数据科学技术:文本分析和知识图谱
正版保障 假一赔十 可开发票
￥ 85.14 6.6折 ￥ 129 全新
库存22件
广东广州
认证卖家担保交易快速发货售后保障
作者苏海波[等]著
出版社清华大学出版社
ISBN9787302649700
出版时间2024-01
装帧平装
开本其他
定价129元
货号14871240
上书时间2024-10-22
商品详情
- 品相描述：全新
- 商品描述
-
作者简介
"苏海波，清华大学电子工程系博士，副研究员，百分点科技首席算法科学家。擅长人工智能领域的自然语言理解、知识图谱、深度学习、个性化推荐以及计算广告技术，有丰富的研发实践经验；曾就职于新浪微博，负责广告系统的算法效果优化，以及信息流产品整体算法策略的设计及研发；现负责百分点大数据与人工智能核心算法，带领团队研发智能校对系统、智能问答系统、知识图谱系统等多款认知智能产品，荣获业界多项奖项，并获得不错的商业化落地效果。 多篇SCI和EI论文发表于 GLOBECOM、ICC、IEICE Transactions 等国外很好学术会议和期刊，获得国家发明专利20余项，曾担任科技部重点研发计划子课题负责人。获得2019年和2020年北京市科学技术进步奖，获得2019年全球人工智能与机器学习大会（AiCon）明星讲师，指导团队获得2021 CCKS（全国知识图谱与语义计算大会）知识图谱问答大赛的季军。"
目录
第1章 什么是数据科学 ························1 1.1 数据科学的定义 ···························1 1.1.1 数据科学的背景 ···················1 1.1.2 数据科学的定义 ···················1 1.2 数据科学的关键技术 ·····················3 1.2.1 数据存储计算 ·····················5 1.2.2 数据治理 ························· 12 1.2.3 结构化数据分析 ················ 28 1.2.4 语音分析 ························· 44 1.2.5 视觉分析 ··························55 1.2.6 文本分析 ··························61 1.2.7 知识图谱 ························· 65 1.3 本章小结 ·································· 65 1.4 习题 ········································ 66 1.5 本章参考文献 ···························· 66 第2章 文本预训练模型······················ 68 2.1 文本分析技术的发展史 ················ 68 2.2 Transformer模型结构 ·················· 70 2.3 预训练模型的结构和变种 ··············75 2.4 加速处理器GPU和TPU ················ 79 2.4.1 GPU的介绍 ······················ 79 2.4.2 GPU产品命名 ··················· 80 2.4.3 TPU和GPU的区别 ·············· 83 2.4.4 TPU的使用总结 ················· 84 2.5 预训练模型的常见问题 ················· 87 2.5.1 模型输入的常见问题 ··········· 87 2.5.2 模型原理的常见问题 ··········· 90 2.5.3 模型进化的常见问题 ··········· 94 2.6 预训练模型的源码解读 ················ 96 2.6.1 模型架构 ························· 96 2.6.2 BertModel ························ 96 2.6.3 BERT预训练任务 ·············· 107 2.6.4 BERT 微调 ······················ 112 2.7 本章小结 ································· 114 2.8 习题 ······································· 114 2.9 本章参考文献 ··························· 115 第3章 多语种文本分析 ·····················116 3.1 多语种文本分析背景介绍 ············· 116 3.2 多语种文本分析技术 ··················· 116 3.2.1 Polyglot技术 ···················· 116 3.2.2 Multilingual BERT ············ 117 3.2.3 XLM多语言模型 ··············· 117 3.2.4 XLMR多语言模型 ············· 119 3.2.5 模型实验效果 ·················· 120 3.3 多语种文本分析源码解读 ············· 121 3.4 本章小结 ································· 125 3.5 习题 ······································· 126 3.6 本章参考文献 ··························· 126 第4章 文本情感分析 ························127 4.1 情感分析背景介绍 ····················· 127 4.2 情感分析技术 ··························· 127 4.2.1 目标和挑战 ····················· 127 4.2.2 技术发展历程 ·················· 129 4.2.3 情感分析的需求分析 ·········· 133 4.2.4 情感分析的落地实践 ·········· 134 4.2.5 模型开发平台的构建 ·········· 137 4.3 情感分析比赛和方案 ·················· 144 4.3.1 背景介绍 ························ 144 4.3.2 方案介绍 ························ 146 4.3.3 数据清洗和增广 ··············· 147 4.3.4 多模态融合 ····················· 147 4.3.5 机器学习技巧 ·················· 148 4.4 情感分析源码解读 ····················· 151 4.4.1 F1值适应优化技巧代码 ······· 151 4.4.2 对抗训练代码 ·················· 152 4.5 本章小结 ································· 154 4.6 习题 ······································· 154 4.7 本章参考文献 ··························· 155 第5章 文本机器翻译 ·······················156 5.1 机器翻译背景介绍 ····················· 156 5.2 机器翻译技术 ··························· 157 5.2.1 基于规则的机器翻译 ·········· 157 5.2.2 统计机器翻译 ·················· 158 5.2.3 神经网络机器翻译 ············ 159 5.2.4 Encoder-Decoder模型 ········· 161 5.2.5 注意力机制模型 ··············· 162 5.2.6 工业级神经网络实践 ·········· 164 5.3 机器翻译比赛和方案 ·················· 167 5.3.1 WMT21翻译任务 ·············· 167 5.3.2 WMT22 翻译任务 ············· 168 5.4 机器翻译源码解读 ····················· 169 5.4.1 通用框架介绍 ·················· 169 5.4.2 翻译模型实现 ·················· 170 5.5 本章小结 ································· 180 5.6 习题 ······································· 181 5.7 本章参考文献 ··························· 181 第6章 文本智能纠错 ·······················183 6.1 文本纠错背景介绍 ····················· 183 6.2 文本智能纠错技术 ····················· 184 6.2.1 智能纠错的意义和难点 ······· 185 6.2.2 智能纠错解决的问题 ·········· 185 6.2.3 业界主流解决方案 ············ 186 6.2.4 技术方案实践 ·················· 190 6.3 文本智能纠错技术 ···················· 193 6.3.1 比赛介绍 ························ 193 6.3.2 校对问题思考 ·················· 194 6.4 纠错方案和源码解读 ·················· 195 6.4.1 GECToR原理解读 ············· 195 6.4.2 MacBERT原理解读 ··········· 199 6.4.3 PERT原理解读 ·················200 6.4.4 PLOME原理解读 ··············202 6.4.5 比赛方案 ························ 203 6.5 本章小结 ·································204 6.6 习题 ······································· 205 6.7 本章参考文献 ··························· 205 第7章 知识图谱构建 ······················ 206 7.1 知识图谱背景介绍 ·····················206 7.1.1 知识和知识图谱 ················206 7.1.2 知识获取、知识抽取与信息抽取 的区别····························207 7.1.3 知识图谱构建范式 ·············208 7.2 非结构化信息抽取技术 ··············· 211 7.2.1 信息抽取框架 ··················· 211 7.2.2 命名实体识别··················· 212 7.2.3 关系识别 ························ 213 7.2.4 事件抽取 ························ 215 7.3 生成式统一模型抽取技术 ············ 216 7.4 模型源码解读 ···························220 7.5 本章小结 ·································224 7.6 习题 ·······································224 7.7 本章参考文献 ··························· 225 第8章 知识图谱问答 ······················ 226 8.1 背景介绍 ································· 226 8.2 知识图谱问答技术 ····················· 229 8.2.1 信息检索方法 ·················· 229 8.2.2 语义解析方法 ·················· 231 8.3 方案和源码解读 ························ 233 8.3.1 NL2SPARQL ··················· 233 8.3.2 NL2SPARQL语义解析方案 ··· 234 8.3.3 T5、BART、UniLM模型简介 ··· 234 8.3.4 T5、BART、UniLM方案 ······ 236 8.3.5 训练T5、BART、UniLM 生成模型 ······················· 237 8.3.6 语义排序方案和代码 ·········· 239 8.3.7 SPARQL修正代码 ············· 241 8.4 本章小结 ································· 245 8.5 习题 ······································· 245 第9章 结构化知识NL2SQL问答 ·········246 9.1 NL2SQL背景介绍 ······················246 9.2 NL2SQL技术 ··························· 249 9.2.1 NL2SQL技术路线 ············· 249 9.2.2 NL2SQL项目实践 ············· 255 9.3 NL2SQL比赛和方案 ··················· 256 9.4 NL2SQL源码解读 ······················ 259 9.5 本章小结 ································· 269 9.6 习题 ······································· 269 9.7 本章参考文献 ··························· 270 第10章 ChatGPT大语言模型 ·············271 10.1 ChatGPT介绍 ·························· 271 10.1.1 ChatGPT的定义和背景 ······ 271 10.1.2 ChatGPT的发展历程 ········· 272 10.2 GPT模型概述·························· 272 10.2.1 GPT-1模型的原理 ············ 272 10.2.2 GPT-2模型的原理 ············ 273 10.2.3 GPT-3模型的原理 ············ 275 10.3 ChatGPT的实现原理 ················· 277 10.3.1 大模型的微调技术 ··········· 277 10.3.2 ChatGPT的能力来源 ········ 278 10.3.3 ChatGPT的预训练和微调 ··· 279 10.4 ChatGPT的应用 ······················· 282 10.4.1 ChatGPT提示工程 ··········· 282 10.4.2 ChatGPT应用场景 ··········· 283 10.4.3 ChatGPT的优缺点 ···········284 10.5 开源大模型 ···························· 285 10.5.1 ChatGLM大模型 ············· 285 10.5.2 LLaMA大模型 ················ 288 10.6 本章小结································ 294 10.7 习题······································ 294 10.8 本章参考文献·························· 295 第11章 行业实践案例 ····················· 296 11.1 智慧政务实践案例 ···················· 296 11.1.1 案例背景 ······················· 296 11.1.2 解决方案 ······················· 297 11.1.3 系统架构和实现 ·············· 299 11.1.4 案例总结 ······················· 307 11.2 公共安全实践案例 ····················308 11.2.1 案例背景 ·······················308 11.2.2 解决方案 ·······················309 11.2.3 系统架构及实现 ·············· 311 11.2.4 案例总结 ······················· 317 11.3 智能应急实践案例 ···················· 318 11.3.1 案例背景 ······················· 319 11.3.2 解决方案 ······················· 320 11.3.3 系统架构及实现 ·············· 321 11.3.4 案例总结 ······················· 332 11.4 本章小结 ································ 334 11.5 习题······································ 334
主编推荐
《数据科学技术：文本分析和知识图谱》是一本深入浅出的数据科学技术指南。书中详细介绍了文本分析和知识图谱等关键技术，结合典型案例展示了数据科学在安全、应急等行业的应用实践。无论你是数据科学领域的专业人士还是对数据科学感兴趣的读者，这本书都能帮助你深入了解数据科学的基本概念、方法和近期新技术。通过学习《数据科学技术：文本分析和知识图谱》，你将能够掌握数据科学的核心知识，为自己的职业发展和创新项目提供有力支持。
精彩内容
数据科学的关键技术包括数据存储计算、数据治理、结构化数据分析、语音分析、视觉分析、文本分析和知识图谱等方面。本书的重点是详细介绍文本分析和知识图谱方面的技术。文本分析技术主要包括文本预训练模型、多语种文本分析、文本情感分析、文本机器翻译、文本智能纠错、NL2SQL问答以及ChatGPT大语言模型等。知识图谱技术主要包括知识图谱构建和知识图谱问答等。本书将理论介绍和实践相结合，详细阐述各个技术主题的实现路线，并对应用于业界算法大赛中的技术方案和技巧进行源代码解读，帮助读者深入理解技术原理。最后，本书还介绍了文本分析和知识图谱技术在政务、公共安全、应急等多个行业中的智能应用实践案例。 《数据科学技术：文本分析和知识图谱》适合具备Python和机器学习技术基础的高等院校学生、文本分析（或者自然语言处理）以及知识图谱领域的算法工程师和研究机构的研究者阅读，也适合数据科学和人工智能领域的研究者作为参考书。
— 没有更多了 —
以下为对购买帮助不大的评价