本文關(guān)鍵詞： HowNet 義原向量 PageRank 詞語相似度 問答系統(tǒng)　出處：《鄭州大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：隨著大數(shù)據(jù)時(shí)代的到來,互聯(lián)網(wǎng)每天都會(huì)產(chǎn)生大量的文本信息,詞語作為文本的基本組成單位,對(duì)詞語語義的理解是文本處理的基礎(chǔ)工作之一。詞語相似度計(jì)算,是用一個(gè)具體的數(shù)值表示兩個(gè)詞語的相似程度,是理解詞語語義的主要方法,詞語相似度問題的解決將會(huì)推動(dòng)自然語言處理領(lǐng)域相關(guān)應(yīng)用技術(shù)的發(fā)展,例如問答系統(tǒng)、信息檢索、詞義消歧和機(jī)器翻譯等。在深入學(xué)習(xí)了詞語相似度計(jì)算及問答系統(tǒng)的相關(guān)研究方法的基礎(chǔ)上,本文提出了一種基于義原向量的詞語相似度計(jì)算方法,并研究了該方法在知識(shí)庫問答系統(tǒng)中的應(yīng)用,主要研究內(nèi)容包括:(1)提出了一種義原向量生成模型SIC_PageRank。在HowNet義原上下位關(guān)系構(gòu)成的層次結(jié)構(gòu)圖中,通過義原及其子孫義原節(jié)點(diǎn)的深度信息計(jì)算每個(gè)義原的信息容量SIC(Sememe Information Content),利用SIC和義原結(jié)構(gòu)圖中的連接關(guān)系,構(gòu)建PageRank轉(zhuǎn)移概率矩陣,基于PageRank思想迭代生成每個(gè)義原的向量表示。(2)提出了基于義原向量的詞語相似度計(jì)算方法�；赟IC_PageRank模型生成義原向量,由義原向量的余弦相似度計(jì)算義原相似度,由義原相似度計(jì)算概念相似度,進(jìn)而計(jì)算詞語相似度。將基于義原向量的詞語相似度計(jì)算方法應(yīng)用到“現(xiàn)代漢語語義詞典”名詞語義類自動(dòng)識(shí)別中,實(shí)驗(yàn)結(jié)果表明,該方法與人工校對(duì)結(jié)果的一致率達(dá)到71.9%,優(yōu)于使用基于最短路徑距離的方法。(3)詞語相似度計(jì)算在知識(shí)庫問答系統(tǒng)中的應(yīng)用。在知識(shí)庫問答系統(tǒng)中,借助詞語相似度來計(jì)算問句謂詞和候選答案謂詞之間的相似度,并結(jié)合兩者的編輯距離、詞共現(xiàn)和分類等特征,使用排序?qū)W習(xí)算法Ranking SVM對(duì)候選答案排序。本文在NLPCC2016知識(shí)庫問答系統(tǒng)評(píng)測(cè)任務(wù)數(shù)據(jù)集上進(jìn)行實(shí)驗(yàn),實(shí)驗(yàn)結(jié)果表明,將基于義原向量的詞語相似度計(jì)算方法應(yīng)用到知識(shí)庫問答系統(tǒng)中,識(shí)別答案的精確率達(dá)到73.88%,召回率達(dá)到82.29%,平均F1值達(dá)到75.88%,在三個(gè)評(píng)價(jià)指標(biāo)上均高于使用word2vec詞向量的方法。
[Abstract]:With the advent of the era of big data, the Internet every day will produce a large amount of text information, words as the basic unit of the text, the semantic understanding is the basis of text processing. Word similarity computation, is used for a specific numerical similarity of two words, is the main method of semantic understanding to solve the problem, the development of word similarity will push Natural Language Processing related application technology field, such as question answering system, information retrieval, word sense disambiguation and Machine Translation. Based on related research methods in-depth study of word similarity calculation and question answering system, this paper presents a method of word similarity computation based on sememe vector, and studies the method for question answering system based on knowledge base, the main research contents include: (1) proposed a sememe vector generation model SIC_Page Figure Rank. in the HowNet hierarchy of sememe hyponymy constitutes, through the depth information of original meaning and original meaning of the children nodes is calculated for each original meaning of information capacity of SIC (Sememe Information Content), the connection between the SIC and the original meaning of the structure chart, construct the PageRank transtion-probablity matrix, PageRank said the idea of iterative generation each based on the original meaning of the vector. (2) proposed the original meaning of word similarity calculation based on vector method. SIC_PageRank model generation based on vector sememe sememe similarity, calculated by cosine similarity sememe vector, by sememe similarity calculation of concept similarity, and word similarity. The word similarity based on sememe vector the calculation method is applied to the "modern Chinese semantic dictionary" noun semantic classes in automatic recognition, the experimental results show that the consistent rate of this method and manual correction results reached 71.9%, better than that With the method of the shortest path distance. (3) based on word similarity computation Q & a system based on knowledge base. In the knowledge base of question answering system, using word similarity to calculate the similarity between question and answer candidate predicate predicate, and combined with the edit distance of the two word co-occurrence and classification, the use of learning to rank Ranking algorithm SVM to rank candidate answers. This article in the NLPCC2016 knowledge base quiz experiment systematically evaluation task data sets. Experimental results show that the original meaning of word similarity calculation based on vector method is applied to the knowledge base of question answering system, accurate answer recognition rate reached 73.88%, the recall rate reached 82.29%, the average value of F1 reached 75.88%. Methods using word2vec term vectors were higher than that in the three evaluation indexes.

【學(xué)位授予單位】：鄭州大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.1

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王樹西;趙星秋;潘碩;;問答系統(tǒng)在教學(xué)中的應(yīng)用[J];中國教育信息化;2007年07期

2 毛先領(lǐng);李曉明;;問答系統(tǒng)研究綜述[J];計(jì)算機(jī)科學(xué)與探索;2012年03期

3 莫麗萍,王樹西,姜吉發(fā),雷雨霞;問答系統(tǒng)和淺層結(jié)構(gòu)模式推理[J];廣西師范大學(xué)學(xué)報(bào)(自然科學(xué)版);2004年01期

4 盧志堅(jiān),張冬茉;中文問答系統(tǒng)中的問句理解[J];計(jì)算機(jī)工程;2004年18期

5 王樹西;問答系統(tǒng):核心技術(shù)、發(fā)展趨勢(shì)[J];計(jì)算機(jī)工程與應(yīng)用;2005年18期

6 林曉慶;;問答系統(tǒng)中基于列表類問題的研究[J];電腦知識(shí)與技術(shù)(學(xué)術(shù)交流);2007年07期

7 張積賓;徐志明;王恒;潘啟樹;;面向大規(guī)模網(wǎng)絡(luò)數(shù)據(jù)的社會(huì)化問答系統(tǒng)[J];哈爾濱工業(yè)大學(xué)學(xué)報(bào);2008年12期

8 賈君枝;毛海飛;;漢語框架網(wǎng)絡(luò)問答系統(tǒng)問句處理研究[J];圖書情報(bào)工作;2008年10期

9 胡小華;劉軒;劉丹;陸偉;;基于冗余的仿真問答系統(tǒng)的輕量級(jí)局部文本分析[J];圖書情報(bào)知識(shí);2009年01期

10 張中峰;李秋丹;;社區(qū)問答系統(tǒng)研究綜述[J];計(jì)算機(jī)科學(xué);2010年11期

相關(guān)會(huì)議論文 前10條

1 何靖;陳，

本文編號(hào)：1443053