计算机与现代化
計算機與現代化
계산궤여현대화
Computer and Modernization
2015年
10期
6-9
,共4页
董奥根%刘茂福%黄革新%舒琦赟
董奧根%劉茂福%黃革新%舒琦赟
동오근%류무복%황혁신%서기빈
word2vec%知识点%余弦距离%语义相似度%向量空间模型
word2vec%知識點%餘絃距離%語義相似度%嚮量空間模型
word2vec%지식점%여현거리%어의상사도%향량공간모형
word2vec%knowledge point%cosine distance%semantic similarity%vector space model
随着基于知识点题库系统的广泛应用，实现试题与知识点的自动匹配，成为当下研究的重要问题。利用word2vec分别得到试题和知识点所包含的每个词的K维空间向量，通过计算空间向量间的余弦距离得到题干与知识点的语义相似度，进而自动发现知识点与试题之间的语义关联关系。实验结果显示此方法能快速发现试题与知识点的关系，提高题库系统的工作效率。
隨著基于知識點題庫繫統的廣汎應用，實現試題與知識點的自動匹配，成為噹下研究的重要問題。利用word2vec分彆得到試題和知識點所包含的每箇詞的K維空間嚮量，通過計算空間嚮量間的餘絃距離得到題榦與知識點的語義相似度，進而自動髮現知識點與試題之間的語義關聯關繫。實驗結果顯示此方法能快速髮現試題與知識點的關繫，提高題庫繫統的工作效率。
수착기우지식점제고계통적엄범응용，실현시제여지식점적자동필배，성위당하연구적중요문제。이용word2vec분별득도시제화지식점소포함적매개사적K유공간향량，통과계산공간향량간적여현거리득도제간여지식점적어의상사도，진이자동발현지식점여시제지간적어의관련관계。실험결과현시차방법능쾌속발현시제여지식점적관계，제고제고계통적공작효솔。
With the extensive application of examination system based on knowledge points, how to automatically match examina-tion question with knowledge points has become an important direction of current research.In this paper, word2vec is used to get the K-dimensional space vector for each word in the texts of examination question and the knowledge points at first.And then, we calculate the cosine distance between the vectors to represent the semantic similarity of the examination question and the knowl-edge points.The experimental results show that this method can quickly find the relationship between examination question and knowledge points and improve the work efficiency of the examination system.
