followed":0}],"redirect_id":undefined,"notfound":undefined,"pdfInfo":{}};