Sharon Goldwater: Resources

Software and data

Word segmentation software. This is an implementation of the models used in my thesis and related papers. (Version 1.2.1, Jan 2016, contains minor fixes for newer compilers contributed by Antonios Anastasopoulos but is otherwise the same as version 1.2, used for the 2009 Cognition paper.)
The data I used, originally collected by Nan Bernstein-Ratner and phonemicized by Michael Brent, is also available as a tar file or a zip file.

Math tutorials: the basics of vectors, sets and counting, and probability theory.
Slides from my two lectures at the IPAM 2011 graduate summer school on Probabilistic Models of Cognition. Intended for a broad (but mathematically savvy) cognitive science audience, they cover foundational models of language, including some Bayesian ways of thinking about standard models: Intro to (psycho)linguistics and n-gram models, HMMs and PCFGs.
Reading list on Bayes for language learning (now very out-of-date, last updated in 2008).

Advice on designing and giving presentations.
Advice on writing clear and concise sentences.
Advice on writing research papers (and theses).
Advice on writing fourth-year and MSc project reports.
How to get a great recommendation letter and get into grad school (both by Matt Might; note that the latter is written for US grad schools and some statements may not apply as much to the UK).
Patterns for Research in Machine Learning, a short guide to best practices in research programming by Ali Eslami, and some further principles by Charles Sutton.
How to be a successful PhD student in CS (especially NLP) by Hanna Wallach and Mark Dredze. A few points about timing are US-specific (where PhDs are far longer than in the UK) but overall this is a great guide for both current and prospective students. (Many students have misconceptions about what they will, or will not, need to learn/do as a PhD student.)