【摘要】：本文所描述的問題推薦模型是基于某互動中文問答平臺所開發(fā)個性化推薦系統(tǒng)。該中文問答平臺上存在著大量未被回答的問題，個性化推薦系統(tǒng)能夠根據(jù)用戶的注冊信息以及其在該互動問答平臺上的登錄、瀏覽和回答等行為，為用戶推薦相關(guān)問題，以降低用戶找到能夠回答的待解決問題的成本，提高問題的回答量，更好地進行知識分享。 該問題推薦系統(tǒng)的推薦模型采用的是基于機器學(xué)習(xí)技術(shù)構(gòu)建的基于內(nèi)容的推薦算法，借鑒了精準定向廣告系統(tǒng)的思路，以推薦問題的點擊率作為系統(tǒng)的優(yōu)化目標(biāo)，結(jié)合中文分詞[76,77,78,79]、關(guān)鍵詞提取、命名實體識別(Named Entity Recognition，NER)[81,82,83,84]等技術(shù)，建立點擊率(CTR)預(yù)估模型來匹配用戶與問題。點擊率預(yù)估模型計算條件概率P(click=true|user=uid, question=qid)，即以新問題被用戶點擊的概率作為用戶與新問題匹配程序的度量，并使用最大熵(Max Entropy)模型來擬合上述條件概率。 原始版本的問題推薦模型存在以下兩點不足：首先是推薦模型僅使用了非常少量的特征。特征的維度少導(dǎo)致模型容易出現(xiàn)欠擬合的現(xiàn)象。其次，靜態(tài)的推薦模型無法適應(yīng)數(shù)據(jù)分布的變化所造成的影響。 本文的工作在于改進了原始版本的問題推薦模型，，具體而言包括以下兩個方面的工作： 1.通過在問題推薦模型中引入語義特征、組合特征以及偏置項等，結(jié)合模型選擇與正則化技術(shù)，提高了推薦模型的準確率。改進后的模型使用了概率潛在語義分析(probability Latent Semantic Analysis,pLSA)技術(shù)提取問題文本的語義特征。在語義層面對文本進行處理能夠獲得比在詞匯層面更好的效果。原有推薦模型在基準數(shù)據(jù)集上的準確率為88%，改進后的模型在基準數(shù)據(jù)集上的準確率為95%。 2.設(shè)計并實現(xiàn)了問題推薦模型的離線訓(xùn)練系統(tǒng)。該系統(tǒng)能夠完成基礎(chǔ)數(shù)據(jù)自動下載、特征提取、模型訓(xùn)練與模型選擇等功能，能夠?qū)崿F(xiàn)問題推薦模型的離線訓(xùn)練與定期更新。設(shè)計離線訓(xùn)練系統(tǒng)的目的在于定期產(chǎn)出新的推薦模型。實驗結(jié)果證明問題推薦模型的數(shù)據(jù)分布具有時序性，使用靜態(tài)模型無法適應(yīng)數(shù)據(jù)分布變化的影響。 改進后的問題推薦模型以及離線訓(xùn)練系統(tǒng)已經(jīng)上線，為該互動中文問答系統(tǒng)的用戶提供更加準確的個性化問題推薦服務(wù)。
[Abstract]:The question recommendation model described in this paper is based on a personalized recommendation system developed by an interactive Chinese question answering platform. There are a large number of unanswered questions on the Chinese question answering platform. The personalized recommendation system can recommend the relevant questions to the user according to the user's registration information and their login, browse and answer behavior on the interactive question answering platform. In order to reduce the cost of users to find the problem to be answered, improve the number of answers, better knowledge sharing. The recommendation model of the problem recommendation system adopts the content-based recommendation algorithm based on the machine learning technology, and draws lessons from the idea of the precision directed advertising system, and takes the click rate of the recommendation problem as the optimization goal of the system. Combined with the techniques of Chinese word segmentation [76 / 77/ 7/ 78/ 78/ 79], keyword extraction and named entity recognition (Named Entity Recognition,NER) [81 / 82/ 83/ 84], a (CTR) prediction model of click rate was established to match the user and the problem. The conditional probability P (click=true user=uid, question=qid) is calculated by using the prediction model of click rate, that is, the probability of the new problem being clicked by the user is taken as the measure of the matching program between the user and the new problem, and the maximum entropy (Max Entropy) model is used to fit the conditional probability. The original version of the problem recommendation model has the following two shortcomings: the first is that the recommendation model only uses a very small number of features. The lack of feature dimension leads to the underfitting of the model. Secondly, the static recommendation model can not adapt to the change of data distribution. The work of this paper is to improve the original version of the problem recommendation model, specifically including the following two aspects of work: 1. By introducing semantic features, combination features and bias items into the problem recommendation model, the accuracy of the recommendation model is improved by combining model selection and regularization techniques. The improved model uses probabilistic latent semantic analysis (probability Latent Semantic Analysis,pLSA) technique to extract semantic features of problem text. Text processing at the semantic level can achieve better results than at the lexical level. The accuracy of the original recommendation model on the datum data set is 88 and that of the improved model on the datum data set is 95. 2. 2. An offline training system for problem recommendation model is designed and implemented. The system can automatically download basic data, feature extraction, model training and model selection, and can realize offline training and periodic updating of problem recommendation model. The purpose of designing an offline training system is to produce a new recommendation model on a regular basis. The experimental results show that the data distribution of the problem recommendation model is time-series, and the static model can not adapt to the influence of the change of the data distribution. The improved question recommendation model and the offline training system have been launched to provide a more accurate personalized question recommendation service for the users of the interactive Chinese question answering system.
【學(xué)位授予單位】：中山大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2013
【分類號】：TP181;TP391.3

【共引文獻】

相關(guān)期刊論文 前10條

1 楊緒兵,韓自存;ε不敏感的核Adaline算法及其在圖像去噪中的應(yīng)用[J];安徽工程科技學(xué)院學(xué)報(自然科學(xué)版);2003年04期

2 陶秀鳳,唐詩忠,周鳴爭;基于支持向量機的軟測量模型及應(yīng)用[J];安徽工程科技學(xué)院學(xué)報(自然科學(xué)版);2004年02期

3 王東雷;;基于單純形算法的優(yōu)化設(shè)計與實現(xiàn)[J];安徽農(nóng)業(yè)科學(xué);2007年36期

4 許高程;張文君;王衛(wèi)紅;;支持向量機技術(shù)在遙感影像滑坡體提取中的應(yīng)用[J];安徽農(nóng)業(yè)科學(xué);2009年06期

5 郭立萍;唐家奎;米素娟;張成雯;趙理君;;基于支持向量機遙感圖像融合分類方法研究進展[J];安徽農(nóng)業(yè)科學(xué);2010年17期

6 ;A Preliminary Application of the Differential Evolution Algorithm to Calculate the CNOP[J];Atmospheric and Oceanic Science Letters;2009年06期

7 馮學(xué)軍;;最小二乘支持向量機的研究與應(yīng)用[J];安慶師范學(xué)院學(xué)報(自然科學(xué)版);2009年01期

8 鄒心遙;姚若河;;基于LSSVM的威布爾分布形狀參數(shù)估計(英文)[J];半導(dǎo)體技術(shù);2008年06期

9 鄒心遙;姚若河;;基于LSSVM的小子樣元器件壽命預(yù)測[J];半導(dǎo)體技術(shù);2011年09期

10 李卓遠,吳為民,王e

本文編號：2238205