發(fā)布時(shí)間：2018-05-20 10:19

  本文選題：中文人名識(shí)別 + 詞向量　； 參考：《大連理工大學(xué)》2016年碩士論文

【摘要】：中文人名識(shí)別任務(wù)是中文信息處理領(lǐng)域中的基礎(chǔ)任務(wù),其性能的好壞將直接影響到其他任務(wù)的性能。中文人名的隨意性使其在未登錄詞中占有較大的比重,解決未登錄詞識(shí)別問題首先要解決人名識(shí)別問題。因此,解決中文人名識(shí)別問題具有重要的意義�，F(xiàn)有基于統(tǒng)計(jì)的中文人名識(shí)別方法存在特征選取復(fù)雜和人工干預(yù)等問題,針對(duì)這些問題,本文提出了一種基于循環(huán)神經(jīng)網(wǎng)絡(luò)(Recurrent Neural Networks)的中文人名識(shí)別方法,該方法僅采用詞向量作為模型的特征且無需人工干預(yù),有效降低了特征選取的復(fù)雜性和人工干預(yù)對(duì)實(shí)驗(yàn)造成的影響。此外,詞向量可以通過大量未標(biāo)注的中文數(shù)據(jù)訓(xùn)練獲得,然后將蘊(yùn)含豐富語義信息的詞向量作為循環(huán)神經(jīng)網(wǎng)絡(luò)模型的輸入,可以使模型學(xué)習(xí)到更多的信息,提升模型的性能。本文將模型分為兩個(gè)階段：模型構(gòu)建階段和后處理階段。在模型構(gòu)建階段,我們將重點(diǎn)放在詞向量的優(yōu)化策略上。針對(duì)詞向量的優(yōu)化問題,本文提出了三種策略：(1)將word2vec訓(xùn)練得到的詞向量替換循環(huán)神經(jīng)網(wǎng)絡(luò)模型的隨機(jī)初始詞向量(2)對(duì)詞向量訓(xùn)練語料進(jìn)行數(shù)詞泛化操作(3)改進(jìn)word2vec模型,將特征信息融入詞向量實(shí)驗(yàn)結(jié)果表明,通過詞向量的優(yōu)化操作,中文人名識(shí)別模型的F值提高了2.23%。在后處理階段,通過上下文規(guī)則對(duì)候選人名進(jìn)行過濾；采用基于篇章的全局?jǐn)U散操作召回在某一位置由于信息不足識(shí)別不出而在其他位置能夠被識(shí)別的人名；使用基于篇章的局部擴(kuò)散操作識(shí)別篇章信息中有名無姓或者有姓無名的人名。實(shí)驗(yàn)結(jié)果表明,通過規(guī)則過濾和擴(kuò)散操作,中文人名識(shí)別模型的F值提高了4.74%。
[Abstract]:The task of Chinese name recognition is the basic task in the field of Chinese information processing, and its performance will directly affect the performance of other tasks. The randomness of Chinese names makes them occupy a large proportion in unrecorded words. To solve the problem of unrecorded words recognition, we must first solve the problem of personal name recognition. Therefore, it is of great significance to solve the problem of Chinese name recognition. The existing Chinese name recognition methods based on statistics have the problems of complex feature selection and artificial intervention. In view of these problems, this paper proposes a Chinese name recognition method based on cyclic neural network (Recurrent Neural Network). This method only uses word vector as the feature of the model and does not need human intervention, which effectively reduces the complexity of feature selection and the influence of artificial intervention on the experiment. In addition, the word vector can be obtained through a large number of unlabeled Chinese data training, and then the word vector with rich semantic information can be used as the input of the cyclic neural network model, so that the model can learn more information and improve the performance of the model. This paper divides the model into two stages: model construction stage and post-processing phase. In the stage of model construction, we focus on the optimization strategy of word vector. To solve the problem of word vector optimization, this paper proposes three strategies: 1) the word vector is replaced by the random initial word vector of the neural network model, which is trained by word2vec, and the random initial word vector is used to generalize the word vector training corpus. (3) the word2vec model is improved. The experimental results show that the F value of the Chinese name recognition model is increased by 2.233 by the optimization of the word vector. In the post-processing stage, the candidate's name is filtered by contextual rules, and the text based global diffusion operation is used to recall the names of people who can be recognized in other places because of the lack of information. A text-based local diffusion operation is used to identify a person with no or no name in the text information. The experimental results show that the F value of the Chinese name recognition model is increased by 4.74 by regular filtering and diffusion operation.
【學(xué)位授予單位】：大連理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.1;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王s，

本文編號(hào)：1914230