發(fā)布時間：2018-03-03 00:36

  本文選題：社區(qū)問答　切入點：問題檢索　出處：《華東師范大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：在社區(qū)問答(Community Question Answering,CQA)中,用戶提出查詢問題,CQA系統(tǒng)在大量已有的問題-答案對的知識庫中搜索相似的問題,然后把該問題的最佳答案當作查詢問題的答案返回給用戶。CQA系統(tǒng)包括兩個關(guān)鍵的子任務(wù):(1)問題檢索(QuestionRetrieval),通過估計問題對的語義相似性來找到和查詢問題最相似的已有問題;(2)答案排序(AnswerRanking),按照答案回答問題的相關(guān)程度對多個答案進行語義相關(guān)性排序,選出最佳的答案。構(gòu)建問答知識庫是一項龐大而復(fù)雜的工程,一種可行的替代方案是利用互聯(lián)網(wǎng)的龐大資源檢索獲得問題的答案。因此,本文的第一個工作是借助搜索引擎來構(gòu)建一個網(wǎng)絡(luò)資源輔助的社區(qū)問答系統(tǒng),該系統(tǒng)在2015年TREC的實時問答競賽中獲得了第二名。以往關(guān)于CQA的研究多將CQA中的問題檢索和答案排序兩個任務(wù)分開獨立解決,沒有考慮它們之間的信息交互。本文的第二個工作考慮這兩個任務(wù)的相互促進,并設(shè)計新的有效特征來進一步提高CQA的性能,相關(guān)工作發(fā)表在2016年IJCNN會議。傳統(tǒng)CQA系統(tǒng)采用專家精心設(shè)計的特征,泛化性差,而深度學(xué)習(xí)的優(yōu)勢是能夠自動學(xué)習(xí)特征。因此,本文的第三個工作探索了深度學(xué)習(xí)模型在問題檢索和答案排序任務(wù)上特征自動學(xué)習(xí)的性能,相關(guān)工作發(fā)表在2016年的SemEval會議。在本文第二個和第三個工作的啟發(fā)下,本文的第四個工作深入研究了深度學(xué)習(xí)框架下的CQA系統(tǒng)。本文提出一個基于門機制的深度神經(jīng)網(wǎng)絡(luò)模型,該門機制能夠自動學(xué)習(xí)問題檢索和答案排序任務(wù)間的交互信息,從而幫助進一步提高CQA性能。本文廣泛而深入地研究了采用傳統(tǒng)自然語言處理技術(shù)與深度學(xué)習(xí)方法的問題檢索和答案排序相互促進的CQA系統(tǒng),大量的實驗結(jié)果表明,本文提出的兩個任務(wù)相互促進的策略在傳統(tǒng)方法和深度學(xué)習(xí)方法中都能夠有效地提高CQA系統(tǒng)的性能。
[Abstract]:In Community Question answering and answering (CQA), users ask queries and CQA systems search for similar questions in a large number of existing questions-answer pairs of knowledge bases. Then the best answer to the question is returned to the user. CQA system including two key sub-tasks: 1) QuestionRetrieval is retrieved by estimating the semantic similarity of the question pairs to find the most similar to the query question. The answer is sorted by AnswerRanking.According to the degree of relevance of the answer to the question, the multiple answers are sorted in terms of semantic correlation. Choose the best answer. Building a question-and-answer knowledge base is a huge and complex project, and a viable alternative is to use the vast resources of the Internet to retrieve the answer to the question. The first work of this paper is to build a community Q & A system assisted by network resources with the help of search engine. In 2015, the system won the second place in the real-time quiz of TREC. In the past studies on CQA, the two tasks of question retrieval and answer sorting in CQA were solved separately and independently. The second work of this article considers the mutual promotion of the two tasks and designs new valid features to further improve the performance of CQA. The related work was published at the IJCNN Conference in 2016. The traditional CQA system adopts the characteristics carefully designed by experts and has poor generalization, while the advantage of deep learning is the ability to learn automatically. The third work of this paper explores the performance of feature automatic learning of deep learning model in question retrieval and answer sorting tasks. The related work was published at the SemEval Conference on 2016. Inspired by the second and third work of this paper, In the fourth work of this paper, we deeply study the CQA system under the framework of deep learning. In this paper, we propose a deep neural network model based on gate mechanism, which can automatically learn the interactive information between question retrieval and answer sorting tasks. In order to further improve the performance of CQA, this paper extensively and deeply studies the CQA system which adopts the traditional natural language processing technology and the deep learning method, the question retrieval and the answer ranking promote each other. A large number of experimental results show that, The strategies proposed in this paper can effectively improve the performance of CQA systems in both traditional methods and depth learning methods.
【學(xué)位授予單位】：華東師范大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.3

【參考文獻】

相關(guān)期刊論文 前1條

1 熊大平;王健;林鴻飛;;一種基于LDA的社區(qū)問答問句相似度計算方法[J];中文信息學(xué)報;2012年05期

相關(guān)博士學(xué)位論文 前1條

1 王君澤;基于大規(guī)模問答語料的問題檢索系統(tǒng)[D];華中科技大學(xué);2010年

相關(guān)碩士學(xué)位論文 前1條

1 文勖;中文問答系統(tǒng)中問題分類及答案候選句抽取的研究[D];哈爾濱工業(yè)大學(xué);2006年

，

本文編號：1558809