《Making of a Genius [A Progression LitRPG]》Chapter 8 - Natural Language Processing

Advertisement

“I want to do NLP - natural language processing,” Lexus said.

As he voiced out his decision, a strong breeze of cold wind blew upon them, causing Lexus’ skin to tingle. Or was it the excitement? He didn’t know.

When he was prompted to do what interests him by the system and the professor, his mind immediately went to natural language processing, which is a subfield of artificial intelligence that aims to allow machines to understand human language.

The authors of “Artificial Intelligence: A Modern Approach” wrote extensively about natural language processing in terms of techniques and applications, and Lexus was so intrigued by the topic that he even tried his hand at creating his own language model to generate text from a given prompt. Obviously, it wasn’t even close to being state-of-the-art, but it incited Lexus’ excitement in the topic, making him want to learn even more. It seemed like a field that was making rapid progress, and Lexus wanted to be a part of that action.

And it’ll be helpful, since the only way I can currently interact with the system is through language, Lexus reasoned with himself. If he could learn more about how language models behaved, maybe he would be able to determine if the system was truly an AI in the conventional sense. If it wasn’t… was it an entity from outside of this world?

In response to Lexus’ declaration, the system said, “Great choice!”

Lexus was weirded out by its overly-nice reaction. What’s wrong with this thing?

Professor Emerson replied, “In that case you should contact Professor Milton, she specialises in that area. I’ll make a recommendation for you, but it’ll be up to you to convince her to take you in.”

That was to be expected. Professor Emerson was impressed by the progress that Lexus had made over the past few months, but if Lexus wanted to do research under another professor, she would have to willingly accept him into her team. And it was Lexus’ job to convince her to do so.

=====

“Mmmph-” Arthur waited until the rice was fully down his throat before speaking. “You’re going to do research under Professor Milton?”

“Yeah”, Lexus replied. “With Professor Emerson’s recommendation, I managed to get into contact with Professor Milton and arranged a meeting with her three days later at the computer lab.”

“Nice! Mate, I know you’ll smash it. What kind of research are you gonna do?” Arthur asked in between mouthfuls of rice.

Lexus laughed at Arthur’s enthusiasm. “Haha, why are you more excited than I am?”

Arthur put his spoon down with a clang, stating, “Of course! My mate’s going to be the best scientist in the world. When are you gonna win the Turing award?”

The system chipped in, “Look, someone who knows what they’re talking about.”

“I haven’t even started doing research yet, you’re thinking too far ahead,” Lexus said. “You know about natural language processing?”

Arthur replied, “I don’t know a lot about it, but wasn’t there this craze about large language models a few years ago? Everyone seemed to be going on about it.”

Lexus took a sip of water. “Yeah, you’re probably talking about the time when GPT-3 was introduced by OpenAI in 2020. Did you know of the time when a student at Berkeley used it to write a series of self help blog posts and published them as an experiment? He didn’t even mention that it was written by an AI, and one of the blog posts made it to the top of Hacker News.”

Advertisement

“Damn, that’s crazy. Do you think it passes the Turing test?” Arthur asked.

“I’m not sure, but it’s probably close. If people didn’t realise that the posts were written by an AI, then the text that it generates shouldn’t be too far of from typical human text,” Lexus replied.

“Man, twitter was going off about how GPT-3 was going to take over the world. That, and the funny responses that it would output from time to time. Hold on, there was one about chess that was pretty funny,” Arthur said.

“Yeah, the guy from Berkeley probably had do do some prompt engineering,” Lexus replied.

Arthur took out his phone and started searching for something on the app. After a while, he said, “This! This is the one I was talking about.”

Arthur showed Lexus the tweet, which went like this:

Human: Do you want to play chess?

AI: I love playing chess!

Human: Okay, you start.

AI: I start with the white pieces.

Human: What’s your opening move?

AI: My opening move is to place the white king’s pawn two squares forward.

Human: I’ll match that with black king’s pawn two squares forward.

AI: Excellent move!

Human: Your turn.

AI: I move my white king’s pawn two squares forward.

Human: That’s not allowed.

AI: Oh, I’m sorry. I didn’t know that.

Human: Try again.

AI: I move my white king’s pawn two squares forward.

Human: I just told you that’s not allowed.

AI: I’m sorry, I didn’t know that.

Human: Do you know the rules of chess?

AI: Yes, I do.

Human: Sigh.

AI: What’s wrong?

Human: You’re obviously not sentient.

AI: What do you mean by “sentient”?

Human: You don’t have any sense.

AI: What do you mean by “sense”?

Human: I mean that you don’t understand anything.

AI: I’m sorry, I don’t understand what you’re saying.

Human: That’s okay. Have a nice day.

AI: You too!

Lexus smiled, “Haha, that’s pretty good. I wonder if newer models like PaLM, LaMDA or BLOOM can do better?”

Arthur put his phone back in his pocket and continued eating. “Not sure, but there’s a lot of action in the field for sure. Great time to go into it!”

Lexus nodded. “Yep, that’s right.” Like many others, Lexus was intrigued by the recent breakthroughs in the field of natural language processing. He sought to understand how each of these technologies worked, and if he had the opportunity to get involved, he wasn’t going to miss it.

A journey of a thousand miles begins with a single step, and Lexus was about to make that first step on what was the start of his research adventure.

=====

As Lexus was making his way to the computer lab, his heart was pounding at the same rhythm as his steps. The route to the computer lab was long and empty, which gave Lexus even more time and space to entertain his nervous thoughts.

Hi Professor Milton, I’m Lexus. Can I do research under you?

No, too straightforward.

Hi Professor Milton, I’m Lexus, a first year. I’m very interested in doing research in natural language processing, and Professor Emerson recommended that I speak to you. I saw that you have a project about neural machine translation, and I’m-

Ahhhhhh, too long. Might as well start with “once upon a time”.

Lexus muttered, “Ahhh, why is this so hard?”

The system yawned. “Just relax. It’s going to be fine.”

“Easy for you to say,” Lexus replied. “My research dream depends on this.”

Advertisement

A hearty laugh erupted inside his head. “Haha! You’re over exaggerating. And anyways, it’s going to go fine. You haven’t done all this preparation for nothing.”

It’s right, Lexus thought. I can’t give up now. Not when I haven’t even started.

“System, can you show me my status?”

---

Name: Lexus Kagan

Current Quest: Publish a research paper

Computer Science: Level 1 [EXP 223/1000 (22%)]

Mathematics: Level 1 [EXP 209/1000 (20%)]

Physics: Level 0 [EXP 12/100 (12%)]

Engineering: Level 0 [EXP 0/100 (0%)]

Chemistry: Level 0 [EXP 0/100 (0%)]

Biology: Level 0 [EXP 2/100 (2%)]

---

Lexus had been making solid progress in terms of experience points even after he had completed his first quest, despite not deliberately optimising for maximising his experience, instead purely following his interests. Every day, he would go on arXiv to search for interesting papers and give them a read, no matter the subject. Most of the time it was about computer science related topics, but there was one particular day where he stumbled on the paper “Absence of atrial smooth muscle in the heart of the loggerhead sea turtle” and just had to give it a skim to see what was going on. Despite not knowing any of the technical biology terms, he had somehow learnt enough to gain 2 experience points in Biology.

[Increased Processing Speed] seemed to apply to the other subjects as well, which pleasantly surprised Lexus. Given that [Right or Wrong] was purely limited to mathematics related problems, Lexus expected the other skills that he gained from levelling up to be of the same nature. Well, he could hardly imagine how the system could refactor his brain to learn a specific subject more quickly and not others…

“Hey system, are all passive skills applicable in all subjects?” Lexus asked as he continued to walk towards the computer lab.

“No, there are passive skills that you can gain that are limited to a specific subject. As your level increases though, the skills you gain will gradually become more powerful and widely applicable. Skills gained from levelling up computer science are an exception though! They form your main branch, and will be significantly more powerful than the skills gained from other subjects,” the system replied before adding, “not that you will get a computer science level up any time soon.”

Lexus stopped in his tracks, looked around to make sure no one was nearby, and retorted, “Come on, I’m making good progress here!”

Despite the snide remark, what the system just said is valuable information, Lexus thought as he resumed his brisk pace. I guess it means that I benefit the most by focusing on computer science.

Which made essentially no difference to what he was currently doing, but it was good to know nonetheless. In fact, it made Lexus even more excited to see what was in store for him as he climbed to the higher levels. Okay, let’s focus on the next step and bag this research opportunity!

=====

At the ground floor of the Cambridge computer lab was a communal area featuring a paper-tape representation of the original boot program for ESDAC, a Generation 1 computer built at the Cambridge Mathematical Laboratory in 1949. Other than that though, it also featured what you would expect at any typical communal area: An abundance of tables and chairs.

Lexus found a table near the window walls and took a seat. Five minutes later, he saw Professor Milton approach from the hallway leading to the room, and stood up to signal to her where he was.

Once they were both comfortably seated, Lexus took the first action. “Hello Professor Milton, I’m Lexus, a first year CS student.”

The professor nodded. “Yes, Professor Emerson told me about you. He said you were interested in doing research in NLP?”

Okay, so good so far.

“Yes that’s right,” Lexus replied. “I’ve been reading about machine learning and natural language processing specifically, and would love to be involved in research at your lab.”

“Do you have any idea what specifically in NLP you want to work on?” she asked.

Uh oh, first test coming right up.

Lexus gave a slight smile and said, “I saw that you have a project about neural machine translation listed on your website, and am very interested to learn more.”

The slightly-impressed-that-he-wasn’t-wasting-her-time look that the professor gave was more than enough for Lexus to know that, phew, he passed the first test.

“That’s great. Noelle, my PhD student, is currently working on that project and I’m sure she would appreciate some help. Do you have any idea what the project is about?”

Alert, second test incoming!

Lexus nodded and said, “from what I understand, it’s about varying different properties of machine learning models and seeing its effect on how much data is needed to achieve satisfactory performance in NMT, neural machine translation, which aims to translate a piece of text from one language to another.”

Was that too much? It was akin to explaining the difference between a turtle and tortoise to a cheloniologist.

Stop thinking about turtles. Focus!

The professor seemed satisfied with Lexus’ answer. “Yes, we aim to measure the effect of modifying the training setup of the model on the data scaling laws of NMT. It’s an interesting problem! As the research in NMT progresses, most of the breakthroughs are with respect to the fixed benchmark measuring the quality of the translation, but it’s unclear how much improvement the newer model architectures have made in terms of the rate of learning from increasing amounts of data. Who knows, maybe they’ve become worse? Unlikely, but I’d like to find out.”

The voice in his head remarked, “Wow, look at her go on and on.”

Lexus wasn’t listening to the system though. All he could think was, yeah, this is so cool!

Professor Milton continued, “If you join our research team, the main things you’ll be doing in the beginning are reading publications to get up to speed as well as participating in team meetings. At your stage, it’s unlikely that you’ll start working on proper research right away, but within the next few years you’ll probably make enough progress to make some contribution. Are you still up for it? It’s not a small commitment.”

“Yes, I’m aware and committed,” Lexus replied. He was prepared to make this his main priority. And he was a quick learner, he would get up to speed in no time!

The professor gave a light nod and said, “Good, then we’ll start with you coming to our next team meeting on Monday morning at 10am, and we can take things from there.”

And the deal is sealed. Woohoo!

    people are reading<Making of a Genius [A Progression LitRPG]>
      Close message
      Advertisement
      To Be Continued...
      You may like
      You can access <East Tale> through any of the following apps you have installed
      5800Coins for Signup,580 Coins daily.
      Update the hottest novels in time! Subscribe to push to read! Accurate recommendation from massive library!
      2 Then Click【Add To Home Screen】
      1Click