My responsibilities include designing and populating a database of linguistic typology and language universals, developing tools for automatically extracting feature values from corpora, and providing linguistic consulting to computer scientists working with annotated data resources.

Refined rules for converting a treebank of constituency trees to dependency trees. Collaborated with computer scientists in the rapid development of named entity recognition systems for under-resourced languages. Participated in the evaluation of an unsupervised morphological analyzer.

Published linguistics research in peer-reviewed journals. Carried out linguistic fieldwork on underdescribed languages. Performed corpus-based, quantitative and qualitative research on the word structure of a minority language (Python/NLTK). Developed WebComparator, a web-based software package for managing comparative linguistic data and performing comparative reconstruction (Haskell/SQLite). Taught four courses per year in various subfields of linguistics, including phonetics, phonology, morphology, field methods, and linguistic typology. Trained undergraduate and graduate students in theoretical and field linguistics, cultivating excellent communication and mentoring skills. Oversaw research assistants using strong managerial skills. Supervised two MA thesis, one PhD dissertation, and participated in numerous MA and PhD committees.

Developed, as part of a team, a web application (Perl/MySQL) for etymological analysis and management of comparative linguistic data. Migrated a large, multilingual lexical database from FileMaker to MySQL. Authored tools for organizing and typesetting an English-Lahu dictionary (Python/LaTeX).