Supporting Annotation Layers for Natural Language Processing

Supporting Annotation Layers for Natural Language Processing

ID:37659291

大小:70.48 KB

页数:8页

时间:2019-05-27

Supporting Annotation Layers for Natural Language Processing_第1页
Supporting Annotation Layers for Natural Language Processing_第2页
Supporting Annotation Layers for Natural Language Processing_第3页
Supporting Annotation Layers for Natural Language Processing_第4页
Supporting Annotation Layers for Natural Language Processing_第5页
资源描述:

《Supporting Annotation Layers for Natural Language Processing》由会员上传分享,免费在线阅读,更多相关内容在行业资料-天天文库

1、SupportingAnnotationLayersforNaturalLanguageProcessingArchanaGanapathiandPreslavNakovandArielSchwartzandMartiHearstCSDivisionandSIMSUniversityofCalifornia,Berkeleyarchanag,nakov,sariel@cs.berkeley.edu,hearst@sims.berkeley.eduAbstractofdescription.Wedemonstratethepowerofthequery

2、languageandtheefficiencyoftheindexingThispaperproposesasimplemecha-architectureonawidevarietyofquerytypesthatnismforsupportingmultipleoverlap-havebeenpublishedintheNLPliterature.pinglayersofannotationsfornaturalThearchitectureisbuiltontopofarelationallanguagetextprocessing.Weprese

3、ntdatabasemanagementsystem(RDBMS),andsoaquerylanguageforflexiblyaccessingcantakeadvantageofadvancedindexingstruc-annotatedtext,anddemonstrateitsuseturessuppliedbysuchsystems.WebelievethisonexamplestakenfromtheNLPliter-paperisthefirsttoexperimentwithdifferentin-ature.Wethenreportone

4、xperimentsdexingstructuresinordertodeterminehowtocomparingdifferentstorageandindex-makeannotation-basedqueriesscaletoverylargeingarchitecturesusinganRDBMS,corporawithmanylayersofannotations.showingthatannotation-basedqueriesAnaddedadvantageofthisrepresentationiscanbemadetoscaleto

5、largecorporathatitsupportsaninfrastructureforrunningcom-withmanylayersofannotations.putationallinguisticsexperiments.OftenNLPal-gorithmsrequiresamplingfromadocumentcol-1Introductionlection,eithertoensurethattrainingandtestingareconductedoverrepresentativedata,ortofindTodaymostnatu

6、rallanguageprocessing(NLP)al-sufficientnumbersofsentencesthatsatisfycertaingorithmsmakeuseoftheresultsofpreviouspro-properties.Forexample,adisambiguationalgo-cessingsteps.Forexample,awordsensedisam-rithmmayneedtotrainonexamplesofawordbiguationalgorithmmayusetheoutputofato-withinva

7、riousdomains,sinceitsmeaningsmaykenizer,apart-of-speechtagger,aphrasebound-varyacrossdifferentsubcollections.aryrecognizer,andamodulethatclassifiesnounIntheremainderofthepaperwedescribere-phrasesintosemanticcategories.Currentlytherelatedwork,illustratetheannotationmodelandtheisnos

8、tandardwaytorepresentandstorethere-query

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。