本文選題：主題分配 + 對(duì)話系統(tǒng)��； 參考：《哈爾濱工業(yè)大學(xué)》2017年碩士論文

【摘要】：隨著人工智能的迅速發(fā)展,理解人類語言并能夠與人類對(duì)話,給出相應(yīng)的信息反饋的機(jī)器人成為了大多數(shù)人的需求。在這樣的背景下,智能聊天機(jī)器人慢慢走入人們的視野。在這股機(jī)器人熱潮中,能夠幫助用戶解決日常生活中各種事情的私人助理機(jī)器人應(yīng)運(yùn)而生。它能夠幫助用戶解決一系列生活中遇到的問題,如打車、預(yù)定餐廳等。與機(jī)器人對(duì)話的最大挑戰(zhàn)就是要把人的自然語言翻譯成機(jī)器可以聽得懂的指令,從而給出相應(yīng)的正確反饋。機(jī)器人能夠給出正確反饋的第一步是理解人類需求,所以將用戶輸入理解為正確的主題,即對(duì)話系統(tǒng)中的主題分配起著非常重要的作用。本文的研究任務(wù)是將用戶的輸入分配到這個(gè)語句對(duì)應(yīng)的主題下,以保證接下來的反饋方向正確。本文主要介紹了三種主題分配的方法:基于傳統(tǒng)分類方法的主題分配模型、基于LDA主題模型特征擴(kuò)展的主題分配方法以及基于深度學(xué)習(xí)的對(duì)話系統(tǒng)主題分配模型。基于傳統(tǒng)分類方法的主題分配模型可以看做是文本分類任務(wù),本文利用有監(jiān)督學(xué)習(xí)的方法,在學(xué)習(xí)的過程中利用學(xué)習(xí)算法從訓(xùn)練語料中以特征的方式學(xué)習(xí)有用信息,從而得到主題分配的模型。該方法的效果高度依賴于人工選擇的特征。基于LDA主題模型特征擴(kuò)展的短文本分類方法考慮到了短文本詞語稀疏性的特點(diǎn),加入了擴(kuò)展詞后,主題特征被加入到了原來的短文本中,以達(dá)到語義擴(kuò)展的效果,避免了短文本傳統(tǒng)的文本表示方法特征稀疏的問題。實(shí)驗(yàn)表明,引入LDA主題詞擴(kuò)展特征后,主題分配模型取得了更好的效果。深度學(xué)習(xí)方法的避免了人工選取特征對(duì)實(shí)驗(yàn)結(jié)果的影響,使機(jī)器自動(dòng)學(xué)習(xí)文本中的特征,增加了文本中隱藏的詞與詞之間的語義聯(lián)系。本文利用基于卷積神經(jīng)網(wǎng)絡(luò)的句子分類方法以及基于循環(huán)神經(jīng)網(wǎng)絡(luò)的的方法作為主題分配的模型進(jìn)行實(shí)驗(yàn),實(shí)驗(yàn)結(jié)果表明基于深度學(xué)習(xí)的主題分配模型相比于傳統(tǒng)方法取得了更好的效果。
[Abstract]:With the rapid development of artificial intelligence, the robot that can understand the human language and communicate with human, giving the corresponding information feedback, has become the demand of most people.In this context, the intelligent chat robot slowly walked into people's view.In this boom of robots, personal assistant robots, which can help users solve all kinds of things in their daily life, come into being.It can help users solve a range of life problems, such as taxi, restaurant reservations and so on.The biggest challenge in conversation with robots is to translate human natural language into instructions that machines can understand and give the correct feedback.The first step for robots to give correct feedback is to understand human needs, so the user input is understood as the correct topic, that is, topic assignment plays a very important role in the dialogue system.The task of this paper is to assign the user's input to the topic corresponding to the statement to ensure the correct direction of the following feedback.This paper mainly introduces three methods of topic assignment: the topic assignment model based on the traditional classification method, the topic assignment method based on the feature extension of the LDA topic model and the topic assignment model of the dialogue system based on in-depth learning.The topic assignment model based on traditional classification method can be regarded as the task of text classification. In this paper, we use supervised learning method and learning algorithm to learn useful information from training corpus in the way of feature.The model of topic assignment is obtained.The effect of this method is highly dependent on the characteristics of manual selection.The short text classification method based on the feature extension of LDA topic model takes into account the sparsity of the short text. After the extension word is added, the theme feature is added to the original short text to achieve the effect of semantic expansion.It avoids the problem of sparse features of traditional text representation in short text.The experimental results show that the topic assignment model is more effective when the extended feature of LDA theme words is introduced.The depth learning method avoids the influence of the artificial selection of the features on the experimental results, makes the machine automatically learn the features in the text, and increases the semantic relation between the hidden words and the words in the text.In this paper, the method of sentence classification based on convolution neural network and the method based on cyclic neural network are used as the model of topic assignment.The experimental results show that the topic assignment model based on deep learning is more effective than the traditional method.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.1;TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前9條

1 王仲遠(yuǎn);程健鵬;王海勛;文繼榮;;短文本理解研究[J];計(jì)算機(jī)研究與發(fā)展;2016年02期

2 李鋒剛;梁鈺;GAO Xiao-zhi;ZENGER Kai;;基于LDA-wSVM模型的文本分類研究[J];計(jì)算機(jī)應(yīng)用研究;2015年01期

3 呂超鎮(zhèn);姬東鴻;吳飛飛;;基于LDA特征擴(kuò)展的短文本分類[J];計(jì)算機(jī)工程與應(yīng)用;2015年04期

4 陸彥婷;陸建峰;楊靜宇;;層次分類方法綜述[J];模式識(shí)別與人工智能;2013年12期

5 張志飛;苗奪謙;高燦;;基于LDA主題模型的短文本分類方法[J];計(jì)算機(jī)應(yīng)用;2013年06期

6 孫志軍;薛磊;許陽明;王正;;深度學(xué)習(xí)研究綜述[J];計(jì)算機(jī)應(yīng)用研究;2012年08期

7 沈競;;基于信息增益的LDA模型的短文本分類[J];重慶文理學(xué)院學(xué)報(bào)(自然科學(xué)版);2011年06期

8 姚全珠;宋志理;彭程;;基于LDA模型的文本分類研究[J];計(jì)算機(jī)工程與應(yīng)用;2011年13期

9 鄭勇濤,劉玉樹;支持向量機(jī)解決多分類問題研究[J];計(jì)算機(jī)工程與應(yīng)用;2005年23期

相關(guān)碩士學(xué)位論文 前1條

1 宋志理;基于LDA模型的文本分類研究[D];西安理工大學(xué);2010年

，

本文編號(hào)：1732015