短文本表示建模及應用

定　價：￥78.00

作　者：	王亞珅黃河燕著
出版社：	北京理工大學出版社
叢編項：
標　簽：	暫缺

購買這本書可以去

ISBN：	9787568298872	出版時間：	2022-02-01	包裝：	平裝-膠訂
開本：	16開	頁數(shù)：		字數(shù)：

內(nèi)容簡介

　　短文本表示建模，通常是指將短文本轉化成機器可以詮釋的形式，旨在幫助機器“理解”短文本的含義。本書詳細介紹了短文本表示建模研究體系中具有代表性的短文本概念化表示建模研究分支和短文本向量化表示建模研究分支的相關研究方法，既涵蓋了大量經(jīng)典算法，又特別引入了近年來在該領域研究中涌現(xiàn)出的新方法、新思路，力求兼顧內(nèi)容的基礎性和前沿性。同時，本書融入了作者多年來從事以概念化和向量化為核心的短文本表示建模方法與理論研究的經(jīng)驗和成果，并以短文本檢索這一典型應用問題為例，詳細介紹了如何把短文本概念化表示建模方法和短文本向量化表示建模方法以及先進的設計思想融入具體應用問題的求解。本書可供計算機、信息處理、自動化、系統(tǒng)工程、應用數(shù)學等專業(yè)的教師以及相關領域的研究人員和技術開發(fā)人員參考。

作者簡介

　　王亞珅，博士，高級工程師，2012年畢業(yè)于北京理工大學計算機學院獲學士學位，2018年畢業(yè)于北京理工大學計算機學院獲博士學位，目前任社會安全風險感知與防控大數(shù)據(jù)應用國家工程實驗室知識智能室主任，研究方向包括自然語言處理、知識工程、社交網(wǎng)絡分析等。獲2018年中國博士后科學基金會第64批面上資助等，主持中國電科集團新一代人工智能專項行動計劃項目“基于大數(shù)據(jù)智能的立體化社會治安防控”等。獲2018年人工智能學會優(yōu)秀博士學位論文獎等。任中國人工智能學會青年工作委員會成員、會員，《無人系統(tǒng)技術》期刊青年編委。近五年，以作者身份發(fā)表TKDE、TKDD、ACL、WWW等會議/期刊論文20余篇，以完成人身份受理發(fā)明專利20余項。

圖書目錄

第1 章緒論···················································································· 1
1.1 研究背景及意義 ······································································· 1
1.2 基本定義及問題描述 ································································· 2
1.3 研究問題圖解 ·········································································· 6
1.4 本書內(nèi)容組織結構 ···································································· 7
第2 章理論與技術基礎 ····································································· 9
2.1 分布假說 ················································································ 9
2.2 向量空間模型 ········································································ 10
2.3 詞頻 − 逆文檔頻率 ·································································· 10
2.4 鏈接分析 ··············································································· 11
2.5 馬爾可夫隨機場 ····································································· 15
2.6 參數(shù)分布估計 ········································································ 17
2.7 詞語向量化 ··········································································· 20
2.8 語言模型 ·············································································· 24
2.9 數(shù)據(jù)平滑算法 ········································································ 26
2.10 模型求解算法 ······································································ 28
2.11 向量語義相似度計算 ······························································ 32
2.12 查詢擴展 ············································································· 34
第3 章面向短文本表示建模的知識庫資源 ··········································· 37
3.1 引言 ···················································································· 37
3.2 百科類知識庫資源 ·································································· 37
3.3 詞匯語義知識庫資源 ······························································· 41
3.4 知識庫資源對比分析 ······························································· 46
第4 章顯式語義建模 ······································································ 48
4.1 引言 ···················································································· 48
4.2 顯式語義分析模型 ·································································· 48
4.3 概念化模型 ··········································································· 49
4.4 顯式語義建模總結分析 ···························································· 51
第5 章半顯式語義建模 ··································································· 52
5.1 引言 ···················································································· 52
5.2 概率化潛在語義分析模型 ························································· 52
5.3 潛在狄利克雷分布模型 ···························································· 53
5.4 層次化狄利克雷過程模型 ························································· 54
5.5 半顯式語義建?？偨Y分析 ························································· 58
第6 章隱式語義建模 ······································································ 59
6.1 引言 ···················································································· 59
6.2 潛在語義分析模型 ·································································· 59
6.3 神經(jīng)網(wǎng)絡語言模型 ·································································· 61
6.4 CBOW 模型和Skip-Gram 模型 ··················································· 65
6.5 隱式語義建模總結分析 ···························································· 67
第7 章短文本概念化表示建模 ·························································· 68
7.1 引言 ···················································································· 68
7.2 問題描述 ·············································································· 68
7.3 短文本概念化方法 ·································································· 69
7.4 短文本概念化方法總結分析 ······················································ 95
7.5 本章小結 ············································································· 105
第8 章短文本向量化表示建模 ························································· 107
第9 章概念化和向量化在短文本檢索問題中的應用 ······························ 149
第10 章總結與展望 ······································································ 200
參考文獻 ······················································································· 204