beyond keywords: the revolution in search

beyond keywords: the revolution in search

ID:18362812

大?。?.09 MB

頁數(shù):20頁

時(shí)間:2018-09-16

beyond keywords: the revolution in search_第1頁
beyond keywords: the revolution in search_第2頁
beyond keywords: the revolution in search_第3頁
beyond keywords: the revolution in search_第4頁
beyond keywords: the revolution in search_第5頁
資源描述:

《beyond keywords: the revolution in search》由會(huì)員上傳分享,免費(fèi)在線閱讀,更多相關(guān)內(nèi)容在學(xué)術(shù)論文-天天文庫。

1、BeyondKeywords:TheRevolutioninSearchJoeBuzzanga,MBA,MLS,MASeniorProductManager,IEEEIntroductionInadigitalworldsearchisessential,pervasive,ubiquitousandceaseless.Yet,searchremainsunsatisfyinginmanyways.Whyisthisthecase?Whenwesearch,we’reafterananswer.Buttoday’ssearchenginesd

2、on’thaveenoughintelligencetoprovideanswers.They’realsonotadvancedenoughtointerpretnaturallyphrasedqueriesandunderstandtheambiguitiesofordinarylanguage.Andsowetypeinkeywordsandgetlinksorlistsofresultsthataremoreorlessrelevantdependingonthetypeofsearch,ourqueryandthecompetenc

3、eofthesearchengine.Thereisalwaysafurtherstepwhenwehavetoselectanitemfromaresultsetandassessit.Hopefully,theanswereventuallyemerges,buttherearenoguarantees.Theultimatesearchenginewoulddirectlyanswerourquery.Perhapsitwouldevenanticipateourqueryandpresenttheanswerbeforeweevena

4、sk.Toanswerus,thesearchenginewouldneedtounderstandourquery,ourcontextandthecorpusofknowledgeatitsdisposal—inshort,itwouldneedArtificialIntelligence(AI).TheproblemofsearchultimatelyresolvestoaproblemofAI.AdeepAIsearchengineremainsafuturisticvisionforthemostpart.Butsearchtech

5、nologyisadvancingrapidlyandrecentinnovationsarebeginningtoovercomethelimitationsoftheconventionalkeywordquery/resultlistmodel.Searchisreflectingglimmersofsomethingresembling“meaning”or“intelligence”.Meaninginsearchisemergingalongthreerelateddimensions.First,meaninginthesens

6、eofenormousknowledgebasesthatprovideafoundationforsupplyingdirectanswerstoqueries.Second,meaninginthesenseofsemanticunderstandingautomaticallyderivedfromunlabeleddocumentcollectionsthroughmachinelearningalgorithms.Third,actionablemeaningintheguiseofintelligentpersonalassist

7、antsthatprovidedeeplycontextualsearchtriggeredthroughanatural,conversationalinterface.TheBuildingBlocksofSearch:ClassicInformationRetrievalModernsearchenginesareapplicationsofthetechnologiesdevelopedinthefieldmoreformallyknownasInformationRetrieval.Inthispaperwetreatsearcha

8、ndinformationretrievalassynonymousconcepts.Tounderstandtherevolutioninsearch,wenee

當(dāng)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(dāng)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(dòng)畫的文件,查看預(yù)覽時(shí)可能會(huì)顯示錯(cuò)亂或異常,文件下載后無此問題,請(qǐng)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(fù)責(zé)整理代發(fā)布。如果您對(duì)本文檔版權(quán)有爭議請(qǐng)及時(shí)聯(lián)系客服。
3. 下載前請(qǐng)仔細(xì)閱讀文檔內(nèi)容,確認(rèn)文檔內(nèi)容符合您的需求后進(jìn)行下載,若出現(xiàn)內(nèi)容與標(biāo)題不符可向本站投訴處理。
4. 下載文檔時(shí)可能由于網(wǎng)絡(luò)波動(dòng)等原因無法下載或下載錯(cuò)誤,付費(fèi)完成后未能成功下載的用戶請(qǐng)聯(lián)系客服處理。