William Mattingly, PhD's Virtual Bookshelf
📕 Introduction
- Position: Postdoctoral Fellow, Smithsonian Data Science Lab
- Specialization: History, AI, and NLP with a focus on archival documents.
- Connect: LinkedIn | Twitter
📙 Open Source Packages
| Name | Description | GitHub Stars | PyPi |
|---|---|---|---|
| 🐍 Python Tutorials for DH | Python coding for humanists. |  |
|
| 🧬 DNA spaCy | Processing DNA inside of spaCy. |  |
 |
| 📖 Vulgata spaCy | Identifying Biblical quotes in Latin texts. |  |
 |
| 🐼 Streamlit Pandas | Pandas DataFrame query applications. |  |
 |
| 📊 LeetTopic | Transformer-based topic modeling. |  |
 |
| ⚖️ Gender spaCy | A pipeline for identifying gender of PERSON entities. |  |
 |
| 🧬 BioSpaCy | Processing biology texts for taxonomic data. |  |
 |
| 🌍 WW2 spaCy | Identify entities specific to WW2. |  |
 |
| 💽 Weaviate Filter | A library for generating nested GraphQL filters for Weaviate. |  |
 |
📗 Publications
- 📖 Introduction to Python for Humanists
- 🧪 Let the Records Show: Attribution of Scientific Credit
- 🏛️ The Classical Language Toolkit: An NLP Framework
📘 Research Interests
- Ethical application of AI on archival documents
- Holocaust and Human Rights documents
- NLP for ancient and medieval languages
- Digital Humanities
- Data Science and History
📒 Contact Me
- LinkedIn:
WJB Mattingly - Twitter:
@wjb_mattingly
This structure uses a combination of headers, bullet points, and horizontal lines to segment information, making it easy to scan. If this was on a website or digital platform, you could also incorporate interactive elements, hover effects, or even images for a more immersive user experience.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent