Facilitating Language Hacking with Digital Tools: A Study of Translation Alignment

Abstract

Master's Defense:

This project examines digital translation alignment as a tool for facilitating a new paradigm of “language hacking.” In this frame, readers use translations as an aid for engaging directly with source texts in languages with which they are unfamiliar, rather than as a replacement for the original materials. I present the results of a pilot study measuring the impact of this form of annotation on the comprehension of users of a digital reading environment and introduce and evaluate a novel approach to the task of generating aligned translations using Universal Dependency Trees.

Research areas: Translation Alignment, Language Acquisition, Natural Language Processing, Graph Theory, Human-Computer Interaction