admin 发表于 2024-10-5 07:30:01

稀牛-AI人工智能工程师-NLP必备技能

<p><img src="/data/attachment/forum/images/202382422422611106.png"></p><p>&nbsp;AI人工智能工程师-NLP必备技能主要指的是在自然语言处理(NLP)领域中,作为人工智能工程师应具备的必要技能。这些技能包括但不限于:</p>
<p>自然语言处理基础知识:掌握自然语言处理的基本概念、原理和常用算法,了解语言学的基础知识。</p>
<p>机器学习和深度学习:熟悉常用的机器学习和深度学习算法,并能应用于NLP任务中,如文本分类、情感分析、机器翻译等。</p>
<p>文本表示与向量化:了解和掌握常用的文本表示方法,如词袋模型、TF-IDF、word2vec等,能够将文本数据转化为向量表示。</p>
<p>语言模型和序列模型:熟悉语言模型的概念和常用模型,如N-gram、循环神经网络(RNN)、长短期记忆网络(LSTM)等,并能应用于文本生成、语音识别等任务。</p>
<p>实体识别和关系抽取:了解实体识别和关系抽取的基本方法和算法,能够从文本中提取出命名实体和实体之间的关系。</p>
<p>情感分析和情感推理:熟悉情感分析的方法和技术,能够判断文本中的情感倾向,并进行情感推理。</p>
<p>机器翻译和问答系统:了解机器翻译和问答系统的基本原理和方法,能够实现基于NLP的自动翻译和问答功能。</p>
<p>除了以上的必备技能外,作为AI工程师在NLP领域还需要具备数据处理和清洗、模型评估和调优、算法优化等相关技能。总之,稀牛的AI人工智能工程师-NLP必备技能旨在帮助工程师全面掌握NLP领域的知识和技术,能够应用于实际的项目中。</p>
<p>课程目录</p>
<p>├──01-自然语言处理基础知识与操作&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;├──第二章英文文本处理与解析&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──【实战】nltk工具库英文文本处理案例.mp4&nbsp; 139.99M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──【实战】spacy工具库英文文本处理案例.mp4&nbsp; 413.95M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──【实战】基于python的英文文本相似度比对.mp4&nbsp; 122.75M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──【实战】简易文本情感分析器构建.mp4&nbsp; 34.02M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──英文文本解析任务介绍:分词、去停用词、提取词干等.mp4&nbsp; 69.12M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──章概述.mp4&nbsp; 13.90M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;└──章小结.mp4&nbsp; 24.52M</p>
<p>|&nbsp; &nbsp;├──第三章中文文本处理与解析&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──jieba工具库介绍.mp4&nbsp; 498.41M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──【实战】python新闻网站关键词抽取.mp4&nbsp; 44.70M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──【实战】python中文文本清洗、处理与可视化.mp4&nbsp; 168.51M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──章概述.mp4&nbsp; 7.38M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──章小结.mp4&nbsp; 35.26M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──中文文本处理任务介绍:分词、去停用词、ngram.mp4&nbsp; 209.10M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;└──中文文本解析任务介绍:词性分析、依赖分析等.mp4&nbsp; 151.12M</p>
<p>|&nbsp; &nbsp;└──第一章自然语言处理基础&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──模式匹配与正则表达式.mp4&nbsp; 431.25M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──文本数据、字、词、term.mp4&nbsp; 182.51M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──一章概述.mp4&nbsp; 6.26M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──一章小结.mp4&nbsp; 58.75M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──字符串处理.mp4&nbsp; 370.12M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;└──字符串基本处理与正则表达式文本匹配与替换.mp4&nbsp; 492.86M</p>
<p>├──02-语言模型与应用&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;├──第二章统计语言模型与神经语言模型构建&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──【实战】kenlm工具库使用及语言模型生成.mp4&nbsp; 189.76M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──【实战】基于kenlm的简易拼写纠错.mp4&nbsp; 174.21M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──【实战】基于pytorch的语言模型训练.mp4&nbsp; 247.99M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──基于rnn的神经语言模型.mp4&nbsp; 647.21M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──基于统计的语言模型构建.mp4&nbsp; 220.51M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──章概述.mp4&nbsp; 29.84M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;└──章小结.mp4&nbsp; 102.33M</p>
<p>|&nbsp; &nbsp;├──第一章语言模型与应用&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──ngram应用:词性标注、中文分词、机器翻译与语音识别.mp4&nbsp; 397.08M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──ngram语言模型.mp4&nbsp; 240.13M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──假设性独立与联合概率链规则.mp4&nbsp; 67.24M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──章概述.mp4&nbsp; 25.92M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;└──章小结.mp4&nbsp; 35.46M</p>
<p>|&nbsp; &nbsp;├──考核作业.zip&nbsp; 221.70kb</p>
<p>|&nbsp; &nbsp;└──课件与代码.zip&nbsp; 8.65M</p>
<p>├──03-文本表示&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;├──第二章-文本表示进阶&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──01章概述.mp4&nbsp; 50.13M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──02-预训练在图像领域的应用.mp4&nbsp; 322.03M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──03-elmo基于上下文的word embedding.mp4&nbsp; 319.96M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──04-gpt transformer建模句子信息.mp4&nbsp; 566.71M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──05-bert 预训练双向transformer.mp4&nbsp; 708.94M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──06-基于bert进行fine-tuning.mp4&nbsp; 176.06M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;└──07章小结.mp4&nbsp; 52.20M</p>
<p>|&nbsp; &nbsp;├──第一章-文本词与句的表示&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──01章概述.mp4&nbsp; 36.86M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──02-文本表示概述.mp4&nbsp; 129.10M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──03-文本离散表示:词袋模型与tf-idf.mp4&nbsp; 305.20M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──04-文本分布式表示:word2vec.mp4&nbsp; 279.58M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──05-【实战】python中文文本向量化表示.mp4&nbsp; 121.62M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──06-【实战】基于gensim的中文文本词向量训练与相似度匹配.mp4&nbsp; 286.17M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;└──07章小结.mp4&nbsp; 28.11M</p>
<p>|&nbsp; &nbsp;└──考核作业.zip&nbsp; 61.54kb</p>
<p>├──04-文本分类&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;├──第二章-文本分类深度学习模型与实战&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──01章概述.mp4&nbsp; 5.44M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──02-词嵌入与fine-tuning.mp4&nbsp; 12.72M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──03-基于卷积神经网络的文本分类.mp4&nbsp; 264.69M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──04-基于lstm的文本分类.mp4&nbsp; 123.65M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──05-transformerself-attention介绍.mp4&nbsp; 62.14M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──06-使用tensorflow构建卷积神经网络完成新闻分类.mp4&nbsp; 105.84M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──07-使用tensorflow构建lstm完成影评褒贬分析模型.mp4&nbsp; 10.41M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;└──08章小结.mp4&nbsp; 7.39M</p>
<p>|&nbsp; &nbsp;├──第一章-文本分类机器学习模型与实战&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──01章概述.mp4&nbsp; 55.82M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──02-朴素贝叶斯模型与中文文本分类.mp4&nbsp; 395.33M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──03-逻辑回归 _svm与文本分类.mp4&nbsp; 1.25G</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──04-facebook fasttext原理与操作.mp4&nbsp; 366.85M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──05-【实战】python中文新闻分类.mp4&nbsp; 214.96M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──06-【实战】基于fasttext的文本情感分析.mp4&nbsp; 183.86M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;└──07章小结.mp4&nbsp; 73.19M</p>
<p>|&nbsp; &nbsp;└──考核作业.zip&nbsp; 99.19kb</p>
<p>├──05-文本主题抽取与表示&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;├──第一章-文本主题抽取与表示&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──01章小结.mp4&nbsp; 6.57M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──02-基于tf-idf与text-rank的主题词抽取.mp4&nbsp; 16.35M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──03-监督学习与文本打标签.mp4&nbsp; 6.58M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──04-无监督学习与lda主题模型.mp4&nbsp; 182.60M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──05基于python的中文关键词抽取与可视化.mp4&nbsp; 6.55M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──06-基于lda的新闻主题分析与可视化呈现.mp4&nbsp; 39.47M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;└──07章小结.mp4&nbsp; 7.20M</p>
<p>|&nbsp; &nbsp;└──考核作业.zip&nbsp; 42.93kb</p>
<p>├──06-序列到序列模型&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;├──第一章-序列到序列模型与应用&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──01章概述.mp4&nbsp; 5.78M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──02-从rnn到seq2seq模型.mp4&nbsp; 6.01M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──03-编码解码模型.mp4&nbsp; 12.59M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──04-seq2seq模型详解.mp4&nbsp; 45.24M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──05-注意(attention)机制.mp4&nbsp; 36.38M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──06-tensorflow seq2seq模型使用方法详解.mp4&nbsp; 177.54M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──07-基于seq2seq的文本摘要生成实现.mp4&nbsp; 148.80M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;└──08章总结.mp4&nbsp; 72.69M</p>
<p>|&nbsp; &nbsp;└──考核作业.zip&nbsp; 47.73kb</p>
<p>├──07-文本生成&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;├──第一章-文本生成与自动创作&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──01章概述.mp4&nbsp; 2.42M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──02-基于rnn lstm的语言模型回顾.mp4&nbsp; 10.51M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──03-基于语言模型的文本生成原理.mp4&nbsp; 2.04M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──04-【实战】基于lstm的唐诗生成器.mp4&nbsp; 67.12M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──05-基于seq2seq的文本序列生成原理.mp4&nbsp; 9.20M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──06-【实战】基于seq2seq的对联生成器.mp4&nbsp; 96.68M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;└──07章小结.mp4&nbsp; 14.87M</p>
<p>|&nbsp; &nbsp;└──考核作业.zip&nbsp; 71.06kb</p>
<p>├──08-机器翻译&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;└──第一章-机器翻译:双语翻译&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──01-统计机器翻译&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──02-基于seq2seq的机器翻译模型&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──03-fackbook基于CNN的机器翻译模型&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;└──04-来自Google的Transformer模型&nbsp;&nbsp;</p>
<p>├──09-聊天机器人&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;└──第一章-聊天机器人:机器客服与语音助手&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──01-基于内容匹配的聊天机器人&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;└──02-基于seq2seq的聊天机器人&nbsp;&nbsp;</p>
<p>├──10-视觉文本任务:看图说话&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;├──01-看图说话问题与实现&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──1.1 本章概述.mp4&nbsp; 2.86M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──1.2 &ldquo;看图说话&rdquo;问题介绍.mp4&nbsp; 7.81M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──1.3 简易cnn+rnn编码解码模型完成图片短文本描述原理.mp4&nbsp; 67.26M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──1.4 注意力模型与&ldquo;看图说话&rdquo;优化.mp4&nbsp; 26.76M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──1.5 【实战】基于cnn+rnn的编解码&ldquo;看图说话&rdquo;与beam-search优化.mp4&nbsp; 105.95M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──1.6 【实战】基于attention model的&ldquo;看图说话&rdquo;实现.mp4&nbsp; 27.92M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;└──1.7 本章小结.mp4&nbsp; 1.84M</p>
<p>|&nbsp; &nbsp;└──02-视觉问答机器人(VQA)原理与实现&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──2.1 本章概述.mp4&nbsp; 1.61M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──2.2 视觉问答机器人问题介绍.mp4&nbsp; 34.82M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──2.3 基于图像信息和文本信息抽取匹配的vqa实现方案.mp4&nbsp; 30.93M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──2.4 基于注意力(attention)的深度学习vqa实现方案.mp4&nbsp; 16.18M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──2.5【实战】使用keras完成cnn+rnn基础vqa模型.mp4&nbsp; 24.39M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──2.6【实战】基于attention的深度学习vqa模型实现.mp4&nbsp; 41.58M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;└──2.7 本章小结.mp4&nbsp; 1.67M</p>
<p>└──11-文本相似度计算与文本匹配问题&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;├──01-文本相似度计算与文本匹配问题&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──1.1 本章概述.mp4&nbsp; 5.89M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──1.2 文本相似度问题与应用.mp4&nbsp; 9.06M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──1.3 传统文本相似度计算方式:编辑距离、simhash、word2vec.mp4&nbsp; 148.01M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──1.4 【实战】编辑距离计算python实现.mp4&nbsp; 23.46M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──1.5 【实战】基于simhash的相似文本判断.mp4&nbsp; 62.75M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──1.6 【实战】词向量word averaging.mp4&nbsp; 24.75M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──1.7 本章小结.mp4&nbsp; 2.36M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;└──第1章文本相似度问题与应用场景.pdf&nbsp; 7.49M</p>
<p>|&nbsp; &nbsp;└──02-基于深度学习的文本语义匹配&nbsp;&nbsp;</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──2.1 本章概述.mp4&nbsp; 2.93M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──2.2 基于深度学习的句子相似度模型.mp4&nbsp; 32.12M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──2.3 dssm(deep structured semantic models)模型详解.mp4&nbsp; 20.85M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──2.4 drmm(deep relevance matching model)模型详解.mp4&nbsp; 21.39M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──2.5【实战】基于lstm的监督学习语义表达抽取.mp4&nbsp; 81.31M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──2.6【实战】基于dssm的问题语义相似度匹配案例.mp4&nbsp; 25.91M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──2.7【实战】基于drmm的问答匹配案例.mp4&nbsp; 21.68M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;├──2.8 本章小结.mp4&nbsp; 3.94M</p>
<p>|&nbsp; &nbsp;|&nbsp; &nbsp;└──第2章基于深度学习的文本语义匹配.pdf&nbsp; 7.84M</p>
<div>&nbsp;</div>
页: [1]
查看完整版本: 稀牛-AI人工智能工程师-NLP必备技能