《知識圖譜的自然語言查詢和關鍵字查詢》是2019年電子工業出版社出版的圖書，作者是胡新。
基本介紹
- 書名：知識圖譜的自然語言查詢和關鍵字查詢
- 作者：胡新
- 出版社：電子工業出版社
- ISBN：9787121354298
內容簡介,圖書目錄,
內容簡介
知識圖譜的自然語言查詢和關鍵字查詢是知識問答中較有前景的兩種知識圖譜查詢方式。知識圖譜是一種結構化的語義知識庫，以圖的方式展現“實體”、實體的“屬性”，以及實體與實體之間的“關係”。知識圖譜的自然語言查詢和關鍵字查詢，使搜尋引擎不僅能返回與查詢相關的網頁，而且能返回智慧型化的答案。本書介紹知識圖譜的自然語言查詢和關鍵字查詢，包括自然語言查詢中的語義關係識別、自然語言聚集查詢、SPARQL 和關鍵字相結合的自然語言查詢、關鍵字查詢等。本書可供高等院校計算機、人工智慧、大數據等相關專業研究生和高年級本科生參考閱讀，也可供知識工程領域的技術人員參考閱讀。
圖書目錄
章 緒論·································．1
1．1 研究背景及意義··················．1
1．2 研究現狀···························．3
1．2．1 知識圖譜自然語言查詢的
研究現狀························3
1．2．2 知識圖譜關鍵字查詢的
研究現狀························4
1．3 存在的關鍵問題··················．5
1．4 研究內容及創新點···············．7
1．5 本書組織結構·····················10
第2 章 自然語言查詢和關鍵字查詢的
相關研究···························12
2．1 知識圖譜的自然語言查詢······12
2．1．1 語義關係識別················．12
2．1．2 自然語言聚集查詢···········．13
2．1．3 查詢映射·····················．14
2．1．4 多樣化的自然語言查詢······．15
2．2 知識圖譜的關鍵字查詢·········16
2．2．1 模式圖························．16
2．2．2 多樣化的關鍵字查詢········．17
2．3 兩種查詢共用的基礎技術······19
2．3．1 實體識別和實體連結········．19
2．3．2 解釋詞典·····················．19
2．4 眾包—輔助語義關係識別規則
挖掘·································20
2．5 知識圖譜的其他非結構化
查詢方式···························21
2．5．1 互動式查詢···················．21
2．5．2 實例查詢和樣例查詢········．22
第3 章 基於眾包的自然語言查詢中
語義關係識別規則挖掘·········23
3．1 問題描述及創新點···············23
3．2 眾包模型···························24
3．2．1 疊代模型和並行模型········．25
3．2．2 疊代式並行模型和
並行式疊代模型·············．25
3．2．3 帶反饋的並行式疊代模型···．26
3．3 生成語義關係數據集和
依賴結構數據集··················27
3．3．1 眾包模型標記語義關係·····．27
3．3．2 Stanford Parser 生成依賴
結構··························．27
3．4 挖掘語義關聯規則···············28
3．4．1 挖掘語義關聯規則的算法···．28
3．4．2 算法MSAR 的複雜度·······．30
3．5 實驗結果及分析—眾包模型··31
3．5．1 實驗數據及評估標準········．31
3．5．2 疊代模型和並行模型········．32
3．5．3 疊代式並行模型和並行式
疊代模型·····················．33
3．5．4 帶反饋的並行式疊代模型···．35
3．6 實驗結果及分析—語義關聯
規則·································36
3．7 語義關係識別·····················38
3．7．1 語義關係識別的算法········．38
3．7．2 算法SRR 的複雜度··········．39
3．7．3 實驗結果及分析—語義關係
識別··························．39
3．8 本章小結···························40
第4 章 知識圖譜的自然語言聚集
查詢·································42
4．1 問題描述及創新點···············42
4．2 查詢流程···························45
4．3 查詢理解···························45
4．3．1 意圖解釋·····················．45
4．3．2 依賴結構分類················．46
4．3．3 從依賴結構中識別意圖解釋·．47
4．3．4 查詢理解的最佳化·············．49
4．3．5 算法AIII 的複雜度··········．49
4．4 構建基本圖模式··················50
4．4．1 擴展的解釋詞典ED ·········．50
4．4．2 短語映射·····················．51
4．4．3 謂詞-類型鄰近集PT ·········．51
4．4．4 謂詞-謂詞鄰近集PP ·········．53
4．4．5 語義關係映射················．53
4．4．6 算法SRM 的複雜度·········．55
4．4．7 構建基本圖模式BGP········．56
4．4．8 算法BBGP 的複雜度········．57
4．5 將基本圖模式翻譯為
SPARQL 語句·····················58
4．5．1 數值型謂詞···················．58
4．5．2 翻譯基本圖模式·············．59
4．5．3 翻譯聚集·····················．59
4．5．4 算法TA 的複雜度···········．61
4．6 實驗結果及分析··················61
4．6．1 實驗數據集···················．61
4．6．2 各階段的最佳化能力···········．61
4．6．3 算法的有效性················．63
4．6．4 與現有算法對比·············．65
4．6．5 回答錯誤的原因·············．66
4．7 相關問題及解決方案············67
4．8 本章小結···························69
第5 章 知識圖譜的自然語言查詢—
SPARQL 和關鍵字··············70
5．1 問題描述及創新點···············70
5．2 查詢流程···························71
5．3 SPARQL 語句的生成過程······72
5．4 查詢分解···························73
5．4．1 查詢理解階段················．73
5．4．2 查詢映射階段················．74
5．4．3 執行SPARQL 階段··········．74
5．4．4 查詢分解算法················．75
5．4．5 算法DQ 的複雜度···········．76
5．5 構建關鍵字索引··················77
5．5．1 算法QUKI ···················．77
5．5．2 算法QUKI 的複雜度········．78
5．6 聚合SPARQL 結果子圖和
關鍵字查詢························78
5．6．1 算法CSK ····················．78
5．6．2 算法CSK 的複雜度·········．80
5．7 實驗結果及分析··················81
5．7．1 算法的有效性················．81
5．7．2 回答正確的原因·············．83
5．7．3 回答錯誤的原因·············．84
5．7．4 以SPARQL 查詢為主導的
優勢··························．85
5．7．5 關鍵字索引的效率···········．85
5．8 本章小結···························86
第6 章 知識圖譜的關鍵字聚集查詢···88
6．1 問題描述及創新點···············88
6．2 查詢流程···························90
6．3 構建類型-謂詞圖·················90
6．3．1 關係提取·····················．90
6．3．2 關係標準化··················．91
6．3．3 類型-謂詞圖··················．92
6．4 查詢理解···························92
6．5 基於類型-謂詞圖構建
查詢圖······························94
6．5．1 查詢圖························．94
6．5．2 構建查詢圖··················．94
6．5．3 算法BQG 的複雜度·········．99
6．6 將查詢圖翻譯為SPARQL
語句·································99
6．6．1 數值型謂詞···················．99
6．6．2 翻譯一般路徑················．99
6．6．3 翻譯聚集·····················100
6．6．4 算法TQGS 的複雜度········102
6．7 實驗結果及分析···············．102
6．7．1 算法的有效性················102
6．7．2 輸入的可擴展性·············104
6．7．3 數據集的可擴展性···········106
6．7．4 組件的有效性················106
6．8 本章小結························．108
第7 章 總結與展望·····················．109
7．1 總結······························．109
7．2 展望······························．111
參考文獻····································．112
