Convolutional Neural Networks for Sentence Classification

Convolutional Neural Networks for Sentence Classification

ID：40352759

大小：235.97 KB

頁數(shù)：6頁

時間：2019-07-31

Convolutional Neural Networks for Sentence Classification_第1頁
Convolutional Neural Networks for Sentence Classification_第2頁
Convolutional Neural Networks for Sentence Classification_第3頁
Convolutional Neural Networks for Sentence Classification_第4頁
Convolutional Neural Networks for Sentence Classification_第5頁
資源描述：

《Convolutional Neural Networks for Sentence Classification》由會員上傳分享，免費在線閱讀，更多相關(guān)內(nèi)容在學(xué)術(shù)論文-天天文庫。

1、ConvolutionalNeuralNetworksforSentenceClassi?cationYoonKimNewYorkUniversityyhk255@nyu.eduAbstractlocalfeatures(LeCunetal.,1998).Originallyinventedforcomputervision,CNNmodelshaveWereportonaseriesofexperimentswithsubsequentlybeenshowntobeeffectiveforNLPconvolutionalneuralnetworks(CNN)andhave

2、achievedexcellentresultsinsemantictrainedontopofpre-trainedwordvec-parsing(Yihetal.,2014),searchqueryretrievaltorsforsentence-levelclassi?cationtasks.(Shenetal.,2014),sentencemodeling(Kalch-WeshowthatasimpleCNNwithlit-brenneretal.,2014),andothertraditionalNLPtlehyperparametertuningandstati

3、cvec-tasks(Collobertetal.,2011).torsachievesexcellentresultsonmulti-Inthepresentwork,wetrainasimpleCNNwithplebenchmarks.Learningtask-speci?conelayerofconvolutionontopofwordvectorsvectorsthrough?ne-tuningoffersfurtherobtainedfromanunsupervisedneurallanguagegainsinperformance.Weadditionallym

4、odel.ThesevectorsweretrainedbyMikolovetproposeasimplemodi?cationtothear-al.(2013)on100billionwordsofGoogleNews,chitecturetoallowfortheuseofbothandarepubliclyavailable.1Weinitiallykeepthetask-speci?candstaticvectors.TheCNNwordvectorsstaticandlearnonlytheotherparam-modelsdiscussedhereinimpro

5、veupontheetersofthemodel.Despitelittletuningofhyper-stateofthearton4outof7tasks,whichparameters,thissimplemodelachievesexcellentincludesentimentanalysisandquestionresultsonmultiplebenchmarks,suggestingthatclassi?cation.thepre-trainedvectorsare‘universal’featureex-1Introductiontractorsthatc

6、anbeutilizedforvariousclassi?ca-tiontasks.Learningtask-speci?cvectorsthroughDeeplearningmodelshaveachievedremarkable?ne-tuningresultsinfurtherimprovements.Weresultsincomputervision(Krizhevskyetal.,?nallydescribeasimplemodi?cationtothearchi-2012)andspeechrecognition(Gravesetal.,2013)tecture

7、toallowfortheuseofbothpre-trainedandinrecentyears.Withinnaturallanguageprocess-task-speci?cvectorsbyhavingmultiplechannels.ing,muchoftheworkwithdeeplearningmeth-odshasinvolvedlearningwordvectorrepresenta-OurworkisphilosophicallysimilartoRazaviantionsthroughneu

當前文檔最多預(yù)覽五頁，下載文檔查看全文

此文檔下載收益歸作者所有

當前文檔最多預(yù)覽五頁，下載文檔查看全文
溫馨提示：
1. 部分包含數(shù)學(xué)公式或PPT動畫的文件，查看預(yù)覽時可能會顯示錯亂或異常，文件下載后無此問題，請放心下載。
2. 本文檔由用戶上傳，版權(quán)歸屬用戶，天天文庫負責(zé)整理代發(fā)布。如果您對本文檔版權(quán)有爭議請及時聯(lián)系客服。
3. 下載前請仔細閱讀文檔內(nèi)容，確認文檔內(nèi)容符合您的需求后進行下載，若出現(xiàn)內(nèi)容與標題不符可向本站投訴處理。
4. 下載文檔時可能由于網(wǎng)絡(luò)波動等原因無法下載或下載錯誤，付費完成后未能成功下載的用戶請聯(lián)系客服處理。