【摘要】：在基于條件隨機(jī)場(chǎng)的中文命名實(shí)體識(shí)別任務(wù)中,現(xiàn)有表示學(xué)習(xí)方法學(xué)習(xí)到的特征存在語(yǔ)義表示偏差,給中文命名實(shí)體識(shí)別帶來(lái)噪聲。針對(duì)此問(wèn)題,提出了一種基于位置敏感Embedding的中文命名實(shí)體識(shí)別方法。該方法將上下文位置信息融入到現(xiàn)有的Embedding模型中,采用多尺度聚類(lèi)方法抽取不同粒度的Embedding特征,通過(guò)條件隨機(jī)場(chǎng)來(lái)識(shí)別中文命名實(shí)體。實(shí)驗(yàn)證明,該方法學(xué)習(xí)到的特征緩解了語(yǔ)義表示偏差,進(jìn)一步提高了現(xiàn)有系統(tǒng)的性能,與傳統(tǒng)方法相比,F值提高了2.85%。
[Abstract]:In the task of Chinese named entity recognition based on conditional Random Field, the existing representation learning methods have semantic representation bias, which brings noise to Chinese named entity recognition. To solve this problem, a Chinese named entity recognition method based on location-sensitive Embedding is proposed. In this method, the context location information is incorporated into the existing Embedding model, and the multi-scale clustering method is used to extract the Embedding features of different granularity, and the Chinese named entities are identified by conditional random fields. Experimental results show that the proposed method can alleviate the deviation of semantic representation and further improve the performance of the existing system. Compared with the traditional method, the value of F is increased by 2.85%.
【作者單位】： 武漢大學(xué)計(jì)算機(jī)學(xué)院;
【基金】：國(guó)家自然科學(xué)基金重點(diǎn)項(xiàng)目(61133012);國(guó)家自然科學(xué)基金面上項(xiàng)目(61373108)
【分類(lèi)號(hào)】：TP391.1

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 邱莎;王付艷;申浩如;段玻;阿圓;丁海燕;;基于含邊界詞性特征的中文命名實(shí)體識(shí)別[J];計(jì)算機(jī)工程;2012年13期

2 彭春艷;張暉;包玲玉;陳昌平;;基于條件隨機(jī)域的生物命名實(shí)體識(shí)別[J];計(jì)算機(jī)工程;2009年22期

3 馮元勇;孫樂(lè);張大鯤;李文波;;基于小規(guī)模尾字特征的中文命名實(shí)體識(shí)別研究[J];電子學(xué)報(bào);2008年09期

4 張sソ，

本文編號(hào)：2233712