Posts about projects

I am currently building a search engine. It seems a weird choice, and maybe unnecessary? So let me explain why I am doing this.

The Internet has been overrun by automated content creation machines. I guess because people and businesses have FOMO about appearing in search results (SEO) and LLM outputs (GEO? AEO?) and they want to sell their products and services. All that AI generated stuff is overwhelming the human-made Internet. Putting text on the internet is no longer proof-of-work. Because of this it has become very difficult for me to find good information. So I've been reading up on ways to deal with that.

This blogpost was co-created with ChatGPT.

In this blogpost, I will describe the workflow I used to efficiently turn my talk videos into blogposts with machine learning. The heavy lifting is done by two relatively new machine learning tools: whisper.cpp and ChatGPT.

Hi everyone! In this post I'll show you how I valuate mergers and acquisitions and other special situation investments. I started doing this after reading You can be a stock market genius by Joel Greenblatt. Despite the clickbait title, this is a really good book about special situation investing.

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.

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.

This is the second post in a series about data-driven investing.

In the first post I described Hetty, a collection of tools for monitoring stocks and doing financial data analysis. Naturally, Hetty needs a steady inflow of financial information, and I prefer not to input that information by hand, so that's where online data sources come in.

This is the first post in a series about data-driven investing.

In this post I describe a software toolkit called hetty, named after Hetty Green, an American investor

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.

Today, Twitter user @iamdevloper started a new meme asking for Harry Potter titles with technical references in them. People started posting so many replies that a friend asked me whether I could find which ones where the best. This post is a write-up of my method. Click here to go straight to the results.

Last updated: October 2020

In this post I want to share some fun data sources for NLG and NLP. In an earlier post, I mentioned why a suitable corpus is important, especially when you're doing natural language generation.

One of my first experiments with natural language generation was writing random-tony, a program that could produce new chocolate flavours. The program uses a grammar as a model of a "valid" chocolate flavour. Here are some examples:

$ python ./generate_flavours.py 

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.

Some time ago I found sensitive personal data on a public web page. I notified the system owner, but was curious to see if my report would have any impact. I decided to monitor the web page to see whether the information was removed.

Since I only wanted to know whether the web page was still online, monitoring changes in the HTTP status code (instead of changes in page content) was enough for this use case. One way of keeping up with the status of a webpage is hitting Refresh until you get a different HTTP status code... But I decided to let my computer do this for me, so I could use my time for more interesting activities.

Last week, when I was visiting the SANS SEC560 course in Brussels, I wrote a small tool in Python 3 called tuvok. This tool takes a tv-series and a minimum rating and then outputs a list of all tv-episodes of that series that have a rating equal to or higher than the minimum rating.