Natural Language Processing

The first “real” (40XP-worth) homework has been posted, and is due at the stroke of midnight Sunday September 14th. All questions are welcome!

The code, corpus, and regex examples from today’s class have been posted. (Clone the class github repo if you want to do these things the right way.)

The repo also contains the htmlstripper.py program which you can use and/or modify for whatever purposes you may desire, if useful.

I have posted a solution to the second reading check.

Also, since numerous people came up after class and said they didn’t have enough time to reasonably finish, I’m going to (1) give at least 5 more minutes on future reading checks, and (2) double everybody’s score on this one.

If you’ve received an accommodation letter from the ODR, and sent it along to me, thank you very much. Let me be specific about how I will handle all of these:

1. I fully intend to comply with all your accommodations, but I may need to be periodically reminded on a case by case basis. If I do end up needing reminding at any time, please don’t interpret that as “Stephen doesn’t care about me or my accommodation.” Instead, interpret it as “Stephen has a lot of things he’s trying to carry in his mind right now, and it’s hard for him to memorize everybody’s accommodation needs at all times.” Please do just gently remind me, and I’m happy to accommodate.
2. For accommodation needs like “the ability to record the lecture,” that power is officially granted to everybody. Heck, you can even stick the recording on Youtube if you want.
3. For accommodation needs like “a distraction-free environment for quizzes,” please tell me at the beginning of our reading checks that you need this, and I will relocate you to another room.
4. For accommodation needs like “extra time on quizzes,” you need to be sure to tell me in advance for each and every quiz that you need me to put your additional time into Canvas. (Unfortunately Canvas doesn’t have a feature that lets the professor give a student extra time for “all quizzes.” So you must remind me each time.)
5. For accommodation needs like “access to a laptop to take notes,” please let me know this in class Tuesday so I can relocate you to the back/side of the classroom (where others won’t be distracted by your screen).
6. For anything else you think I need to know about, just come ask me: email, after class, and office hours are all good.

I have posted a solution to the first reading check.

A student just asked an excellent math question about…. the material in allthemath.org Volume One (discrete math). Keep in mind that the reading checks this semester (including tomorrow’s) are on linear algebra (Volume Two on allthemath) not Volume One!

If you’re reading this, it’s high time you earned your first +1XP of the semester by registering on the class scoreboard! (Click on the “New NLP student” tab when you get there.)

Be sure to choose a screen name that no one will be able to guess, and do not reveal it to anyone throughout the course of the semester! Also: for the first name of your “real name,” please use whatever you actually like to be called, not what’s in Banner (if they’re different).

Completing this step is a necessary prelude to earning any more XP for the entire semester!

Hark, most noble visitors! Ye are right welcome unto the fair Autumn of the Year of Our Lord Two Thousand and Five-and-Twenty, wherein is held the most wondrous course of DATA Four Hundred and Seventy — Natural Language Processing with Master Stephen!

Verily, this humble web of sites shall anon be stuffed to bursting with rare and excellent content. Therefore, tarry not far, but keep thine eyes most watchful!   🪶