- ARCHIVE / July, 2009
- NLP for Classical Studies
If you’re into humanities computing and NLP, you might want to check out the eAqua project. eAqua stands for ‘Extraction of structured knowledge from ancient sources’, and it’s a project that combines various text mining techniques to extract information for ancient texts. The eAqua-project aims at generating specific knowledge from ancient texts and will provide […]
- Python web-parsing libraries
While continuing the interminable search for the ideal python editor, I run into three really useful libraries for scraping information off webpages: mechanize: Stateful programmatic web browsing in Python, after Andy Lester’s Perl module WWW::Mechanize scrape: Python module for web browsing and scraping BeautifulSoup: a Python HTML/XML parser designed for quick turnaround projects like screen-scraping I had a quick play with the […]
- Roman Port Networks project
The Roman Port Networks Project is a collaboration between 30 European partners, examining the connections between Roman ports across the Mediterranean. The project has received financial support from the British Academy (BASIS) and the University of Southampton (School of Humanities, Department of Archaeology and School of Electronics and Computing Science). From the website (the bold […]