CS 124: From Languages to Information

(DRAFT WEBSITE SO DETAILS MAY STILL SHIFT A BIT)




Welcome to CS124!! Some FAQ


When is the course? Tu/Thu 2:30-3:50

Do I have to come to class? For COVID, this course can be taken asynchronously. Nonetheless, we strongly recommend you be available during this time frame if possible. There are 4 group class exercises during class time that are strongly recommended; they are not graded so could be done by yourself at home later, but you will get more out of them if you come to class. Lectures are either pre-recorded or will be delivered live and recorded, and midterms will have alternate times.

Is 106B the only prereq? Do I need 109 or 221 before I take CS124? : 106B is the only prereq. Taking the course as a sophomore or junior is recommended. It will help if you have at least done some programming beyond 106B, and is also useful to have had 107, but not required.

Textbook? None, we'll use free online pdf chapters mostly here

More details? below. You are responsible for reading this entire syllabus before the 2nd day of class Thursday April 1!

Most important: Have fun and learn lots!!!!

Logistics

Instructor

Dan Jurafsky (jurafsky@stanford.edu)
Office: Margaret Jacks 117 (when not during COVID)
Office Hours: TBD

Teaching Assistants

TBD

TA Office Hours

• Tuesdays 1:00pm to 2:30pm
• Wednesdays 7:00pm to 10:00pm
• Fridays 1:00-2:30pm

Class Time

Tuesday and Thursday 2:30-3:50pm

Email

We can not reply to email sent to individual staff members. If you have a question that is not confidential or personal, post it on the Piazza forum - responses tend to be quicker and have a wider audience. To contact the teaching staff directly, we strongly encourage you to come to office hours. If that is not possible, you can also email (non-technical questions only) to the course staff list, cs124-spr2021-staff@lists.stanford.edu. If you have a matter to be discussed privately, please come to office hours, or use cs124-spr2021-staff@lists.stanford.edu to make an appointment. For grading questions, please talk to us after class or during office hours.

We try to redundantly use Piazza, Canvas, and mailing lists to make sure any messages we convey to the class reach you all! We will assume that all students read these messages.

Honor Code

Since we occasionally reuse homeworks from previous years, we expect students not to copy, refer to, or look at the solutions in preparing their answers. It is an honor code violation to intentionally refer to a previous year's solutions. This applies both to the official solutions and to solutions that you or someone else may have written up in a previous year. It is also an honor code violation to find some way to look at the test set or interfere in any way with programming assignment scoring or tampering with the submit script.

Since quizzes are a form of assessment, students are not allowed to collaborate on completing quizzes. It is an honor code violation to discuss quiz questions with other students.

Textbooks

• There is no required textbook, but I will expect you to know the material listed above, drawn from the textbooks and other readings. The material in the readings will be tested on the final exam. Different people may learn better from different combinations of videos/lectures, reading the chapters, or coming to the in-class group exercises. The best-prepared students who do the best on the final exams tend to do all three. But I won't take roll for lectures and attendance is up to you.
  • Online new chapters from Jurafsky and Martin. third edition in progress. Speech and Language Processing.
  • Chapters from Manning, Raghavan, and Schutze. 2008. Introduction to Information Retrieval. Cambridge University Press. You can buy the book, get it from the library, or it's also available online *HERE*.

Course Description

Extracting meaning, information, and structure from human language text, speech, web pages, social networks. Introducing methods (string algorithms, edit distance, language modeling, machine learning classifiers, neural embeddings, inverted indices, collaborative filtering, PageRank), applications (chatbots, sentiment analysis, information retrieval, question answering, text classification, social networks, recommender systems), and ethical issues in both.

Prerequisites

CS106B. CS 107 can be helpful, but if you haven't had it we'll cover the required UNIX material.

Required Work

Video Lectures

Each week, we will ask you to watch a set of video lectures (2 to 2.5 hours total). The videos will have some in-video questions embedded in them, which you should answer. You are required to watch the videos but the embedded quizzes are not counted toward the final grade. For those duplicate lectures you can watch either the in-class or recorded version.

In class Lectures

A few lectures will be live, but will be recorded and posted to Canvas afterwards for those who missed it, or for review for the midterms.

In-class group problem-solving

4 in-class sessions are for group problem-solving activities. These are strongly recommended, and the first one (April 1 on Unix text processing) is required and will be tested on the quiz, meaning that if you can't make that date, you must get permission in advance to do the entire exercise at home instead (for those taking the class fully asyncrhonously). Previous students who did well in the class have reported that the in-class group exercises have been extremely useful.

Automated Review Quizzes

After watching a week's video lectures, we will ask you to answer an open-notes, open-book review quiz (about 5 questions) on the content that you just learned. Each review quiz may be attempted twice, with a time lag between each attempt. The questions, as well as the options for each question, are randomly selected from a larger pool each time you take a quiz. The system will automatically take the best score of your two attempts for the quiz. Review Quizzes for each week are due 11:59pm Tuesday of the following week. There are no late days for review quizzes.

Class Participation

You have to watch all lectures, but video-only is fine, attendence for the live lectures is optional. However, attendence for group work sessions is strongly recommended (but still optional); we will cover material that will be tested on the midterm.
You can get extra credit for class participation by:: helpful answers on the class forum, helping out other students in office hours or group work sessions, being the first person to find typos in the textbook (not counting bugs in figure or chapter numbering), speaking up in the group work sessions.

Programming Assignments

6 Python programming assignments. Each assignment is due at 5:00pm on the Friday it is due.

Programming Assignment Collaboration for PA 1-5: You may talk to anybody you want about the assignments and bounce ideas off each other. But you must write the actual programs yourself. We will use the normal automatic checks for overlap between your code and other students' code.

Programming Assignment Collaboration for PA 6: PA6 is a group homework, so you can work together with your group, and write code together. You must describe in your writeup who worked on which parts of the assignment/code.

Late homeworks

You have 4 free late (calendar) days to use on programming assignments 1-5. You cannot use late days on PA 6. Once late days are exhausted, any PA turned in late will be penalized 20% per late day. Each 24 hours or part thereof that a homework is late uses up one full late day. However, no assignment will be accepted more than four days after its due date.

Readings

This class has a significant amount of textbook reading. Most weeks have around 25 textbook pages. The homeworks and exams will be based heavily on the readings.

Final grade computation

• 63% homeworks (PAs 1-5 are each worth the same, 9% (ignore the different point values for each homework). PA6 is worth 18%, double the others)
• 11% Midterm 1
• 11% Midterm 2
• 15% weekly review quizzes