Posts about research

This blogpost applies (as all my PhD related writings) to a PhD in computer science in the Netherlands. It will be different for other research fields and other countries.

In The Netherlands, most PhD students get a contract as university employees for 4 years. After the first 12-18 months there is an evaluation moment. By then, you are expected to have either your first conference paper under your belt (co-written with your supervisor), or at least have a paper manuscript ready for publication.

I finished my PhD in computer science more than three years ago. Now that I have a little bit of mental distance from my PhD time, I'm going through my research diary to see if there's stuff in there that can be useful for other people.

Apparently I'm incapable of writing short-form texts, so here is part 1. ;)

This is a textual version of the talk I gave at Foundations of Digital Games 2021, for the research paper titled Fine-tuning GPT-2 on annotated RPG quests for NPC dialogue generation. The talk was transcribed using Whisper.cpp and co-edited with the open beta of ChatGPT to improve the flow of the text.

Good morning everyone. My name is Judith van Stegeren and I'm here to present a fun project that I worked on together with my co-author Jakub.

I wrote this list of tips for networking just after I visited my first conference, where networking was supereasy! And it was FUN! Although Troopers 2017 was an industry conference, the tips should work fine for academic conferences too.

I talked to so many interesting people, people working in infosec from all over the globe. I even managed to help some of them, by answering questions on social media, introducing people to each other, and pointing people to good self-education resources on the internet. I love to help people, so that made the networking activity feel very natural for me. It was not like the picture I had in my head at all (people in suits loudly talking about themselves while scattering business cards at random). I also loved to exchange horror stories about employers or infosec-gone-wrong. And the most fun thing is to form a spontaneous group of conference-friends and explore the local cuisine.

This is a textual version of the talk I gave at the Intelligent Narrative Technologies workshop at AIIDE 2020, for the research paper titled Fantastic Strings and Where to Find Them. The talk was transcribed using Whisper.cpp and co-edited with the open beta of ChatGPT to improve the flow of the text.

Hi everyone, thank you for tuning in to my talk. My name is Judith van Stegeren and I collected three new datasets with video game text.

GPT-2 and BERT are two methods for creating language models, based on neural networks and deep learning. GPT-2 and BERT are fairly young, but they are 'state-of-the-art', which means they beat almost every other method in the natural language processing field.

GPT-2 and BERT are extra useable because they come with a set of pre-trained language models, which anyone can download and use. Pre-trained models have as main advantage that user don't have to train a language model from scratch, which is computationally expensive and requires a huge dataset. Instead, you can take a smaller dataset and "fine-tune" the large, pre-trained model to your specific dataset with a bit of additional training, which is much cheaper.

A few months ago I was interviewed by Wired about NaNoGenMo 2019, an online programming challenge where participants try to build a novel-generator in 30 days. The interview was part of the background research for this Wired article.

I figured some people might be interested in this interview too, so I decided to put the questions and their answers up on my blog. I've rewritten some answers of my answers to clarify them -- the reporter who interviewed me had read my NaNoGenMo paper, but perhaps you haven't. :)

Today was the Alice & Eve 2020 symposium at the University of Twente. I sent in an abstract for the poster session about last year's paper about story generation, in which I discuss 60 projects from NaNoGenMo 2018.

The audience of Alice & Eve's poster session was "people with a technical background", so a relatively general audience. I tried to write the abstract in such a way that anyone can understand it. I'm pretty happy with how it turned out, so now you can read it here. :)

Following some of my favorite bloggers, I've written an overview of 2019. It was a very good year: I spent a lot of time traveling, meeting new people and learning new stuff. I've noticed I'm slowly getting better in the things that were new in the first year of my PhD, such as writing scientific papers and formulating research questions.

In this blogpost I want to explain how I use Twitter, and how social media is helping me with my research.

This blogpost is meant for researchers that either already have an account at Twitter or want to start using it. Throughout this post, I do assume you are already familiar with how Twitter works. If you're not, read the documentation in the Twitter help center or just create an account, dive in and learn it by doing. ;)

By popular demand, another conference report! Please note that this report is very biased towards the topics that are relevant for my PhD research, i.e. text generation and procedural content generation for games.

Between August 24 and August 27 2019 I visited the IEEE Conference On Games (COG) in London, UK.

This is a short report of my visit to ICCC, or the International Conference on Computational Creativity 2019, in Charlotte, NC. It's not meant as a summary, but as an overview of the things I found interesting during the conference. If you want more information about the talks, check the conference program, or read the live-tweets from Matthew Guzdial, Christoph Salge and me.

I'm working as a PhD student at the University of Twente, where I research natural language generation for adapative games. People often ask me what my research is about, so I figured I should write a blogpost to explain a bit more about my research field.

A natural language is a language that is used by humans, such as English, Dutch or Japanese, as opposed to the formal languages of mathematics and logics. Note that I use this very informal definition, since I'm a computer scientist and not a linguist. If you ask a linguist to define a natural language, you get probably many different answers, such as the definition from Wikipedia.

Blogger and book master Ryan Holiday wrote an article in which he describes his personal way of reading books. His method builds heavily on note-taking and is optimized for recording thoughts, associations and interesting quotes during reading. These notes can then be used for further research or as writing material. After stumbling upon Holiday's blog post, I wanted to try this method for myself.

What better way to test Holiday's method for reading books by testing it out on one of his own? So I went to the local bookstore and obtained a copy of "The Obstacle is the Way", a book about the philosophy of the Stoics. Then I followed the method as described in Holiday's blog post. Here are my experiences.

When I was writing my master's thesis, I discovered that to finish the thesis I needed more than divine inspiration and mathematical skill. I needed discipline and a good dose of tenacity. I started collecting productivity hacks and tips and tricks on writing research papers. This article summarizes the best tips I found.

1. Optimise your productivity

Hello world.

When I was still a student, I was mentally preparing myself for becoming a PhD student. I knew from the experiences of some acquaintences that the life of a PhD student can be hard and stressful.