At last , this paper introduces the evaluation of question - answering system 最后還介紹了自動(dòng)問答系統(tǒng)的評(píng)價(jià)問題。
This paper introduces the current research status and the methods that are often used in question - answering 本文介紹了自動(dòng)問答技術(shù)的發(fā)展現(xiàn)狀和自動(dòng)問答系統(tǒng)中常用的技術(shù)。
In general , a question - answering system is made up of three parts : question analysis , information retrieval and answer extraction 自動(dòng)問答系統(tǒng)一般包括三個(gè)主要組成部分:問題分析、信息檢索和答案抽取。
Question - answering is a hot research field in natural language processing , which includes many kinds of nlp technology 摘要自動(dòng)問答技術(shù)是自然語言處理領(lǐng)域中一個(gè)非常熱門的研究方向,它綜合運(yùn)用了各種自然語言處理技術(shù)。
Question - answering system is a research topic which collecting natural language processing , knowledge expressing and information retrieving to one body . it establishes on the text retrieval foundation , but it is different from the traditional search engines 問答系統(tǒng)是集自然語言處理、知識(shí)表示、信息檢索于一體的研究課題,它建立在文本檢索的基礎(chǔ)上,但又不同于傳統(tǒng)的搜索引擎。
In view of the shortage of the on - line question - answering system , this paper deals with designing the on - line question - answering system , supplies the realization of automatic question - answering system and the application of data excavation in data analyzing and processing 摘要針對(duì)目前國內(nèi)答疑系統(tǒng)的不足,本文對(duì)網(wǎng)上答疑系統(tǒng)的設(shè)計(jì)進(jìn)行了論述,提出了系統(tǒng)自動(dòng)答疑實(shí)現(xiàn)和數(shù)據(jù)挖掘在數(shù)據(jù)分析處理中的應(yīng)用。
Generally speaking , examination is developed in question - answer format in order to get favorable information . this thesis explores power in the discourse of cross - examination ? an important component of courtroom discourse ? from the perspectives of conversation analysis and the modality system 本文發(fā)展和應(yīng)用了話語分析和系統(tǒng)功能語言學(xué)的情態(tài)系統(tǒng),并從這兩個(gè)角度分析了法庭交叉質(zhì)詢,從語言學(xué)的角度找出了法庭交叉質(zhì)詢所揭示的權(quán)勢(shì)關(guān)系。
The traditional search engines request user input the combination of keywords , and then locate the literature for the inquiry of which the user submitted , users must depend on himself to filter the useful information that he needs ; while question - answering systems enable users to input a question in natural languages , finally give users concise and accurate answers also in natural languages 傳統(tǒng)的搜索引擎要求用戶輸入一些關(guān)鍵字的組合,且對(duì)于用戶提交的查詢只能定位出文獻(xiàn),用戶必須依靠自己去篩選需要的有用信息;而問答系統(tǒng)允許用戶以自然語言的形式輸入一個(gè)問句,最終返回給用戶的也是自然語言形式的簡短而準(zhǔn)確的答案。
Presently , many scientific research institutes have been investigated english question - answering systems , some mature english question - answering systems have been widely recognized , but few institutes are doing research on chinese question - answering systems , for the chinese question - answering system demands much higher to the correlation domain research request , for example , there is no blank space between chinese words , chinese syntax analysis and semantic understanding is more difficult , all of these have made the chinese question - answering systems development slowly 目前,國外已有很多科研機(jī)構(gòu)參與了英文問答系統(tǒng)的研究,甚至已經(jīng)有相對(duì)成熟的英文問答系統(tǒng),但是國內(nèi)參與中文問答系統(tǒng)的研究不多,因?yàn)橹形膯柎鹣到y(tǒng)對(duì)相關(guān)領(lǐng)域的研究要求更高,例如:中文詞語之間沒有空格;漢語的句法分析和語義理解更為困難等,這些都造成了中文問答系統(tǒng)的發(fā)展緩慢。
The influence of institutional power is exhibited through turn - type allocation and turn control strategies in the phase of turn development . the whole conversation goes mainly under question - answer adjacency pair . the differences and similarities of the turn - control strategies employed by the show hosts and the show guests have been investigated 本文在定性分析的基礎(chǔ)上采用z - test檢驗(yàn)了主持人使用各種放棄話輪、取得話輪的方法的數(shù)量占主持人總話輪的比率與嘉賓使用各種放棄話輪、取得話輪的方法的數(shù)量占嘉賓總話輪的比率之間是否有顯著差異。