藏文句义分割方法  

Semantic Segmentation Method of Tibetan Sentences

作　　者：柔特[1,2,3] 色差甲 才让加[1,2,3] ROU Te;SE Chajia;CAI Rangjia(Computer College,Ministry of Education,Qinghai Normal University,Xining 810008,China;Provincial Key Laboratory of Tibetan Intelligent Information Processing and Machine Translation,Ministry of Education,Qinghai Normal University,Xining 810008,China;Key Laboratory of Tibetan Information Processing,Ministry of Education,Qinghai Normal University,Xining 810008,China)

机构地区：[1]青海师范大学计算机学院,西宁810008 [2]青海师范大学青海省藏文信息处理与机器翻译重点实验室,西宁810008 [3]青海师范大学藏文信息处理教育部重点实验室,西宁810008

出　　处：《计算机工程》2020年第2期286-291,共6页Computer Engineering

基　　金：国家重点研发计划(2017YFB1402200);国家自然科学基金(61662061);国家社会科学基金(14BYY132)

摘　　要：句子是字或词根据语法规则进行组合的编码,句义分割是句子组合规律的解码问题,即对句义进行解析。在藏文分词后直接进行语义分析,其颗粒度过小,容易出现词语歧义,而以句子为分析单位,则颗粒度过大,不能较好地揭示句子的语义。为此,提出一种藏文句义分割方法,通过长度介于词语和句子之间的语义块单元进行句义分割。在对句子进行分词和标注的基础上,重新组合分词结果,将句子分割为若干个语义块,并采用空洞卷积神经网络模型对语义块进行识别。实验结果表明,该方法对藏文句义分割的准确率达到94.68%。Sentences are characters or words that are combined according to grammatical rules.Semantic segmentation is a decoding problem of sentence combination rules,that is,parsing the meaning of sentences.If the semantic analysis is performed directly after the Tibetan word segmentation,the granularity is too small,and word ambiguity is prone to occur.However,if the sentence is used as the analysis unit,the granularity is too large to reveal the semantics of the sentence.To this end,this paper proposes a semantic segmentation method for Tibetan sentences.The method segments sentences by semantic chunk,the length of which is between a word and a sentence.After word segmentation and labeling of the sentence,the word segmentation results are re-combined to segment the sentence into several semantic chunks.Then the dilated convolutional neural network model is used to identify the semantic chunks.Experimental results show that the accuracy of the proposed method for Tibetan sentences achieves 94.68%.

关 键 词：句义分割 语义块 语义分析 空洞卷积神经网络 藏文 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]