顧及句法特征的中文地名識(shí)別方法
發(fā)布時(shí)間:2018-07-16 10:11
【摘要】:中文地名識(shí)別是命名實(shí)體識(shí)別的重要研究課題之一,也是擴(kuò)展地理信息系統(tǒng)數(shù)據(jù)來源的關(guān)鍵。傳統(tǒng)的地名識(shí)別主要基于地名元素或詞性特征進(jìn)行識(shí)別,特征來源單一。針對(duì)上述問題,提出了一種顧及句法特征的中文地名識(shí)別方法,挖掘中文地名在自然語言中的句法信息,設(shè)計(jì)了短語結(jié)構(gòu)和依存關(guān)系兩類句法特征,利用條件隨機(jī)場(chǎng)模型實(shí)現(xiàn)了中文地名的訓(xùn)練和識(shí)別。實(shí)驗(yàn)表明,句法特征能夠有效提高中文地名識(shí)別的準(zhǔn)確率和召回率,尤其是對(duì)于復(fù)雜地名的識(shí)別,具有良好的效果。
[Abstract]:Chinese place name recognition is one of the important research topics of named entity recognition, and it is also the key to extend the data source of GIS. Traditional geographical names recognition is mainly based on geographical names elements or part of speech features, the source of features is single. The conditional random field model is used to realize the training and recognition of Chinese place names.
【作者單位】: 信息工程大學(xué);四川省應(yīng)急測(cè)繪與防災(zāi)減災(zāi)工程技術(shù)研究中心;
【基金】:國(guó)家自然科學(xué)基金青年基金項(xiàng)目(41401467) 四川省應(yīng)急測(cè)繪與防災(zāi)減災(zāi)工程技術(shù)研究中心開放基金項(xiàng)目(K2015B014)
【分類號(hào)】:P208
,
本文編號(hào):2126057
[Abstract]:Chinese place name recognition is one of the important research topics of named entity recognition, and it is also the key to extend the data source of GIS. Traditional geographical names recognition is mainly based on geographical names elements or part of speech features, the source of features is single. The conditional random field model is used to realize the training and recognition of Chinese place names.
【作者單位】: 信息工程大學(xué);四川省應(yīng)急測(cè)繪與防災(zāi)減災(zāi)工程技術(shù)研究中心;
【基金】:國(guó)家自然科學(xué)基金青年基金項(xiàng)目(41401467) 四川省應(yīng)急測(cè)繪與防災(zāi)減災(zāi)工程技術(shù)研究中心開放基金項(xiàng)目(K2015B014)
【分類號(hào)】:P208
,
本文編號(hào):2126057
本文鏈接:http://sikaile.net/kejilunwen/dizhicehuilunwen/2126057.html
最近更新
教材專著