人工智能探索-------外文翻譯.doc
約38頁DOC格式手機(jī)打開展開
人工智能探索-------外文翻譯,無論是打印的或者手寫的字體,如果想識別特定的字母字符,問題就在于理解單詞、句子或更大的一段文字組合的“自然”語言,如英語。為了區(qū)分語言如英語和機(jī)器語言,前者通常被稱為“自然語言”。在機(jī)器語言中, 理解輸入的自然語言通常指轉(zhuǎn)換到某種記憶模型(如拉斐爾使用的sir系統(tǒng)或奎廉所使用的語義網(wǎng)絡(luò))或執(zhí)行一些恰當(dāng)?shù)妮斎雱幼?。自然語...
內(nèi)容介紹
此文檔由會員 wanli1988go 發(fā)布
無論是打印的或者手寫的字體,如果想識別特定的字母字符,問題就在于理解單詞、句子或更大的一段文字組合的“自然”語言,如英語。為了區(qū)分語言如英語和機(jī)器語言,前者通常被稱為“自然語言”。在機(jī)器語言中, 理解輸入的自然語言通常指轉(zhuǎn)換到某種記憶模型(如拉斐爾使用的SIR系統(tǒng)或奎廉所使用的語義網(wǎng)絡(luò))或執(zhí)行一些恰當(dāng)?shù)妮斎雱幼鳌?br />
自然語言能說出和寫的一樣的意思。那是因為演講聽起來是和分割印刷在紙上的是不一樣的,理解話語有著額外的困難,我會在一個后來的篇章來描述。
自然語言理解的逆輸入生成自然語言輸出的口語和書寫。從一種語言翻譯成另外一種,既要理解和又要生成。進(jìn)行一場談話也是如此。所有的這些問題-理解、產(chǎn)生、翻譯與一般的談話——構(gòu)成了“自然語言處理”(有時也簡稱NLP)。
7.1 語言水平
語言學(xué)家和其他學(xué)習(xí)語言者對語言的認(rèn)識和分析處在不同級別上的。從那些處理最基本組成的語言(音)和訴訟到部分進(jìn)行上行水平處理序列的句子,這些可以安排在一種層次,如果演講處理成有層次的語音(語音)和音系學(xué)(組織的聲音字)。對于講話,交易形態(tài)與全字是如何加在一起,從小型零件的制造和銷售。例如,“走出去”包括“行走”加上“吸引”。
接下來,語法關(guān)注句子的結(jié)構(gòu)和語法。它規(guī)定所試圖描述一串字在一個特定的語言被貼上要么語法或不是。例如,該字符串“約翰打了球”是語法,但是“球到約翰”則不是。連同這本字典定義的詞、句法的重要性理解句子的意義。舉例來說,這句話“約翰看見那人拿著望遠(yuǎn)鏡”有兩種不同的意義取決于它句法結(jié)構(gòu)(也就是說,這取決于“用望遠(yuǎn)鏡”是指“男人”有一個望遠(yuǎn)鏡或“看見”。)
但是語法是不夠確定的意義。例如這句話,“無色的綠色思想在
Beyond pattern recognition of individual alphanumeric characters,whether they be of fixed font or handwritten,lies the problem of understanding strings of characters that form words,sentences,or larger assemblages of text in a“natural” language,such as English.To distinguish languages such as English from the languages used by computers,the former are usually called“natural languages.”In artificial intelligence,“understanding”natural language input usually means either converting it to some kind of memory model(such as the one used by Raphael in his SIR system or the semantic network used by Quillian)or the evocation of some action appropriate to the input.
Natural languages are spoken as well as written.And,because speech sounds are not as well segmented as are the characters printed on a page,speech understanding presents additional di?culties,which I’ll describe in a later chapter. The inverse of understanding natural language input is generating natural language output–both written and spoken.Translating from one language to another involves both understanding and generation.So does carrying on a conversation.All of these problems understanding, generation, translation, and conversing–fall under the general h
自然語言理解的逆輸入生成自然語言輸出的口語和書寫。從一種語言翻譯成另外一種,既要理解和又要生成。進(jìn)行一場談話也是如此。所有的這些問題-理解、產(chǎn)生、翻譯與一般的談話——構(gòu)成了“自然語言處理”(有時也簡稱NLP)。
7.1 語言水平
語言學(xué)家和其他學(xué)習(xí)語言者對語言的認(rèn)識和分析處在不同級別上的。從那些處理最基本組成的語言(音)和訴訟到部分進(jìn)行上行水平處理序列的句子,這些可以安排在一種層次,如果演講處理成有層次的語音(語音)和音系學(xué)(組織的聲音字)。對于講話,交易形態(tài)與全字是如何加在一起,從小型零件的制造和銷售。例如,“走出去”包括“行走”加上“吸引”。
接下來,語法關(guān)注句子的結(jié)構(gòu)和語法。它規(guī)定所試圖描述一串字在一個特定的語言被貼上要么語法或不是。例如,該字符串“約翰打了球”是語法,但是“球到約翰”則不是。連同這本字典定義的詞、句法的重要性理解句子的意義。舉例來說,這句話“約翰看見那人拿著望遠(yuǎn)鏡”有兩種不同的意義取決于它句法結(jié)構(gòu)(也就是說,這取決于“用望遠(yuǎn)鏡”是指“男人”有一個望遠(yuǎn)鏡或“看見”。)
但是語法是不夠確定的意義。例如這句話,“無色的綠色思想在
Beyond pattern recognition of individual alphanumeric characters,whether they be of fixed font or handwritten,lies the problem of understanding strings of characters that form words,sentences,or larger assemblages of text in a“natural” language,such as English.To distinguish languages such as English from the languages used by computers,the former are usually called“natural languages.”In artificial intelligence,“understanding”natural language input usually means either converting it to some kind of memory model(such as the one used by Raphael in his SIR system or the semantic network used by Quillian)or the evocation of some action appropriate to the input.
Natural languages are spoken as well as written.And,because speech sounds are not as well segmented as are the characters printed on a page,speech understanding presents additional di?culties,which I’ll describe in a later chapter. The inverse of understanding natural language input is generating natural language output–both written and spoken.Translating from one language to another involves both understanding and generation.So does carrying on a conversation.All of these problems understanding, generation, translation, and conversing–fall under the general h