互聯(lián)網(wǎng)新聞的漢越雙語話題演化關(guān)鍵技術(shù)研究
發(fā)布時間：2018-07-16 12:39
【摘要】：越南與中國的關(guān)系密切,從海量的漢越新聞話題文本集合中分析出話題隨著時間變化而發(fā)生的演變,對于增進兩國人民的文化交流有著十分重要的意義。話題演化分析技術(shù)旨在將用戶關(guān)注的話題以簡潔、有序地方式表示出來,這樣可以幫助用戶清楚地了解話題的整個來龍去脈。漢越話題文本集合是使用兩種語言描述了相同內(nèi)容的文本集合,由于文本中無論是哪種語言,都包含了意思相同或者相近的事件要素,例如對象、時間、地點和事件觸發(fā)詞。利用漢越話題文本集合中存在的這種公性,可以構(gòu)建漢越話題要素對將兩種語言聯(lián)系到一起。本文圍繞已有的漢越話題文本集合,使用了基于子話題關(guān)聯(lián)的演化分析方法,并完成了如下兩個特色工作:1.提出了基于超圖的漢越雙語新聞話題要素提取方法。首先根據(jù)觸發(fā)詞激勵的方法提取新聞中的事件要素,然后在此基礎上構(gòu)建話題超圖模型,將漢越事件要素作為結(jié)點,將漢越文本集合中的句子作為超邊,根據(jù)概率評估函數(shù)計算結(jié)點和超邊的初始權(quán)重,最后采用PageRank隨機游走方法,對漢越事件素進行評分,從而得到漢越話題要素。實驗結(jié)果表明,該方法相比只考慮單文本事件要素提取方法的效果有顯著提高。2.提出了基于子話題關(guān)聯(lián)的漢越雙語話題演化分析方法。首先采用k-means算法得到初始子話題集合,把已經(jīng)獲得的初始子話題集作為樣本實例,通過基于knn算法的單遍聚類方法得到各個時間片內(nèi)的子話題集合。然后用余弦方法和KL距離的混合公式計算出不同時間窗口內(nèi)子話題的相似度值。最后通過本文提出的話題演化分析步驟得到不同時間片之間的子話題的關(guān)系。與相似度只用KL距離或者只用余弦公式計算的方法相比,本文提出的方法更加有效。
[Abstract]:Vietnam has a close relationship with China. It is of great significance to analyze the evolution of topics over time from the mass collection of Chinese and Vietnamese news topics, which is of great significance to enhance the cultural exchanges between the two peoples. The technology of topic evolution analysis aims to express the topics concerned by users in a concise and orderly manner, which can help users to understand the whole context of the topic clearly. The Sino-Vietnamese topic text set is a text set in which the same content is described in two languages. No matter which language it is, it contains the same or similar event elements, such as object, time, place and event trigger word. By using this commonality in the text set of Chinese and Vietnamese topics, we can construct a pair of Chinese and Vietnamese topic elements to connect the two languages. In this paper, an evolutionary analysis method based on sub-topic association is used around the existing Sino-Vietnamese topic text set, and the following two special works are completed: 1. A method of extracting Chinese and Vietnamese bilingual news topic elements based on hypergraph is proposed. First of all, the event elements in news are extracted according to the method of trigger word motivation, then the topic hypergraph model is constructed on the basis of which, the Sino-Vietnamese event element is used as the node, and the sentence in the Sino-Vietnamese text set is taken as the super-edge. According to the probability evaluation function, the initial weights of nodes and overedges are calculated, and PageRank random walk method is used to score the Sino-Vietnamese event elements, and then to obtain the Sino-Vietnamese topic elements. The experimental results show that the effectiveness of this method is significantly higher than that of only considering single text event element extraction. A method of Chinese and Vietnamese bilingual topic evolution analysis based on subtopic correlation is proposed. First, the initial subtopic set is obtained by using the k-means algorithm, and the initial subtopic set is taken as a sample example, and the sub-topic set in each time slice is obtained by the single-pass clustering method based on the knn algorithm. Then the similarity values of subtopics in different time windows are calculated by using the mixed formula of cosine method and KL distance. Finally, the relationship of sub-topics between different time slices is obtained by the analytical steps of topic evolution proposed in this paper. Compared with the method using only KL distance or cosine formula, the proposed method is more effective.
【學位授予單位】：昆明理工大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.1
本文編號：2126415
[Abstract]:Vietnam has a close relationship with China. It is of great significance to analyze the evolution of topics over time from the mass collection of Chinese and Vietnamese news topics, which is of great significance to enhance the cultural exchanges between the two peoples. The technology of topic evolution analysis aims to express the topics concerned by users in a concise and orderly manner, which can help users to understand the whole context of the topic clearly. The Sino-Vietnamese topic text set is a text set in which the same content is described in two languages. No matter which language it is, it contains the same or similar event elements, such as object, time, place and event trigger word. By using this commonality in the text set of Chinese and Vietnamese topics, we can construct a pair of Chinese and Vietnamese topic elements to connect the two languages. In this paper, an evolutionary analysis method based on sub-topic association is used around the existing Sino-Vietnamese topic text set, and the following two special works are completed: 1. A method of extracting Chinese and Vietnamese bilingual news topic elements based on hypergraph is proposed. First of all, the event elements in news are extracted according to the method of trigger word motivation, then the topic hypergraph model is constructed on the basis of which, the Sino-Vietnamese event element is used as the node, and the sentence in the Sino-Vietnamese text set is taken as the super-edge. According to the probability evaluation function, the initial weights of nodes and overedges are calculated, and PageRank random walk method is used to score the Sino-Vietnamese event elements, and then to obtain the Sino-Vietnamese topic elements. The experimental results show that the effectiveness of this method is significantly higher than that of only considering single text event element extraction. A method of Chinese and Vietnamese bilingual topic evolution analysis based on subtopic correlation is proposed. First, the initial subtopic set is obtained by using the k-means algorithm, and the initial subtopic set is taken as a sample example, and the sub-topic set in each time slice is obtained by the single-pass clustering method based on the knn algorithm. Then the similarity values of subtopics in different time windows are calculated by using the mixed formula of cosine method and KL distance. Finally, the relationship of sub-topics between different time slices is obtained by the analytical steps of topic evolution proposed in this paper. Compared with the method using only KL distance or cosine formula, the proposed method is more effective.
【學位授予單位】：昆明理工大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.1
【參考文獻】
相關(guān)期刊論文 前10條
1 劉煒;劉菲京;王東;劉宗田;;一種基于事件本體的文本事件要素提取方法[J];中文信息學報;2016年04期
2 潘清清;周楓;余正濤;郭劍毅;線巖團;;基于條件隨機場的越南語命名實體識別方法[J];山東大學學報(理學版);2014年01期
3 張先飛;郭志剛;劉嵩;程磊;田雨暄;;基于觸發(fā)詞指導的自相似度聚類事件檢測[J];計算機科學;2010年03期
4 張闊;李涓子;吳剛;王克宏;;基于詞元再評估的新事件檢測模型[J];軟件學報;2008年04期
5 洪宇;張宇;范基禮;劉挺;李生;;基于子話題分治匹配的新事件檢測[J];計算機學報;2008年04期
6 孫吉貴;劉杰;趙連宇;;聚類算法研究[J];軟件學報;2008年01期
7 趙妍妍;秦兵;車萬翔;劉挺;;中文事件抽取技術(shù)研究[J];中文信息學報;2008年01期
8 邱立坤;龍志yN;鐘華;程葳;;層次化話題發(fā)現(xiàn)與跟蹤方法及系統(tǒng)實現(xiàn)[J];廣西師范大學學報(自然科學版);2007年02期
9 洪宇;張宇;劉挺;鄭偉;龔誠;李生;;基于層次聚類的自適應信息過濾學習算法[J];中文信息學報;2007年03期
10 宋丹;王衛(wèi)東;陳英;;基于改進向量空間模型的話題識別與跟蹤[J];計算機技術(shù)與發(fā)展;2006年09期
相關(guān)碩士學位論文 前1條
1 馮禮;基于事件框架的突發(fā)事件信息抽取[D];上海交通大學;2008年
，本文編號：2126415
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2126415.html
最近更新
教材專著
