Details of CS4101 (Autumn 2022)
| Level: 4 | Type: Theory | Credits: 4.0 |
| Course Code | Course Name | Instructor(s) |
|---|---|---|
| CS4101 | Natural Language Processing | Dwaipayan Roy, Kripabandhu Ghosh |
| Preamble |
|---|
| This course is offered by NPTEL. The instructors listed here are the coordinators.
Enrolment: A student has to enrol themself in the course and should also opt for the course in the Welearn portal. Following are the dates for enrolling in the NPTEL portal. Course start date: 25 July, 2022 Course end date: 14 October, 2022 Exam date (on NPTEL): 29 October, 2022 Enrollment ends: ongoing, until 01 Aug 2022 Enrol here: https://onlinecourses.nptel.ac.in/noc22_cs98/preview Check here: https://nptel.ac.in/courses/106105158 Examination: The examination of the course will be conducted in-house by the Department of CDS. Specifically, there will be mid-semester and end-semester examinations. This in-house examination will be conducted for the course requirement of IISER Kolkata only and *will not* enable a student to get a certificate from NPTEL. If students want to get a course completion certificate from NPTEL, they need to register separately on NPTEL for the exam, pay a fee to NPTEL and write the proctored exam conducted by NPTEL in person at any of the designated exam centres. NPTEL will make the announcement regarding the commencement of registration for the examination. The online registration form must be filled and the candidate must pay the certification exam fee. More details will be made available by NPTEL when the exam registration form is published on the NPTEL course website. If there are any changes, they will be mentioned then. Please check the form for more details on the cities where the exams will be held, the conditions you agree to when you fill the form etc. (details available here: https://onlinecourses.nptel.ac.in/noc22_cs98/preview). Supplementary examination: In case a student fails in the course, there will be a provision for appearing for a supplementary exam which will be conducted by the department of CDS. There will be regular assignments from NPTEL that need to be submitted to NPTEL within the deadline. This is a requirement for getting a certificate from NPTEL together with seating for the exam. Although this is *not mandatory* for the purpose of course requirements at IISER Kolkata, it is encouraged as attending the assignments will help the students answer the questions in the in-house exams. |
| Syllabus |
|---|
| Week 1: Introduction and Basic Text Processing
Week 2: Spelling Correction, Language Modeling Week 3: Advanced smoothing for language modeling, POS tagging Week 4: Models for Sequential tagging MaxEnt, CRF Week 5: Syntax Constituency Parsing Week 6: Dependency Parsing Week 7: Distributional Semantics Week 8: Lexical Semantics Week 9: Topic Models Week 10: Entity Linking, Information Extraction Week 11: Text Summarization, Text Classification Week 12: Sentiment Analysis and Opinion Mining |
| Prerequisite |
|---|
| Basic knowledge of probabilities for the lectures and python for programming assignment |
| References |
|---|
| .1. Dan Jurafsky and James Martin. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics and Speech Recognition. Prentice Hall, Second Edition, 2009.
Some draft chapters of the third edition are available online: https://web.stanford.edu/~jurafsky/slp3/ 2. Chris Manning and Hinrich Schtze. Foundations of Statistical Natural Language Processing. MIT Press, Cambridge, MA: May 1999. |
Course Credit Options
| Sl. No. | Programme | Semester No | Course Choice |
|---|---|---|---|
| 1 | IP | 1 | Not Allowed |
| 2 | IP | 3 | Elective |
| 3 | IP | 5 | Not Allowed |
| 4 | MR | 1 | Not Allowed |
| 5 | MR | 3 | Not Allowed |
| 6 | MS | 3 | Not Allowed |
| 7 | MS | 5 | Not Allowed |
| 8 | MS | 7 | Elective |
| 9 | MS | 9 | Elective |
| 10 | RS | 1 | Elective |
| 11 | RS | 2 | Elective |