【摘要】：自動問答系統(tǒng)是自然語言處理領(lǐng)域的一個重要任務(wù)。以“問答對”為基本成分的語料庫是自動問答系統(tǒng)答案的主要來源,語料庫中的“問答對”一般都從百度知道、知乎等問答社區(qū)中抽取的。然而,問答社區(qū)中的一個問句通常有多個答案,從不同的角度回復(fù)問句,自動問答社區(qū)中的答案卻只選取其中一個答案作為問句的回復(fù),這就導(dǎo)致語料庫中的答案不夠全面。因此,本文研究答案融合方法,將多個候選答案進行融合,從而解決自動問答系統(tǒng)語料庫存在的不全面、冗余等問題。本文使用深度學(xué)習(xí)方法、注意力機制等方法解決答案融合問題。答案融合方法是從多個候選答案中抽取答案,因此答案抽取的準(zhǔn)確性,決定了答案融合方法結(jié)果的準(zhǔn)確性及全面性。同時答案融合方法得到答案是從多個候選答案中抽取的,語義存在著不連貫、可讀性差的問題。因此本文從答案自動抽取及語義連貫性兩個方面提升答案融合效果。答案自動抽取能夠從多個候選答案抽取中能夠答案問題的答案句,使答案更加精簡、更加全面。語義連貫性通常表現(xiàn)為段落內(nèi)的句子順序,因此使用句子排序方法解決答案語意連貫性問題,增強候選答案間的語意連貫性,使答案融合結(jié)果可讀性更好,語義更連貫。本文主要研究工作圍繞答案自動抽取以及句子排序展開,分為以下四個方面:1、基于詞共現(xiàn)的答案自動抽取模型。本文利用句內(nèi)注意力機制對問句及答案句進行特征提取,同時針對語料,引入詞共現(xiàn)特征、文檔倒數(shù)特征、詞相似度特征,并采用隨機采樣方法處理語料中存在的數(shù)據(jù)不平衡問題。對比基線方法,基于詞共現(xiàn)的答案自動抽取模型能夠提高抽取答案的準(zhǔn)確度。2、基于句子匹配的句子排序方法。本文將深度學(xué)習(xí)方法引入句子排序中,使用深度學(xué)習(xí)方法解決句子排序問題,同時將句子匹配方法引入句子排序中,對比基線方法,模型提高了句子排序方法的效果。3、基于注意力機制的句子排序方法。為了增強句子排序模型捕捉語義邏輯關(guān)系的能力,將注意力機制引入句子排序任務(wù)中,實現(xiàn)了基于靜態(tài)注意力機制的句子排序模型、基于詞對齊注意力機制的句子排序模型以及基于句內(nèi)注意力機制的句子排序模型�；谧⒁饬C制的句子排序方法能夠有效捕捉句子間語義邏輯關(guān)系,提升句子排序效果。4、答案融合系統(tǒng)設(shè)計與實現(xiàn)。對答案自動抽取模塊及句子排序模塊進行整合,實現(xiàn)答案融合系統(tǒng),解決語料庫構(gòu)建中存在的語義不全面、冗長的問題
[Abstract]:Automatic question answering system is an important task in the field of natural language processing. The corpus with "question and answer pair" as the basic component is the main source of the answer of the automatic question and answer system. The "question and answer pair" in the corpus is generally extracted from the community of questions and answers such as Baidu. However, a question in a Q & A community usually has multiple answers. The answer in the automatic Q & A community only selects one of the answers as the answer to the question, which leads to the incompleteness of the answers in the corpus. Therefore, this paper studies the method of answer fusion and combines multiple candidate answers to solve the problems of incomplete and redundant in the corpus of automatic question answering system. In this paper, the method of deep learning and attention mechanism are used to solve the problem of answer fusion. The method of answer fusion is to extract answers from multiple candidate answers, so the accuracy of answer extraction determines the accuracy and comprehensiveness of the results of answer fusion. At the same time, the solution is extracted from multiple candidate answers by the method of answer fusion, and there are some problems in semantic incoherence and poor readability. Therefore, this paper improves the result of answer fusion from two aspects: automatic answer extraction and semantic coherence. Automatic answer extraction can extract the answer sentence from multiple candidate answers, which makes the answer more concise and more comprehensive. Semantic coherence is usually expressed as sentence sequence in paragraphs, so sentence sorting method is used to solve the problem of semantic coherence of answers, to enhance semantic coherence between candidate answers, and to make the results of answer fusion more readable and semantic coherent. This paper focuses on automatic answer extraction and sentence sequencing, which is divided into four parts: 1, and the automatic answer extraction model based on word co-occurrence. In this paper, we use intra-sentence attention mechanism to extract the feature of question sentence and answer sentence, at the same time, we introduce word co-occurrence feature, document reciprocal feature, word similarity feature to the corpus. And the random sampling method is used to deal with the data imbalance in the corpus. Compared with the baseline method, the auto-extraction model based on word co-occurrence can improve the accuracy of the answer extraction by 0.2, and the sentence ranking method based on sentence matching. In this paper, the method of deep learning is introduced into sentence sorting, and the problem of sentence sorting is solved by using depth learning method. At the same time, the method of sentence matching is introduced into sentence sorting, and the baseline method is compared. The model improves the effect of sentence sort method. 3, and sentence sorting method based on attention mechanism. In order to enhance the ability of sentence sorting model to capture semantic logic relation, the attention mechanism is introduced into sentence sorting task, and a sentence sorting model based on static attention mechanism is implemented. Sentence ordering model based on word alignment attention mechanism and sentence sorting model based on intra-sentence attention mechanism. The method of sentence sorting based on attention mechanism can effectively capture the semantic logic relationship between sentences, improve the effect of sentence sorting. 4. The design and implementation of answer fusion system. The automatic answer extraction module and sentence sorting module are integrated to realize the answer fusion system, and to solve the problem of semantic incompleteness and verbosity in the construction of corpus.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.1;TP181

【參考文獻】

相關(guān)期刊論文 前9條

1 康世澤;馬宏;黃瑞陽;;一種基于神經(jīng)網(wǎng)絡(luò)模型的句子排序方法[J];中文信息學(xué)報;2016年05期

2 劉秉權(quán);徐振;劉峰;劉銘;孫承杰;王曉龍;;面向問答社區(qū)的答案摘要方法研究綜述[J];中文信息學(xué)報;2016年01期

3 韓永峰;許旭陽;李弼程;朱武斌;陳剛;;基于事件抽取的網(wǎng)絡(luò)新聞多文檔自動摘要[J];中文信息學(xué)報;2012年01期

4 唐朝霞;;多特征融合的中文問答系統(tǒng)答案抽取算法[J];貴州大學(xué)學(xué)報(自然科學(xué)版);2011年05期

5 田衛(wèi)東;祖永亮;;基于答案模式和語義特征融合的答案抽取方法[J];計算機工程與應(yīng)用;2011年13期

6 徐永東;王亞東;劉楊;王偉;權(quán)光日;;多文檔文摘中基于時間信息的句子排序策略研究[J];中文信息學(xué)報;2009年04期

7 余正濤;毛存禮;鄧錦輝;章程;郭劍毅;;基于模式學(xué)習(xí)的中文問答系統(tǒng)答案抽取方法[J];吉林大學(xué)學(xué)報(工學(xué)版);2008年01期

8 劉里;曾慶田;;自動問答系統(tǒng)研究綜述[J];山東科技大學(xué)學(xué)報(自然科學(xué)版);2007年04期

9 王作英,肖熙;基于段長分布的HMM語音識別模型[J];電子學(xué)報;2004年01期

相關(guān)碩士學(xué)位論文 前2條

1 趙惜墨;基于問句實體擴展和全局規(guī)劃的答案摘要方法研究[D];哈爾濱工業(yè)大學(xué);2015年

2 劉平安;基于HLDA模型的中文多文檔摘要技術(shù)研究[D];北京郵電大學(xué);2013年

，

本文編號：2221526