KA213001 Natural Language Processing

Hiroshima University Syllabus

Japanese

Academic Year 2024Year School/Graduate School School of Informatics and Data Science

Lecture Code KA213001 Subject Classification Specialized Education

Subject Name 自然言語処理

Subject Name
（Katakana）シゼンゲンゴショリ

Subject Name in
English Natural Language Processing

Instructor EGUCHI KOJI

Instructor
(Katakana) エグチ　コウジ

Campus Higashi-Hiroshima Semester/Term 3rd-Year, First Semester, 2Term

Days, Periods, and Classrooms (2T) Weds1-4：ENG 103

Lesson Style Lecture Lesson Style
(More Details) 　

This course will mainly consist of lectures.

Credits 2.0 Class Hours/Week 　 Language of Instruction B : Japanese／English

Course Level 3 : Undergraduate High-Intermediate

Course Area（Area） 25 : Science and Technology

Course Area（Discipline） 02 : Information Science

Eligible Students Undergraduate Level

Keywords Natural language processing, Language modeling, Word embedding, Text classification, Information retrieval, and Information extraction.

Special Subject for Teacher Education 　 Special Subject 　

Class Status
within Educational
Program
(Applicable only to targeted subjects for undergraduate students)
Criterion referenced
Evaluation
(Applicable only to targeted subjects for undergraduate students) Computer Science Program
（Knowledge and Understanding）
・D1. Knowledge and ability to understand the theoretical framework underlying computer science and to collect and process high-dimensional data through full use of information processing technology based on scientific logic.

Data Science Program
（Abilities and Skills）
・A. Information infrastructure development technology, information processing technology, technology that analyzes data and creates new added value.

Intelligence Science Program
（Knowledge and Understanding）
・D1. A deep systematic understanding of the advanced intelligence of human beings and its realization by computers.
（Abilities and Skills）
・D2. Information processing ability and data analysis ability to contribute to the application and development of artificial intelligence and IoT.

Class Objectives
/Class Outline Course Objectives:
- To develop basic skills required for handling human languages via computers.
- To learn basic techniques and theories related to natural language processing.
- To understand typical applications of natural language processing to gain practical skills on real-world problems.

Course Outline:
A lot of intelligent human activities are supported by natural languages, such as Japanese and English. Techniques for handling and analyzing such natural languages are referred to as natural language processing. This course covers statistical and machine learning approaches to address disambiguation in natural languages. We also learn some applications, such as text classification, information retrieval, information extraction, and natural language generation. This course further overviews four stages of natural language processing: morphological analysis, syntactic analysis, semantic analysis, and context analysis.

Class Schedule lesson 1: Introduction to natural language processing
lesson 2: Basics of character codes and text processing
lesson 3: Morphological analysis
lesson 4: Statistical analysis and language models
lesson 5: Text classification and Naïve Bayes
lesson 6: Information retrieval
lesson 7: Web retrieval
lesson 8: Word senses
lesson 9: Neural networks and word embedding
lesson 10: Information extraction
lesson 11: Sequence to sequence models and large language models
lesson 12: Syntactic parsing (1)
lesson 13: Syntactic parsing (2)
lesson 14: Semantic parsing and context analysis
lesson 15: Clustering

Basically, exercises are conducted every week.

Text/Reference
Books,etc. Handouts will be provided. No textbooks will be required for this course.
Reference books will be introduced in the lectures.

PC or AV used in
Class,etc. 　

(More Details) PDF handouts and video materials will be provided.

Learning techniques to be incorporated 　

Suggestions on
Preparation and
Review Handouts will be provided before each lecture. Students are expected to look through the handouts before and after the lecture.

Requirements

Grading Method The course grade will be determined by the exercises.

Practical Experience Experienced

Summary of Practical Experience and Class Contents based on it The professor has experiences in developing specifications for scientific information retrieval systems and library information systems. The scope of this course covers basics of natural language processing that can be applied to various fields, including but not limited to those mentioned above.

Message

Other

Please fill in the class improvement questionnaire which is carried out on all classes.
Instructors will reflect on your feedback and utilize the information for improving their teaching.

Academic Year	2024Year	School/Graduate School	School of Informatics and Data Science
Lecture Code	KA213001	Subject Classification	Specialized Education
Subject Name	自然言語処理
Subject Name （Katakana）	シゼンゲンゴショリ
Subject Name in English	Natural Language Processing
Instructor	EGUCHI KOJI
Instructor (Katakana)	エグチ　コウジ
Campus	Higashi-Hiroshima	Semester/Term	3rd-Year, First Semester, 2Term
Days, Periods, and Classrooms	(2T) Weds1-4：ENG 103
Lesson Style	Lecture	Lesson Style (More Details)
This course will mainly consist of lectures.
Credits	2.0	Class Hours/Week		Language of Instruction	B : Japanese／English
Course Level	3 : Undergraduate High-Intermediate
Course Area（Area）	25 : Science and Technology
Course Area（Discipline）	02 : Information Science
Eligible Students	Undergraduate Level
Keywords	Natural language processing, Language modeling, Word embedding, Text classification, Information retrieval, and Information extraction.
Special Subject for Teacher Education		Special Subject
Class Status within Educational Program (Applicable only to targeted subjects for undergraduate students)
Criterion referenced Evaluation (Applicable only to targeted subjects for undergraduate students)	Computer Science Program （Knowledge and Understanding）・D1. Knowledge and ability to understand the theoretical framework underlying computer science and to collect and process high-dimensional data through full use of information processing technology based on scientific logic. Data Science Program （Abilities and Skills）・A. Information infrastructure development technology, information processing technology, technology that analyzes data and creates new added value. Intelligence Science Program （Knowledge and Understanding）・D1. A deep systematic understanding of the advanced intelligence of human beings and its realization by computers. （Abilities and Skills）・D2. Information processing ability and data analysis ability to contribute to the application and development of artificial intelligence and IoT.
Class Objectives /Class Outline	Course Objectives: - To develop basic skills required for handling human languages via computers. - To learn basic techniques and theories related to natural language processing. - To understand typical applications of natural language processing to gain practical skills on real-world problems. Course Outline: A lot of intelligent human activities are supported by natural languages, such as Japanese and English. Techniques for handling and analyzing such natural languages are referred to as natural language processing. This course covers statistical and machine learning approaches to address disambiguation in natural languages. We also learn some applications, such as text classification, information retrieval, information extraction, and natural language generation. This course further overviews four stages of natural language processing: morphological analysis, syntactic analysis, semantic analysis, and context analysis.
Class Schedule	lesson 1: Introduction to natural language processing lesson 2: Basics of character codes and text processing lesson 3: Morphological analysis lesson 4: Statistical analysis and language models lesson 5: Text classification and Naïve Bayes lesson 6: Information retrieval lesson 7: Web retrieval lesson 8: Word senses lesson 9: Neural networks and word embedding lesson 10: Information extraction lesson 11: Sequence to sequence models and large language models lesson 12: Syntactic parsing (1) lesson 13: Syntactic parsing (2) lesson 14: Semantic parsing and context analysis lesson 15: Clustering Basically, exercises are conducted every week.
Text/Reference Books,etc.	Handouts will be provided. No textbooks will be required for this course. Reference books will be introduced in the lectures.
PC or AV used in Class,etc.
(More Details)	PDF handouts and video materials will be provided.
Learning techniques to be incorporated
Suggestions on Preparation and Review	Handouts will be provided before each lecture. Students are expected to look through the handouts before and after the lecture.
Requirements
Grading Method	The course grade will be determined by the exercises.
Practical Experience	Experienced
Summary of Practical Experience and Class Contents based on it	The professor has experiences in developing specifications for scientific information retrieval systems and library information systems. The scope of this course covers basics of natural language processing that can be applied to various fields, including but not limited to those mentioned above.
Message
Other
Please fill in the class improvement questionnaire which is carried out on all classes. Instructors will reflect on your feedback and utilize the information for improving their teaching.

Back to syllabus main page