【摘要】：隨著時(shí)代的發(fā)展,中國(guó)英文學(xué)習(xí)者的數(shù)量在急劇上升。有限的教師資源和巨大的學(xué)習(xí)需求使得智能自動(dòng)輔助教學(xué)備受關(guān)注。英文文章智能評(píng)改系統(tǒng)是一款為中國(guó)英文學(xué)習(xí)者寫的英文文章自動(dòng)評(píng)改系統(tǒng),這很大程度的緩解了英文學(xué)習(xí)者過(guò)多和教師資源不足的矛盾。面向中國(guó)學(xué)生英文文章的詞性標(biāo)注是實(shí)現(xiàn)對(duì)中國(guó)學(xué)生英文文章自動(dòng)評(píng)改的基礎(chǔ)。到目前為止已有大量的研究者對(duì)英文詞性標(biāo)注做了很多有益的研究,然而,對(duì)中國(guó)學(xué)生寫的英文文章詞性標(biāo)注的研究卻是非常少見(jiàn)。另外,在現(xiàn)有的絕大部分詞性標(biāo)注方法中,人工提取的特征提取過(guò)程是必不可少的。由于中國(guó)學(xué)生寫的英文文章可能出現(xiàn)大量的未知錯(cuò)誤,并且不同層次的英文學(xué)習(xí)者寫的文章犯的錯(cuò)誤非常不同,因此對(duì)這類文章詞性標(biāo)注所需要提取的特征是非常不容易被發(fā)現(xiàn)的。本文從詞向量的角度,對(duì)中國(guó)學(xué)生寫的英文文章詞性標(biāo)注研究。本文提出一種基于詞向量的兩層詞性標(biāo)注方法。這種方法只有少量的人工提取的特征被提取,大部分的特征通過(guò)詞向量與第一層標(biāo)注概率向量自動(dòng)訓(xùn)練得到。另外,這種方法還將標(biāo)注集分成兩類,按照兩層結(jié)構(gòu)對(duì)句子進(jìn)行詞性標(biāo)注。提出一種特征值動(dòng)態(tài)更新方法。該方法在標(biāo)注模型訓(xùn)練過(guò)程中對(duì)特征值按照一定的規(guī)則動(dòng)態(tài)更新。本文的詞性標(biāo)注模型使用上述特征值動(dòng)態(tài)更新方法訓(xùn)練,然后使用基于詞向量的兩層詞性標(biāo)注方法對(duì)文本進(jìn)行詞性標(biāo)注,其準(zhǔn)確率達(dá)到了 95.63%,超過(guò)了現(xiàn)有的基于詞向量詞性標(biāo)注器對(duì)中國(guó)學(xué)生寫的英文文章詞性標(biāo)注的準(zhǔn)確率。
[Abstract]:With the development of the times, the number of Chinese English learners is rising sharply. The limited teacher resources and the huge learning demand make the intelligent automatic assistant teaching pay more attention. The intelligent evaluation system of English articles is an automatic evaluation system for Chinese English learners, which greatly alleviates the contradiction between the excessive number of English learners and the shortage of teachers' resources. Part of speech tagging for Chinese students' English articles is the basis for automatic evaluation of Chinese students' English articles. Up to now, a large number of researchers have done a lot of useful research on English part-of-speech tagging. However, it is very rare to study the part of speech tagging in English articles written by Chinese students. In addition, in most of the existing parts of speech tagging methods, the artificial feature extraction process is essential. Due to the fact that there may be a large number of unknown errors in English articles written by Chinese students, and the errors made by English learners at different levels are very different. Therefore, it is very difficult to find the features that need to be extracted for this kind of articles. From the point of view of word vector, this paper studies the part of speech tagging of English articles written by Chinese students. In this paper, we propose a two-layer tagging method based on word vector. In this method, only a small number of artificial features are extracted, and most of the features are obtained by automatically training the word vector and the first layer tagging probability vector. In addition, the method divides the tagging set into two categories, and carries on the part of speech tagging according to the two-layer structure. A dynamic updating method for eigenvalues is proposed. The method dynamically updates the eigenvalues according to certain rules during the training process of the annotation model. The part of speech tagging model in this paper uses the dynamic updating method of the above eigenvalues to train, and then uses the two-layer tagging method based on word vector to label the text in part of speech. The accuracy of this method is 95.63. It exceeds the accuracy of the existing word vector tagging devices for Chinese students' English articles.
【學(xué)位授予單位】：北京郵電大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.1;TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 譚詠梅;吳坤;;面向英語(yǔ)文章的詞性標(biāo)注算法[J];北京郵電大學(xué)學(xué)報(bào);2014年06期

2 譚詠梅;楊雪;;結(jié)合實(shí)體鏈接與實(shí)體聚類的命名實(shí)體消歧[J];北京郵電大學(xué)學(xué)報(bào);2014年05期

3 朱敏;賈真;左玲;吳安峻;陳方正;柏玉;;中文微博實(shí)體鏈接研究[J];北京大學(xué)學(xué)報(bào)(自然科學(xué)版);2014年01期

4 張楊;;如何提高學(xué)生英語(yǔ)寫作水平[J];黑龍江教育學(xué)院學(xué)報(bào);2012年05期

5 李業(yè)剛;孫福振;李鑒柏;呂新宇;;語(yǔ)義角色標(biāo)注研究綜述[J];山東理工大學(xué)學(xué)報(bào)(自然科學(xué)版);2011年06期

6 金雪丹;施朝健;;圖像處理與神經(jīng)網(wǎng)絡(luò)識(shí)別技術(shù)在船舶分類中的應(yīng)用(英文)[J];上海海事大學(xué)學(xué)報(bào);2007年01期

7 李紅;;大學(xué)生英語(yǔ)寫作常見(jiàn)錯(cuò)誤歸類分析[J];當(dāng)代教育論壇;2006年16期

8 胡耀垓,李偉,胡繼明;一種改進(jìn)激活函數(shù)的人工神經(jīng)網(wǎng)絡(luò)及其應(yīng)用[J];武漢大學(xué)學(xué)報(bào)(信息科學(xué)版);2004年10期

9 邢永康;馬少平;;統(tǒng)計(jì)語(yǔ)言模型綜述[J];計(jì)算機(jī)科學(xué);2003年09期

10 陳傳波,彭炎,陸楓;基于聚類的神經(jīng)網(wǎng)絡(luò)及其在預(yù)測(cè)中的應(yīng)用[J];華中科技大學(xué)學(xué)報(bào)(自然科學(xué)版);2003年06期

相關(guān)碩士學(xué)位論文 前2條

1 吳廣財(cái);HMM增量學(xué)習(xí)算法在中文命名實(shí)體識(shí)別中的應(yīng)用研究[D];華南理工大學(xué);2011年

2 雷靜;基于圖像處理和神經(jīng)網(wǎng)絡(luò)的車牌識(shí)別系統(tǒng)研究[D];中南大學(xué);2009年

，

本文編號(hào)：2402964