Brendan O’Connor is a researcher and data scientist writing about programming languages, data analysis, and machine learning. His work bridges Python, R, and Java, with thoughtful essays on software tools, research workflows, and empirical data exploration.
6 articles from this blog
A guide for Python/R users transitioning to Java, focusing on the necessity of IDEs like Eclipse or IntelliJ for productive development.
Explains the meaning of ACL 2014 peer review scores and criteria for natural language processing papers.
A scatterplot analysis comparing perplexity results of Kneser-Ney, hierarchical Pitman-Yor, and hierarchical Dirichlet language models from a research paper.
Explains the mathematical relationship between the tanh and logistic sigmoid functions, and why tanh is preferred in neural networks.
Authors respond to critique of their computational linguistics paper on analyzing movie characters, discussing interdisciplinary research methods.
An intuitive, probabilistic explanation of the B3 coreference resolution metric, focusing on precision and recall calculations for clustering evaluation.
