Here’s a list of tools developed in collaboration with colleagues and students.
Entity Aspect Linking. A tool for linking an entity-mention in context to the most relevant section of its Wikipedia page. [paper, demo, code, resources]
Semantic Text Scaling. A tool for unsupervised semantic scaling of political text. [polsci-preprint, nlp-paper, demo, code, resources]
Entity-based Topic Modeling. A tool for corpus exploration that associates each LDA topic with a descriptive entity-label. [paper, code, evaluation-platform]
Collecting News from the Internet Archive. A series of simple scripts from creating a dataset of news from the Internet Archive archived version of a newspaper website. [Python code and R re-implementation]
Highlighting Sentences in Political Manifestos. An easy-to-use visualisation for highlighting specific sentences in political manifestos, in collaboration with Giacomo Nanni. [code]
TREC-Car Dataset: How To. A few scripts to pull out useful information from the TREC-Car dataset. [code]