- 11 411 181004 12 CFParsing
- 11-4_611 NLP (2019-10-08) Lecture 13
- 11-411 2018 08 30 15 00 21 Applications
- 11-411 2018-08-28 01 Intro
- 11-411 2018-09-06 Morphology
- 11-411 2018-09-18 Classification
- 11-411 2018-09-27 Syntax
- 11-411_11-611 (2020_04_21) Lecture 25 - Deep Learning
- 11-411_11-611 (2020_04_23) Lecture 26 - Machine Translation
- 11-411_11-611 (2020_04_28) Lecture 27 - Interpreting Social Media
- 11-411_11-611 (2020_14_04) Lecture 28 - Multimodality
- 11-411_11-611 Applications 2019-01-17
- 11-411_11-611 Compositional semantics semantic parsing 2018-11-01
- 11-411_11-611 Discourse 2018-11-06
- 11-411_11-611 Machine Translation 2018-11-29
- 11-411_11-611 NLP (2019-01-29) - Lecture 5. Language Models and Smoothing
- 11-411_11-611 NLP (2019-02-05) - Lecture 6. Information Theory
- 11-411_11-611 NLP (2019-02-07) - Lecture 7. Classification
- 11-411_11-611 NLP (2019-02-12) - Lecture 8. Part of Speech Tags
- 11-411_11-611 NLP (2019-02-14) - Lecture 9. Hidden Markov Models
- 11-411_11-611 NLP (2019-02-19) - Lecture 10. Syntactic representations of natura
- 11-411_11-611 NLP (2019-02-21) - Lecture 11. Chomsky Hierarchy
- 11-411_11-611 NLP (2019-02-28) - Lecture 13. CFG Parsing Part II & Beyond CFG Pa
- 11-411_11-611 NLP (2019-03-05) - Lecture 14. Treebanks & PCFG
- 11-411_11-611 NLP (2019-03-19) - Lecture 16. Lexical Semantics
- 11-411_11-611 NLP (2019-03-21) - Lecture 17. Embeddings
- 11-411_11-611 NLP (2019-03-26) - Lecture 18. MRLs_Semantic Roles
- 11-411_11-611 NLP (2019-03-26) - Lecture 19. Compositional Semantics and Semanti
- 11-411_11-611 NLP (2019-04-02) - Lecture 20. Semantic Disambiguation
- 11-411_11-611 NLP (2019-08-27) - Lecture 1. Introduction
- 11-411_11-611 NLP (2019-08-29) - Lecture 2. Applications
- 11-411_11-611 NLP (2019-09-03) - Lecture 3. Project
- 11-411_11-611 NLP (2019-10-31) - Lecture 19. Compositional Semantics and Semanti
- 11-411_11-611 NLP (2019-11-07) - Lecture 21. Sentiment Analysis & Computational
- 11-411_11-611 Project (Question & Answering) 2019-01-22
- 11-411_11-611 S19 Introduction
- 11-411_11-611 Vector Semantics 2018-10-25
- 11-411_11-611 Verb_sentence semantics 2018-10-30
- 11-411_11-611 WSD_SRL 2018-11-08
- 11-411_611 Deep Learning 2018-12-04
- 11-411_611 09_25 09 HMM
- 11-411_611 2018 09_11 lm Language models and smoothing
- 11-411_611 2018-10-09 13 Parsing algorithms
- 11-411_611 2018-10-11 14 Advanced Parsing
- 11-411_611 2018-10-23 Lexical Semantics
- 11-411_611 Conclusions 2018-12-06
- 11-411_611 NLP (2019_11_12) - Lecture 22 - Speech 1
- 11-411_611 NLP (2019_11_14) - Lecture 23 - Speech 2 (1_2)
- 11-411_611 NLP (2019_11_14) - Lecture 23 - Speech 2 (2_2)
- 11-411_611 NLP (2019_11_21) - Lecture 25 - Social Media Analysis (Guest Lecture)
- 11-411_611 NLP (2019_11_26) - Lecture 26 - Machine Translation (1_2)
- 11-411_611 NLP (2019_11_26) - Lecture 26 - Machine Translation (2_2)
- 11-411_611 NLP (2019_12_03) - Lecture 27 - Deep Learning for NLP (guest lecture)
- 11-411_611 NLP (2019-09-05) Lecture 4 - Words and morphology
- 11-411_611 NLP (2019-09-10) Lecture 5 - Language modeling and smoothing
- 11-411_611 NLP (2019-09-12) Lecture 6 - Information theory and noisy channels
- 11-411_611 NLP (2019-10-03) Lecture 12
- 11-411_611 NLP (2020_01_14) - Lecture 1 - Intro and Course Overview
- 11-411_611 NLP (2020_01_16) - Lecture 2 - Applications of NLP
- 11-411_611 NLP (2020_01_21) - Lecture 3 - Project
- 11-411_611 NLP (2020_01_23) - Lecture 4 - Words Morphology and Lexicons (Part 1
- 11-411_611 NLP (2020_01_23) - Lecture 4 - Words Morphology and Lexicons (Part 2
- 11-411_611 NLP (2020_01_28) - Lecture 5 - Language Model
- 11-411_611 NLP (2020_01_28) - Lecture 6 - Noisy channel and edit distance
- 11-411_611 NLP (2020_02_04) - Lecture 7 - Parts of Speech
- 11-411_611 NLP (2020_02_06) - Lecture 8 - HMM
- 11-411_611 NLP (2020_02_11) - Lecture 9 - Classification 1
- 11-411_611 NLP (2020_02_13) - Lecture 10 - Classification - II
- 11-411_611 NLP (2020_02_13) - Lecture 11 -Syntax
- 11-411_611 NLP (2020_02_20) - Lecture 12 - Chomsky Hierarchy
- 11-411_611 NLP (2020_02_25) - Lecture 13 - Context free recognition and parsing
- 11-411_611 NLP (2020_02_27) - Lecture 14 - Parsing algorithms
- 11-411_611 NLP (2020_03_03) - Lecture 15 - Treebanks and PCFGs
- 11-411_611 NLP (2020_03_24) - Lecture 17 - Word embeddings_vector semantics
- 11-411_611 NLP (2020_03_26) - Lecture 18 - Verb_sentence semantics
- 11-411_611 NLP (2020_03_31) - Lecture 19 - Compositional Semantics
- 11-411_611 NLP (2020_04_02) - Lecture 20 - Discourse entity linking pragmatics
- 11-411_611 NLP (2020_04_07) - Lecture 21 - Sentiment Analysis and Computational
- 11-411_611 NLP (2020_04_07) - Lecture 22 - Speech 1
- 11-411_611 NLP (2020_04_16) - Lecture 24 - Non-English NLP
- 11-411_611 NLP(2019-02-26) -Lecture 12 CF parsing
- 11-411_611 NLP(2019-09-24) Lecture 8 Classification 1
- 11-411_611 NLP(20190926) Lecture 9 Classification 2
- 11-411_611 Social Media 2018-11-27
- 11-411_611 Speech I 2018-11-13
- 11-411_611 Speech II 2018-11-15
- 27 - NLP for Languages Other than English
- 2018 09 20 15 04 55
- 2018 10 02 15 03 40
- 2018 11 20 15 06 59
- 2019 04 04 15 02 41
- 2019 04 09 15 01 29
- 2019 04 16 15 02 11
- 2019 04 18 15 00 50
- 2020 11 24 11 411 Deep Learning
- 2020-09-01 Introduction
- 2020-09-03 Applications of NLP
- 2020-09-08 Project
- 2020-09-10 Words and Morphology
- 2020-09-15 Language Models and Smoothing
简介:随着人工智能的快速发展,自然语言处理应用愈加广泛。本课首先对其发展历程、现状、技术体系、开发环境等概述。然后从数据准备、可视化、KNN算法模型、实际应用、sklearn算法改进等方面进行实战,旨在帮助大家轻松入门。
自然语言处理是计算机科学与技术专业的一门专业选修课。它的主要任务是使学生了解自然语言处理的主要研究内容及关键技术,并介绍自然语言处理方面的研究成果,为学生从事自然语言处理研究和开发做准备。此外,通过指导学生阅读计算语言学专业会议的论文,进行摘要和评价,并进行介绍、提问和讨论,使他们对所学课程的有关概念与目前的流行方法和技术的关系有更深入地了解。在此基础上,要求学生完成一篇有关自然语言处理主题的课程项目,使他们能用所学的知识发挥自身的能力查找有关资料和概括某一研究领域的国内外最新理论和技术并最终加以实践。
主要教学内容
主要包含三个重要部分:自然语言处理综述、语言模型(N-gram语言模型)、序列标注问题(Sequence labelling problem)、句法分析、语义分析、情感分析、词向量等。其中:自然语言处理综述主要介绍人工智能发展历史综述,不同领域自然语言处理应用问题及方法等,自然语言处理基本技术方法概述,其中包括部分机器学习知识,自然语言处理层次架构,具体任务介绍,歧义问题,经验主义方法等;语言模型主要包括自然语言处理相关语言模型基础理论以及相关平滑处理技术等(如N-Gram;链式规则Chain Rule等);序列标注问题(Sequence labelling problem)主要知识点包括序列标注学习极其相关应用等(如离散/连续马尔科夫模型、中文分词、词性标注、命名实体识别等);句法分析主要包括自然语言中语法分析等基础理论知识等(如上下文无关文法、自上而下句法分析、概率上下文无关文法、最大似然训练、依存语法树等);语义分析主要主要知识点包括自然语言中语义分析等基础理论知识等(如语义角色、语义角色标注、基于句法树方法等);情感分析(Sentiment Analysis)主要包括情感分析技术理论与方法等(如感情倾向性分析等);词向量主要包括基于神经网络的自然语言处理技术与基础理论知识等(如Word2vec词向量、基于循环神经网络语言模型等)。力求跟踪自然语言处理的发展脉络、技术理论、产业成果并以翔实的形态进行展现教学。