In this episode of the Research Like a Pro Genealogy podcast, Diana and Nicole discuss the advancements in handwritten text recognition by large language models (LLMs), specifically Claude 3.5 Sonnet. Nicole shares her experience testing Claude’s transcription abilities with an 1829 North Carolina deed. She is impressed with the accuracy, noting that Claude even outperformed her manual transcription in some instances. Diana and Nicole then provide listeners with valuable tips for transcribing handwritten text using...
In this episode of Research Like a Pro, Nicole and Diana discuss Transkribus, a platform that uses AI to transcribe handwritten documents. They explain how Transkribus works, the benefits it offers for genealogy research, and how to get started using it. Diana and Nicole outline the transcription process, including uploading documents, choosing the right model, and reviewing the results. They also highlight advanced features like language models, Smart Search, and Super Models, which can improve...
In this episode of the Research Like a Pro Genealogy podcast, Diana and Nicole discuss using AI in timeline creation and source analysis. Diana shares her experience using AI tools to transcribe, abstract, summarize, and analyze documents for her Isabella Weatherford project. She explains how AI can be a powerful ally in genealogical research, but emphasizes the importance of verifying AI-generated information and using your own genealogical expertise to interpret the results. Diana used AI...
In this episode of the Research Like a Pro Genealogy Podcast, Nicole and Diana interview Steve Little, the National Genealogical Society Artificial Intelligence Program Director. Steve explains what Large Language Models are and their strengths, including summarization, extraction, generation, and translation. He discusses how AI can be used in genealogy to extract names, dates, and relationships from text, assist with genealogical writing and translating documents, transcribe printed and handwritten text, and transform text to different...
Welcome back to my series on Isabella Weatherford! In part one, I used AI to explore research questions and write the research objective: The objective of this research phase is to examine the economic and social conditions in Dallas County, Texas, in the early 1870s and their influence on Isabella D Weatherford’s life and marriage prospects. Isabella was born on 4 Mar 1858 in Missouri; she first married John H. Carpenter on 16 Jan 1874...
In this episode, Diana and Nicole discuss the advancements in AI tools for transcribing handwritten text. They highlight FamilySearch’s new full-text search feature that uses AI to transcribe deed and probate images, and they demonstrate how ChatGPT and Claude can quickly transcribe uploaded images, significantly reducing the time needed for such tasks. They explain that before May 13, 2024, file upload capabilities were exclusive to the paid version of ChatGPT, but the newly released...
Would you like to automate the transcription of handwritten documents? Or quickly search for a particular name in a large probate or pension application file? Transkribus is an innovative platform that harnesses the power of artificial intelligence (AI) to make deciphering old handwriting faster. Whether you’re tracing your family tree or researching historical figures, Transkribus can save you countless hours by automatically transcribing handwritten documents into searchable text. In this blog post, we’ll explore how...
Handwritten text recognition by large language models (LLMs) has become much better with the latest releases of ChatGPT 4o and Claude 3. 5 Sonnet. Claude 3.5 Sonnet is the smartest LLM available today. See Anita Kirkovska, “Claude 3.5 Sonnet vs GPT-4o,” vellum (https://www.vellum.ai/blog/claude-3-5-sonnet-vs-gpt4o). I decided to test Claude 3.5 Sonnet with one of my favorite tasks – handwritten text recognition, a challenging task for LLMs. To test the capabilities of Claude 3.5 Sonnet, I created a...
Artificial Intelligence tools have made huge strides in transcribing handwritten text in recent years. I’ve already written about FamilySearch’s use of AI to transcribe thousands of deed and probate images here: AI-Powered Full-Text Search of Handwritten Text at FamilySearch. In this post, I’ll share how I’ve been using ChatGPT 4.0 (the paid version) and Claude (free version) to upload images (.jpg and .png) and transcribe them quickly. These large language models (LLMs) do a pretty...
Uniquely identifying a person who is only mentioned in three records can be challenging. The creation of a research objective requires that you identify the person uniquely in time and place. How then, do you define the research project? I encountered this challenge when beginning a project to study Sally Keaton. The only records I have for her include a court order printed in a newspaper and two documents in William Keaton’s estate packet. The...
