Taken in Fall 2025, not Summer

I enjoyed this class a lot, and would definitely recommend it!

Lectures: Professor Riedl does a great job explaining topics in the NLP space. Of all the classes I've taken in OMSCS, this class has far and away the best lectures. I'm only talking about the first half of the class, because the Meta AI ones that don't come from the professor are not good for the most part (they mostly just read from the slides). The task-oriented dialogue and question-answering modules in particular were brutal. I would replay some of the Meta AI videos several times and still not understand what was being said. Professor Riedl informed us that he plans to record those lectures in the future when he has the time/resources which will make the class that much better.

Textbook: The class uses "Natural Language Processing" by Jacob Eisenstein (2018). I would guess most people ignore the readings, because they are not really required (like for exams and stuff). I did do the readings, but will admit that certain sections were harder to understand compared to Riedl's lectures. Still, there's some interesting material in the textbook. It goes a bit further on some of the concepts if you're interested in the domain.

Quizzes: I agree with the post below. They are not too hard. Generally, most weeks there will be a 2-4 question quiz on the module. You have to go through the honorlock system each time which is a bit annoying but not the worst thing in the world. Like in other OMSCS classes, my main tip is for the multiple selection questions do not choose options that you are not relatively confident about because your score for the question gets subtracted for incorrectly chosen options.

Assignments: The assignments are all in Python notebooks, so you can run it in Jupyter or Colab. You should not have to spend a ton of time to get full points on the majority of the assignments. There are small asks like implementing a neural network via PyTorch's nn.module (the constructor and forward functions) and tuning the model by playing around with the batch and embedding sizes. Due to Gradescope, all cells for each assignment should run within 30 minutes or so. They also provide the test cases so you can compare your output versus what is expected to determine what part of your code is off. I will note for assignment 3B (at least for this semester) you have to implement an attention-based architecture that will only work if you follow the steps outlined in the Attention lecture. It felt rewarding after I figured that out. Occasionally, I ran into issues importing/installing packages but often a restart resolved those problems.

Final/Mini Project: The final homework (HW5) is a more open-ended mini project. You get three weeks for it, as opposed to two for most of the other assignments. It's a cool concept in that you really get to decide how you want to do the preprocessing (i.e. glove embeddings, tokenization) to improve model accuracy. You also get to implement the training/test loops unlike the previous assignments (I honestly think this should be done for the earlier assignments too, but in those everything is done for you). The recitation video for the assignment posted on Ed Discussion helps point you in the correct direction (they have a video for each assignment), although the pseudocode is not 100% correct and you have to tweak things. It is important to point out that you are not graded on model accuracy, but rather your ability to articulate your decision-making processes and why you implemented your architecture a certain way. My main issue with the final project was that I was running in Colab and kept getting kicked off the GPU towards the end after a couple hours and would not regain access for another day. It is impossible to finish this assignment using CPU alone. Hopefully, the class provides Colab Pro licenses for students at the beginning in the future to avoid issues like this. I ultimately had to switch to Jupyter otherwise I wouldn't have finished. On the plus side, they grade the assignment fairly leniently.

Exams: The exams are a bit tricky, partly due to the fact that they aren't out of a ton of points. I would say the midterm is more based off the lectures, but the final was a bit different and open-ended. The exams mostly have short answer questions. I think most can be answered in a couple sentences. For the final, we were asked things like how we would develop a dataset for various scenarios, and how we would design the architecture of the actual model. Don't stress too much about the formulas. There will be a question or two on calculating tf-idf, rouge, and bleu scores but as long as it's in your notes you'll be fine. I ended up needing the entire time for both the midterm and final, but I also probably wrote a lot more for each response than what was required.

Other thoughts: Due to the fact that the final project and final exam had to be manually graded, the TAs unsurprisingly did not have enough time to go through them with a close eye for each of the 750 students taking the class this semester. I would not be surprised if they change things next semester to make things more manageable. Since grades were due shortly after the final exam, students could not request regrades and I'm sure that angered some that were borderline between letter grades.

Overall: If you get 100s on most of the assignments (not hard to do) and do well on the quizzes, you don't have to stress as much about the exam grades and should get an A. There was not really a curve at the end of the class, but the professor added 0.61% to each student (he added 0.5% to each student's grade, and we were also given half a point back on quiz 4 because honorlock wasn't configured properly at the beginning when the quiz was released). That should be more than enough to get you to an A. Like the student below, I was like a few hundredths of a percent under the 90% before the rounding and finished with an A.

*FALL 2025

Me: I had an undergrad in CS. I started in Fall '24. This was my 4th semester. I've taken:

• HCI. High A.
• KBAI. High A.
• AIES. High A.
• RAIT. High B (I was lazy. It's an easier A than KBAI).
• CN. Low A (I was lazy again).
• DL. High B (laaazy bones).

I'm a full-time student. I took this alongside DL.

NLP grade: A (89.67%).

It's a good course. You learn alot. The lectures by the professor were great. The Meta lectures were hard to sit through. Some weren't that bad, some were really bad.

The assignments are informative. They are very easy. It's pretty easy to get 100% on every single assignment and even the mini project. Most of the class did.

There are quizzes almost weekly for each module. They are easy. Do well on them cuz you don't want them to be the reason you miss out on the A. I missed one and kinda YOLOd others and that almost cost me my A oops.

There are 2 exams, midterm and final. They each cover the first half and then the second half of the course. I.e. The final isn't comprehensive. The exams are interesting. Study well and you should be fine honestly. They are also open notes. So you can just put any notes you find online in a pdf and upload that and ctrl F throughout the exam. But even though the time given is long, it runs out fast. The notes help, but it's not like a cheat code. Still study. The grading seemed lenient, though that may depend on the grader. But yea, not too hard over all. Averages in the semester were like 80% or higher for both.

TL;DR: Assignments are easy. Quizzes are easy and almost weekly, don't skip them and do well. Exams are kinda easy too, just study the material well and have good notes.

Courses I've taken in order of difficulty: AIES (1/5) < CN (1.5/5) < HCI (2/5) < RAIT (2.5/5) < KBAI (3/5), NLP (3/5) < DL (3.5/5).

I got more out of this course than most GT classes. The lectures were interesting and engaging, although several lectures were from partners with strong accents that significantly reduced my comprehension and learning. The course has a pretty light workload, with two tests, five homework assignments, and weekly reading quizzes. I only have two real complaints. The homework instructions are fairly poor and unmaintained. Every assignment had several points of confusion because the assignment had very strict implementation requirements, but vague, unhelpful, incorrect, or actively misleading instructions. Many common points of confusion persist across multiple semesters without updates from the staff. My other complaint is that the 2 point weekly reading quizzes are proctored with a room scan, which always feels like an unnecessarily silly hassle.

An excellent course. Lectures are very informative and well structured and I learned a lot from the projects.

Easily one of the best courses I've taken so far (7 courses in).

This class is substantially harder than is indicated by omscentral, unless you you ML/AI experience. The professor is great, but they replaced the easy paper midterm into a miserable proctor exam this semester to try to combat AI usage. I took the course to have a nice summer break between spring and fall where I am taking 2 classes each semester, and I don't feel like it was a break.

I wish I had taken the course earlier! Prof. Mark Riedl did a great job explaining how different language models and architectures work. The projects were well designed, and the exams were challenging yet enjoyable. Every student could tell how much effort he's put into this course.

This course was really interesting. Like many others, I must agree that the Meta lectures were quite hard to follow and cumbersome to watch, but Dr. Reidl's lectures were some of the best lectures I've seen in this program. The content is pretty interesting overall and the programming assignments were not too difficult. There are recorded office hours that will go through the pseudocode for some of the assignments which makes it easier to follow and complete the assignments.

There were 4 programming assignments, a mini project, a midterm, and a final. There are also weekly quizzes based on the lectures for that week. The midterm and final were both open note/ open book, but I suggest going through the lectures again before the exams and really understand the content. This semester they made a change in the exam format where there are more short answer questions and you will need to write a sentence or two explaining your answer. Knowing the material will definitely help so you don't have to shift through all the notes looking for the right content (there is quite a bit).

I was misled by previous reviews that claimed this was an easy course. It’s not. I had no prior experience with ML or DL before taking this course, and I struggled throughout. It was only a generous curve that saved me from an F or D.

I've taken GIOS (A), SDP (A), KBAI (A), and CN (A) so far, and NLP had by far the most material and the most difficult exams.

Here’s the entire material you need to review for the exams, keep scrolling, note that you have to memorise and understand all of it: https://monzersaleh.github.io/GeorgiaTech/CS7650_NLP.html

There was a lot of content that was unfamiliar to me, and I often had to look online to better understand the concepts. The lectures are very dense, and the exams are brutal. You'll find your notes mostly useless. You need to memorize a lot of material and understand it deeply just to score around average on the exams. This requires thinking and reviewing lectures multiple times to obtain a comprehensive understanding of the subject. My experience with rest of the courses was very different, and you could answer the exams much easier. The exam questions are mind-bending. Some questions were two paragraphs of explanation, and you had to write an essay to answer. You may be asked to explain an entire pipeline to accomplish a task, and sometimes the questions touch on topics that are still active areas of research. I honestly don’t know how someone without real production experience could answer some of them.

The assignments for this class are barely programming assignments. They are similar to Game AI where its more of a "fill in the blank" within Jupyter notebooks.

There was a new exam format this semester and the exams were tricky. The weighting was also increased. I'll squeeze out an A, but only barely.

Overall, if not for the exams, its a 1 in terms of a difficulty, but with the exams, you should be able to get a B with ease. Getting an A would require a bit of preparation for the exams, but completely achievable.

I read the reviews prior to taking this course and they were spot on about the Meta lectures. Modules 1-6 are some of the best lectures in OMSCS, but a few hours into the Meta lectures and you'll be wondering if there is even any point in watching them.

I've given the rating a 3, because it is clear that the frustrations with the Meta lectures have gone on for multiple semesters and I don't believe that people have not complained about them in the CIOS survey, yet they remain. If they replace these lectures, the class would easily be a 5.

Dr. Reidl's lectures were quite good. The assignments were perhaps a bit too easy, but were manageable. One thing I'd note is that the course material is rapidly becoming outdated. It's kind of an intro/overview course, and NLP is progressing so rapidly that even though the lectures try to point in the direction of emerging technologies, some are outdated. About 1/3rd of the lectures are from Meta people, and some are frankly bad. The other thing I'd note, that I don't see an any other reviews, is that I found the tests (both midterm and final are closed book/open note now) incredibly difficult. They required a level of synthesis based on the presented (sometimes poorly in case of the second half of the course) information that was far beyond my ability. I didn't have any experience in machine learning, nlp, or deep learning prior to this, so maybe that was the problem. I (anticipate) having a 95% percent on the 70% of the course that is not the exams, and based on my projection of the final (and my midterm grade) I'm praying I get a C.

Modules 1–6 were excellent — some of the best content I’ve encountered in the OMSCS program. However, the MetaAI lectures were a major disappointment. They were poorly organized and difficult to follow, making it frustrating to prepare for the semi-open-book final that heavily relies on them. Be prepared to spend hours trying to make sense of the material. Good luck.

ML4T is preparation for ML/RL, and NLP is preparation for DL. They're a similar amount of work and similar level of difficulty. First four projects were straightforward (with autograding) with a large jump in difficulty with the last one (not autograded).

Dr. Riedl's lectures were fantastic and clear. The meta lectures were not, but it was possible to get the required information from them after reviewing them a few times.

Exams were actually pretty great:

• Midterm was an essay response to a paper
• Final was open-ended responses to questions from the lectures with some questions requiring logical leaps to put together

Grading is lenient. I finished with over a 99%, but it doesn't mean I didn't put my time in and work hard to understand the material.

Discord was active and chatty, I never looked at Ed once (didn't need to).

Overall, course was high quality, the material was interesting, it's preparation for another course that gets deeper into the topics. Definitely worth it.

I would consider the pedagogy of this course better than that of DL because Professor Reidl's lectures are excellent. I came out of the DL course having a very fuzzy understanding of transformers and other newer architectures but the lectures in this course coupled with the relevant assignments did a commendable job of explaining the key concepts. It is a also a low stress course meaning you get to devote sufficient time on key concepts not worrying about busy work forced on you. Getting an A in this course should be very easy. I think the biggest missed opportunity in this class is not exposing students to more real world applications of NLP. While the HW5 does a good job of implementing the much famed "attention" mechanism, the overall project was based on a redundant architecture. Assignments aimed at achieving real life use cases using pre-trained models/transfer learning would have been amazing.

Background: I work full time as a data engineer. Undergrad majored in Statistics. Relevant OMSCS Courses taken include AI and ML.

I registered into NLP after seeing the waves of good reviews about this course, and because I never formally learned NLP techniques.

Pros:

• Good lectures for 3/4 of the course. At about the halfway mark the lectures change to Meta and each Meta lecture has their own lecturer - some I preferred to others.
• Easy. Most of the class gets an A. If that's what you're looking for...
• Midterm and Final are interesting! Subject to change, but this semester it was a bunch of open form questions about the topics, which was really neat! Learned a bunch from them.
• Final project

Cons:

• Communication: Might have been an issue only in this semester, but the communication from the staff was lacking. Questions went unanswered on Ed for weeks on end (and much later in the course we were told this was to encourage conversation - a heads up would have been nice). Grading of hand-graded work (significant part of the grade) was always very late (with no communication from staff) and no feedback on these hand-graded assignments. And when I say no feedback, sometimes you're not event told where points were taken off.
• Slow. The course is slow as molasse. Great to pair with others, but there's weeks that we had very little to do.
• Assignments (Except final project) are too simple. The structure is made I believe so that students can focus on the material and ignore a lot of the set up challenges that come from working with text, but the drawback is that I found it too hand-holding. It resulted in pretty simple assignments that can be completed in a few hours of work. The assignments could benefit from diving into more topics or letting us set up the stage so to speak.

There's a lot of good about this course, mostly around the content and the open-ended projects. I think it would be excellent as a MOOC.

I suspect that the course was under-staffed, especially with the hand-graded assignments, and if OMSCS fixes the ratio of student/staff, it would improve the course experience a lot!

Prof Riedl lectures are good but that's only half of the course, rest half are presentations from Meta employees and not a single person liked them. I am afraid the course is already outdated, assignments are based on RNN and LSTM, even the project is based on a 2016 paper. There is 1 lecture on Transformers but no assignments related to that, so taking this course won't prepare you for Modern NLP jobs. Assignments are easy, it is not hard to get an A but you will have to learn NLP from other sources if you actually want to master the subject.

Overall a solid course, and I am very happy i took it.

The lectures were great, especially Dr. Riedl's; he makes the lectures very entertaining and is great at explaining concepts. The meta lectures were pretty good. Overall the instruction was top-notch.

The assignments were fairly straightforward, with my only real criticism being that the markdown code in the notebooks sometimes steered me the wrong way; for example sometimes it would tell you incorrect dimensions of tensors. Overall the assignments were a good high-level overview of the topics covered. If anything though, they were a bit too easy. The final mini project was definitely the most interesting and was just the right level of difficulty in my opinion. Make sure you run this on a CUDA machine.

The exams were a good format - written essays and paragraphs. I liked this format as it forced me to really think through what was being asked and research my answer rather than focusing on memorization of lectures.

I am almost at the end of the OMSCS journey and I must say this is one of the best courses I have taken. The lectures are top notch, especially the ones that help you understand the fundamentals of probability at the beginning of the course. I agree with other reviewers, the meta lectures were not very good.

The TAs are very responsible and they provide good timely feedback. The assignments are easy. The final exam can be a bit tricky if you haven't watched the lectures properly.

LLMs are an excellent topic, and this course will help you understand its inner workings.

HW5 can be tricky and time-consuming. I would strongly recommend using a GPU.

I loved this class. I would rate this class among one of the best if not the best class in this program. The lectures by Professor Riedl are top notch, however, the lectures by Meta researchers were a hit and miss. The overall workload is very manageable and can easily be paired with another class as long as the student has a background in ML/DL and Python. The assignments were a lot of fun and rewarding. They all require using PyTorch but it can easily be learned on the fly. The class provides a lot of hand holding and starter code so it makes things much easier for the student to pick up from.

This is a good class to take prior to taking Deep Learning (CS7643). If you are taking it after DL, then the class would mostly be a breeze for you.

Pro tip: Subscribe to the Google collab pro for the second half of the semester for this class. It will save you a lot of time especially in the final project.

My 9th course, and the best one so far! The lectures are well-structured, and the assignments align perfectly with them. Dr. Reild explains NLP concepts clearly, which is fantastic. However, the Meta AI lectures are less impressive.

Likely grade: A with a near 100% score This course is super easy if you have taken ML in the past. Its on part with ML4T in terms of effort, but you are gonna get to learn the cutting edge in NLP. I took it over DL because I wanted a more applied course that taught me transformers. This class is basically DL applied to natural language processing with the latest techniques arch system architechtures in industry.

The homeworks don't require that much effort week to week, with the exception of hw5 it definitely takes 20hours to finish. It doesn't help that the recitation was super confusing. The quizzes require you to perhaps go 1 level deep to dig into the root cause or 1 level above in terms of inference. They don't require you to make several logical leaps in order to come to the answer and are some are common sense.

The midterm was a paper review, they give you 2 papers to pick from, and ask you to answer questions about the one you picked. The questions really test how deeply you have understand the paper. I wrote very comprehensive answers and made a 12/12, the avg was maybe a 10/12. It was easy to make a good score but really hard to make a perfect score. The final was comprehensive exam of the entire course content with emphasis on the second half. 12 points again. Both exams were open notes and open for a week. The midterm was multiple submissions, the final was not but they give you a downloadable word doc of it so you can work offline.

The lectures: Rields lectures are fantastic, he distills information in a way that even a toddler can understand. But the lectures from Meta that constitute the second half of the course are pure trash. There are 4 Meta researchers that teach most of second half of the course. Out of those only 1 or 2 are any good, the others are pure trash. I used a previous students lecture notes https://lowyx.com/posts/gt-nlp/ to study most of the second half and parts of the first half as well.

This was my last course in the program and it was the perfect finale in terms of format, level of commitment, and topic interest. I really wanted something that was fun and a little challenging as my last course, nothing complete fluff or that would make me pull my hair out (what is left of it).

On top of that, I preferably wanted a course with no traditional exam format (proctored, closed book) and of course, no dreaded group work. This one fit the bill perfectly.

Other reviews have touched on the makeup and mechanics of the course, so I won't reiterate those here. I will say that the midterm this semester was pretty awesome, it reminded me of the first part of EdTech where you read a paper and answer a few questions. It was good in the fact that it wasn't overly challenging but it also gave us a good introduction to the topics covered in the papers offered.

I will echo some of the other sentiments about the homework projects. Projects 1 through 4 are pretty low-lift filling in template code and they focus more on the machine learning aspect of setting up the appropriate classes for the model than doing the infrastructure stuff like data preprocessing etc. Time commitment for this part of the course was really low, just a few hours a week (excluding lectures if you watch them).

These assignments ostensibly prepare you for the final project so you can pretty easily implement the actual model, but the bulk of the challenge and the work on the final project (for me anyway) was in doing all that data processing, constructing datasets, training/testing, etc. that you didn't need to do before. So if you're not too familiar with that kind of stuff in Python, then give yourself plenty of time to figure it out before the due date. It was kind of a neat format for this project too because you didn't need to attain a certain accuracy or certain number of correct outputs, you just had to construct the model, show that it was learning, and then answer questions about what your model did and how/why it did that.

The only project recitation I watched was the final one and it was pretty helpful to clear up some of the fuzzy parts of the project for me.

The quizzes at the end of the modules are open everything so they were pretty easy. I think I missed one question all semester and that was because it was weirdly worded and I was misinterpreting the answer choices.

The final exam is essay style and I found it really interesting and fun and also a good learning experience. Which is not how I find closed book proctored exams, so this was great for me. Not sure how I did on it yet but I am not too worried.

So all in all, this was a great low-stress class for my last semester. The material was interesting enough to be fun to work on and lots of opportunity to learn cool stuff for those of us that enjoy programming and NLP but aren't professionals.

If you're proficient in this topic then it's probably a waste of time to take it unless you just want the credits. Pairing it with another class wouldn't be too much of a big deal if you're relatively familiar with Python beforehand.

Oh and you have a choice whether to use a local or Colab environment. I used local for all but the final when a GPU was helpful. Adapting the notebooks for a local environment is not a big deal if you are familiar with the process. I bought 100 credits for Colab runtime and only used like 40 of them for the final project. So 100 would probably get you through the entire semester on Colab but I just hate their IDE so stuck with local as much as possible.

This is an overall great course and newly developed. This is great staying away from the hideous old videos for most of the other OMSCS courses.

It's still currently small in numbers and hard to get in, however it will grown soon with more potential TAs graduating every semester.

The material is extensive, very extensive to be honest. In fact too extensive and you barely get tested on anything. Even if about half the videos were taught, you would still get a good education and would not even affect the assignments/exams.

The quizes are mostly hard even though they are usually 2-3 questions, they are tricky so take your time, you only get 2 attempts each.

Midterm and final exams are take home open everything (except for your favourite GPT). These are written questions you need to answer. I found them ok overall but take time to complete.

The 6 homework assignments are the real meat here taking up 70% of the grade. They are all coding with some written question in the final assignment which counts 20% of the overall grade. The first 5 homeworks are autograded on Gradescope but some take quite a while to run.

My suggestion is to use Google Colab with paid subscription, this is the most efficient way of working through these since the starter code is adapted for this platform in mind. You can do it on your environment as well and works ok for some assignments but a pain to adapt for others.

The homework assignments do build up, from only a few lines in the first assignment to quite a sizeable amount of lines in the last one. Be prepared for this. Another tip is to start early HW5 (the last one). I left mine at the last minute along with the exam since the deadline was on Wednesday instead of the usual Sunday. I rushed through the final assignment and the exam merely missing an A by a hairline!

Final note on the videos, the first half of the course with the videos made by the professor are absolutely the best. The second half where Meta AI folks do the videos are absolutely horrible, dry and for most part pointless. I would not suggest you skip them but prepare to be bored to death. I really hope these are done again in the future as this is one of the best classes in OMSCS.

Heavy Math, Lot of coding. If you are new to deep learning or AI. Learning curve will be high. It works with other courses too. DON'T TRUST SOME RANDOM 5+ year experienced SWE/MLE says its easy class.

Yeah NLP is now worth to take for all specializations because of GPT HYPE. I don't trust cynical people say its just stochastic parrot. If we think about Electric Vehicle last 10 years. People make same repatory(Its not worth to make EV and difficult to commercialize it).

Assignments, projects, reading papers for final project. It's not easy at ALL. Everything you learn from this course will give you strong benefit. Keep in mind always try hard.

The explanation of Professor Riedl on lectures is one of the best in OMSCS. This is mainly the only part I liked of this course, the bad this is the assignments.

The assignments took me less than 4 hours each, the final mini-project around 10 hours. Quizzes are open book as well as the final exam.

There were weeks I did not touch anything about this class, the time commitment is so low. I spend less than 4 hours a week for this class, and I feel I did not gain deep knowledge about this field.

This class have to be redesigned at least for this assignments and be at the same rigors as DL, BD4H or HDDA.

Note this review is actually for spring 2024.

This is an OK class. For background I've been in the program since 2022 and this was taken along with 2 other class while I took a semester off from work to do this full time. I'm in the ML track and so have done 7643 and was doing DL concurrently with this.

LECTURES: The lectures by Prof Reidl are great. The only criticism is that they are a bit long. That said you will always leave the lectures understanding what concept is being taught. I credit this class for really understanding LSTM, Transformers and some other DL things.

There are some Meta AI lectures. These are definitely better than the ones in DL but not great. If Mark's lectures are a 5 then these are a 3. The info is good for the most part and they mostly get the point across

Most of the lecture content in this course is focused on actual NLP. That means the BOW model, machine reading, embeddings, information retrieval and more. This is a survey class, it's not a class about LLMs. You spend only a bit of time on them really. If you want to learn about LLMs take DL and then watch some of Andrej Karparthy's great YouTube videos.

Quizzes: There is a trivial quiz at the end of each section. These are a little challenging because the sections can be very long (2+ hrs) and can be a bit detail oriented. You get two tries on each and they are open so can't complain here.

Homework: Oh boy... This is a very big disappointment. Coming out of ML and seeing what DL is doing with HW I was really left scratching my head. The assignments are all very, very easy jupyter notebooks. Most time is spent debugging the testing framework you are given or trying to understand what you are actually required to do. None of them are super hard but I found them very annoying.

My bigger frustration is that they do a poor job reinforcing lecture. In DL you have to implement a transformer from Pytorch primitives. The furthest you go here in terms of DL is implementing an LSTM. We don't even use the built in PyTorch transformer module at any point. I'm not sure why an NLP class doesn't have you work with one of the most important NLP mechanisms out there right now.

As is I also don't feel the HW does a great job of reinforcing what is in lecture unless you do the notebook while watching the lectures at the same time. They almost need to be thought of as a companion to the lectures. So if that was the goal when creating them that is reasonable.

PROJECT: The project was to implement an attention mechanism. I think the project would have been a great opportunity to either use the PyTorch transformer or build one from scratch. The lecture walk through is good enough for that. Instead we implement a mechanism from 2016 that doesn't really have a purpose in this day and age. The idea is that we are trying to get experience working with attention mechanisms but that's really a small part of it.

I will say it is good that they force you to write your train and test loops from scratch. This aligns with the expectation that the prior notebooks have trained you for the project. I am just not convinced the project does a good job of reinforcing NLP since it's so hard to get good results from this sort of network. I'd give this project a 2/5 in current state.

Exams: Midterm was childish. Felt like something from high school. You are given a set of question you must answer in a word doc like format based on a paper you have read. The problem is that they really don't let you flex your muscles if you are used to writing quality papers like you would do in ML4T, ML or even DL to an extent. They also expected you to identify very specific things, even though you are ostensibly just giving a summary. This was the lowest point of the class for me. 1/5.

Final was open everything short respsone. They ask potentially very deep systems design questions but then expect you to answer 1-2 paragraphs. Based on the grading for midterm being very specific I found this to be impossible. Weirder still is that half the questions seemed to focus on LLMs. This was strange since we spent very little time talking about them in the class. When asking the TAs if we should incorporate stuff from outside the class we were told it shouldn't be needed. Not sure how that works since some questions had virtually no coverage in the course.

Now that said, none of the questions were hard. I just don't understand why we were being asked those questions given everything else we learned in the class.

Summary: So who is this class for? I think this is a good course if you are in the CS track and want to try something ML related that isn't brutal like DL and is not ML4T. This course does a great walkthrough of NNs and can take you from nothing to writing PyTorch code. That's pretty cool.

If you already know NNs, have taken DL or something like that then some of the non NN NLP stuff is interesting. I just don't think the treatment is rigorous enough to really learn a lot. I now know a bunch of concepts but I don't feel I can strongly apply them. The NN side get's completely covered in the 4th section of DL. You will learn nothing new here related to NNs if you have taken DL. Again, you never use a transformer in this class.

The TAs are trying their best. I think this course could be super great if you have the lectures form the base and then have the students go out and extend them. I think lectures can be tightened up and can assume a bit more prior knowledge. I could have skipped the whole module on Bayes having seen it in AI4R for example. Have this go from a 10hr/week course to a 15, clean up the notebooks and make requirements more clear (why is GT allergic to type hints?), and give us a more modern project. Do that and I think you have a winner.

I got a mid A for what it's worth. Many weeks I completely forgot about this course.

This is my 7th course and by far the best. It does a good balance of theory/lecture, programming assignments and paper overview. It doesn't beat you to death with sadistic assignments and provides a shell where you focus on the conncepts learned and see it working. I finally understood the intuition of a Transformer model and its variants. Prof. Riedl is stupendous and i wish he finished the entire modules.

He should come up with advanced NLP since there is lot of interest on how to quantize and FineTune a LLM models using HITL RLHF or DPO. I think Finetuning itseld can be a course starting with multiple sub-word, PE and attention techniques that can be explored.

Only thing that they can improve is better homework recitation by TA.

My 8th course in the program and one of my favorites so far. There are about 18 hours of lecture content. Reidl's lectures are very good, I actually went through all of his twice to try and fully absorb the content. A handful of the modules are done by guest lecturers from Meta and are much worse in comparison--some of them seem to be reading straight from teleprompter, most just do a terrible job at explaining things. Most of the content of the course focuses on neural networks, although there is some content on foundational math in the beginning. If you have a strong foundation of ML, I would expect this class to be not too hard. If you don't, you might have to do a little more work to catch up. There are 6 homework assignments that entail filling out various functions in a jupyter notebook, you are given a lot of supporting functionality, and they are graded based off included tests. I'd say they ramp up in complexity pretty steadily. The first 4 are a breeze, and can be done in an afternoon or two very easily. The 5th was somewhere in between. The 6th is a "project" that is still just a notebook with some instructions, but more open ended about the approach you can use and doesn't have any auto-grading. We had an extra half a week for the project, but I spent as much time on the project as I did every other assignment combined, so start early. Everything is done with Pytorch, and you actually build models that do stuff, which makes the learning feel well applied. I feel like I am walking away with a toolkit to do more projects using what I learned--a first for me in this program. There were two exams. They consisted of a series of short answer questions, with unlimited time and open notes/internet to complete. In order to make this somewhat challenging, they're structured to make you apply concepts from the course in more creative scenarios, not just regurgitate facts from the lectures (most of the time). I found it took me quite a bit of time to think through each question, but I learned in the process of completing the exam. It was challenging, but honestly, it's the most fair and effective exam structure I've ever encountered (and my philosophy is generally that exams are a waste of time). Besides the bad lectures from Meta, my criticism of the class, at least in this semester, is that the TAs are still figuring a lot of things out about how to best run the course. They were very slow on grading, and very inconsistent with responding to questions on Ed. Some of the instructions in the homeworks were very confusing, and at times I felt the challenge was in interpreting what was written, not in actually doing the task itself. I expect some of this will resolve as time goes on and they improve the logistics of the course. They also are very strict about not releasing anything early, including lecture content, which is released on a weekly basis and includes short quizzes which must be done in the week they are released. In this semester, we weren't allowed to download lecture videos or slides from the lectures. I don't really understand why, but these things were a big inconvenience to me when I had some international travel during the semester. My time estimate is an average across the semester. In the early part of the course, I would often spend 3-5 hours a week on the course. During exams and toward the end, it was closer to 15-20.

I have liked this course so far. The first half or more of the course is going deeper into NLP concepts I had already seen in DL. The homework assignments are not too hard. The project is very interesting. NLP is a lot easier than ML and DL. I would recommend it for a summer class.

This course does a good job of explaining modern NLP topics, such as word embeddings, RNNs/LSTMs, attention, Transformers, and Key/Value stores. It also covers some info retrieval topics.

The early lectures of the class are very detailed and cover the topics very well. The explanations are stellar.

The homeworks are simple and basic. Can be done in a few hours. This class is so light it can easily be paired with others. The exams are open book and you are given ample time to do them without honor lock. The late policy is very flexible (5 free late days for the semester).

The downsides of this course are vague lectures from Meta towards the end which just throw a lot of terminology in a survey fashion, rather than explain any concepts. The professor should re-record them with his explanations (since he does a great job in the other lectures). And the course could easily have 3x more homework and still be quite doable. I've sometimes ignored the class for weeks and done well.

No topics on pretrained model refinement or Reinforcement from Human feedback.

Overall a good class. I learned a lot. But I would have preferred some more projects that delve into more of the typical NLP tasks. Rather than just a couple of basic tasks.