Monday, October 21, 2024

Homebrewed Software: A Handwriting Transcription App

By Shawn Graham Continuing from the last experiment and ruminating on Drew Breunig's taxonomy of use cases for AI (in short: gods, interns, cogs, and toys) as well as 'homecooked software' I undertook to use Anthrophic's 'Claude' model to see what I could do. I'm building a cog via Claude's 'artifacts' feature which allows... More

Friday, October 18, 2024

Transcribing Handwriting with a Multimodal Model

by Shawn Graham Legacy archaeological data is often trapped in handwritten context sheets, site diaries, and scraps of paper. Transcribing such materials so that one can work with them is time consuming and difficult. If you're an English speaker, trained in North American cursive you're probably better off that the average undergrad today who... More

Monday, June 3, 2024

Using a Large Language Model and Pydantic to Extract Structured Data for Cultural Heritage Crime

A few weeks ago Vianney Mixtur published a blog post and related code repository showing how he used the Mixtral model to pull together recipe data from semi-structured cookery information. We have been experimenting here for some time using a variety of approaches to create knowledge graphs from academic articles, newspaper articles, auction... More

Tuesday, April 9, 2024

The Behaviour Space(s) of Large Language Models

By Shawn Graham. For many years, I built agent based models of various phenomena based on archaeological data. These are models of interacting software agents in a simulated environment, with many different parameters; the first step in understanding what your model implies for the culture under study is to understand how your model behaves.... More

Wednesday, March 27, 2024

XLab Confab Agenda

XLab Confab Agenda Location: Richcraft Hall (River Building), 2nd floor atrium & conference rooms. Location Map Here. We will email participants attending virtually a zoom link - watch your inboxes! Day 1: Tuesday, April 2nd, 2024 8:30 am: Grab a name tag and have a coffee! 9:00 am - 9:10 am: Welcome, Land Acknowledgement... More

Friday, March 15, 2024

XLab Confab Keynote – Building the Internment Archaeology Digital Archive

Dr. Ethan Watrall will be delivering our keynote address: Building the Internment Archaeology Digital Archive - A Practical Discussion of a Community Engaged Digital Heritage Project. In 1942, President Roosevelt issued Executive Order 9066. Nearly overnight, 120,000 Japanese Americans were rounded up and shipped off to incarceration and... More

Tuesday, March 5, 2024

XLab Confab Workshops

In a month's time, we'll be hosting the XLab Confab and we really hope you'll join us! The workshops can be counted towards the Canadian Certificate in Digital Humanities. And what are the workshops about? We're glad you asked! Dr. Ethan Watrall will be taking us through issues around building and sustaining digitization projects... More

Thursday, February 22, 2024

Maps and Annotations

Michael Carrier is an MA History with Digital Humanities Student, with a focus on archaeological research The Thomas Ashby photographic archive is now in the public domain. Ashby was the first student (and later, the third Director) of the British School at Rome, and pioneered landscape archaeology in Italy through a number of ground... More

Tuesday, February 6, 2024

LLM as a discovery bridge for an API

...in which I discuss the logic and functioning of two jupyter notebooks that use Simon Willison's LLM to act as a kind of discovery agent for a history api and an archaeology api. Both notebooks are available for copying and improving and use! Crossposted from ElectricArchaeology by Shawn Graham I have been playing with... More

Thursday, January 25, 2024

Call For Papers – Speculative Futures in Cultural Heritage Informatics

Speculative Futures in Cultural Heritage Informatics An open-access volume edited by Katherine Davidson, Kavita Mistry, and Scott Coleman, to be published by The Digital Press at the University of North Dakota With a foreword by Shawn Graham and an Afterword by Ethan Watrall You are a graduate student or early career researcher working at... More

Friday, December 15, 2023

Qualitative Analysis of Social Media Posts – A Workflow from OCR to Obsidian

In the past, we have applied many different distant reading techniques to social media posts related to the human remains trade. As part of a new analysis, we are exploring a computer-facilitated close reading of social media posts. Here we detail a workflow that assumes one already has a collection of images that capture... More

Friday, December 8, 2023

Trawling Data: The Panama Papers and our Knowledge Graph

The dataset for the Panama Papers is available here. Wouldn't it be great to examine it for people connected to the antiquities trade? In this post I try to do that, using our knowledge graph generated from the Trafficking Culture Encyclopedia. Behind that link you will find: Offshore Leaks (2013) Panama Papers (2016) Bahamas... More

Wednesday, November 15, 2023

Notes on Building a GPT Agent with OpenAI

OpenAI has recently unveiled a new feature, where you can customize an underlying GPT model to become a kind of agent for you. To do this, you have to have the $20 a month subscription, or have paid access to the API. If you only have API access, you can build in the sandbox... More

Wednesday, October 25, 2023

Further Adventures with LLM-GPT4All and Templates

Yesterday Simon Willison updated the LLM-GPT4All plugin which has permitted me to download several large language models to explore how they work and how we could work with the LLM package to use templates to guide our knowledge graph extraction. For instance, using GPT4, we could pipe a text file with information in it... More

Tuesday, October 24, 2023

Using Simon Willison’s LLM Package to Extract a Knowledge Graph

Simon Willison's LLM package is a lovely little command line utility that allows you to work with many different large language models. In this post, we use LLM to extract a knowledge graph from a mermaid diagram sketch. 1. Sketch out the basics of your knowledge graph. On paper - yes, on paper! It's... More

Tuesday, October 10, 2023

archaeCLIP: or building a visual search engine for archaeology

If you take a bunch of text, and drop it through a large language model, you can get what is called an 'embedding' - a mathematical representation of where that text, that idea you wrote, is located within what the model 'knows'. Other texts that get embedded get a location, too, and once you... More

Wednesday, September 20, 2023

Congratulations to the 2023 XLab graduates!

Covid played merry hell with our schedules, but we're pleased to say 'congratulations' to our student RAs who have made it to the finish line in 2023! Chantal Brousseau wrote Metadata in the Margins: Reshaping Archives as Data through Early Modern Marginalia . In this major research essay, Chantal rebuilds an open source image... More

Wednesday, September 13, 2023

Setting Up Some Project Management Software

Shawn here. I've always found managing other people and projects to be a very challenging aspect of the job of being an academic. You work largely by yourself for so many years, and then one day, you find yourself trying to guide students, keep their projects on track. You end up with budgets, and... More

Tuesday, September 5, 2023

XLab Awarded CFI-JELF Funding

Laura Banducci and Shawn Graham are pleased to report that the XLab is one of 13 Carleton recipients of a grant from the Canada Foundation for Innovation’s John R. Evans Leaders Fund (JELF) to develop and support the XLab! This includes funds for setting up laboratory space for some kinds of archaeological analysis, a... More

Thursday, August 10, 2023

A follow-up to ‘Mermaid Diagram to Ontology via GPT3 for the illicit antiquities trade’

  Using the ontology crafted in the previous post I fed 129 Trafficking Culture articles through GPT4. I used a script to pass the ontology, with You are an excellent assistant with deep knowledge of research in the field of illegal and illicit antiquities. Below is an ontology structuring knowledge about the field; using... More

Friday, July 28, 2023

Mermaid Diagram to Ontology via GPT3 for the illicit antiquities trade

I believe chatgpt using GPT4 is only available to plus customers (July 2023 version) so what follows was developed using GPT3, though in my next experiment, I will be able to use GPT4 to process unstructured text in bulk using the results of today's experiment. In a blog post, Kingsley Uyi Idehen demonstrated his... More

Wednesday, June 28, 2023

Writing An Ontology with ChatGPT3

So far in our experiments with knowledge graphs and large language models (see here,and here ) we've been content to work with the unstructured text and let the data model, such as it is, to percolate up from below, trying to impose a bit of structure on it afterwards by seeing what subject -... More

Wednesday, May 31, 2023

Using GPT3 To Generate a Knowledge Graph

We talked a bit about using GPT3 to create a knowledge graph in an earlier post.  In this one, we'll go into the weeds with a bit more detail. If you could take a long-distance, macroscopic, big-picture look at the antiquities trade, what might you see? This is the question animating our 'New Organigram... More

Friday, March 24, 2023

Computer, Digital Archaeology Now!

A version of this post was originally put on Shawn Graham's Electric Archaeology What if you could do digital archaeology by simply describing what you wanted to happen? Or any kind of cultural heritage informatics work? Like the computer in Star Trek, what if you could just describe what you want to have happen,... More

Tuesday, February 28, 2023

Applying RTI Analysis To Byzantine Coin Wear Patterns: Who did What in Medieval Athens?

  Scott Coleman is a PhD candidate in the Department of History As discussed in my previous Xlab post, I am interested in applying Reflectance Transformation Imaging (RTI) and photogrammetry/3D imaging to study Byzantine (Eastern Roman Empire) coins. In particular, I want to explore how these methods can be implemented to create better... More

Friday, February 17, 2023

The “Collector Psychology”

Katherine Davidson is a PhD candidate in the Department of Sociology and Anthropology. Many, many thanks to Tina Nichol for the conversation which led to this blog topic. I have been wrapping up my doctoral fieldwork over the last few months, where I am exploring the meaning that understudied collections have for First Nations... More

Wednesday, February 8, 2023

Unpacking AI’s Problems with Physical Media

Katherine Davidson is a PhD candidate in the Department of Sociology and Anthropology The AI debate is upon us in full swing; Getty Images is suing Stability AI over digital image copyright (Vincent 2023), OpenAI and others are releasing tools to help detect AI-written text (of particular interest to educators in the fight for... More

Thursday, February 2, 2023

Knowledge Graphs and GPT-3

One of the things we're working on in our group are ways to extract structured knowledge from lots of unstructured text. In an article coming out soon in Advances in Archaeological Practice, we demonstrate some of the things that we can accomplish when we have statements about a domain (in this case, the antiquities... More

Monday, January 9, 2023

Excavating Memes and the Bone Trade on Instagram

Cassandra McKenney is an MA student in the Department of History Part of Xlab’s work is concerned with how people engage with cultural heritage artifacts and ideas in digital environments. This led us to a collaborative study of memes related to human remains trading, or the “Bone Trade” on Instagram, including the accounts who... More

Thursday, November 17, 2022

Digital Absences in Cultural Heritage: Who cares?

Sam Nicholls is an MA student in the Department of History I’ve spent a lot of time in heritage institutions – as both visitor and employee. I’m sure if you’re reading this post, that you also have likely spent some time within these organizations, at either the local or national level. My experience in... More

Wednesday, November 9, 2022

The Imagination of the Machines

Kavita Mistry is a PhD candidate in the Department of History If you have seen me walking around campus, you will know me as the “tiny girl with the massive backpack” because I carry a 5 lbs gaming laptop everywhere I go. But it’s for good reason. I am returning as a Research Assistant... More

Wednesday, November 2, 2022

Rethinking Access to Ancient Coins: A Reflective Transformation Imaging Story

Scott Coleman is a PhD candidate in the Department of History For my first Xlab post, I will discuss how I came to be part of this extraordinary group of scholars seeking to push the boundaries of digital scholarship. I first joined the Xlab team in the fall of 2021. I intended to perform... More

Thursday, October 20, 2022

For your toolbox: AI transcription for audio files

Katherine Davidson is a PhD candidate in the Department of Sociology and Anthropology For those of us using audio recording for data collection - one-on-one or group interviews, archival audio, collaborative audio-visual methods - having a good resource for accurate and fast transcription is a game-changer. Transcription services quickly turn your... More

Thursday, October 20, 2022

Paying it Back and Forward

Katherine Davidson is a PhD candidate in the Department of Sociology and Anthropology On October 3rd, 2022, John Oliver aired a special on museums and colonial looting, featuring a short called “The Payback Museum”. Kumail Nanjiani takes viewers on a tour of all the places that nations would display their cultural heritage, had it... More

Thursday, October 13, 2022

Machine Learning and Knowledge Graphs

Jonah Ellens is a second year student in the Department of History This year I’m continuing to assist Xlab’s 'The New Organigram Project' as a researcher. For the Organigram Project uses machine learning to help build a knowledge graph modelling the trafficking of stolen antiquities. To support the work, I get to delve into... More

Share: Twitter, Facebook
Short URL: https://carleton.ca/xlab/?p=20