Mixed-initiative Natural Language Translation a Dissertation Submitted to the Department of Computer Science and the Committee on Graduate Studies of Stanford University in Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy

�ere are two classical applications of the automatic translation of natural language. Assimilation is translation when a gist of the meaning is su�cient, and speed and convenience are prioritized. Dissemination is translation with the intent to communicate, so there is usually a prede�ned quality threshold. �e most common assimilation scenario is cross-lingual web browsing, where fully automatic machine translation (MT) best satis�es the speed and convenience requirements. Dissemination is the setting for professional translators, who produce translations with the intent to communicate. MT output does not yet come with quality guarantees, so it is best incorporated as an assistive technology in this setting. �is dissertation proposes amixed-initiative approach to translation for the dissemination scenario. In amixed-initiative system, human users and intelligentmachine agents collaborate to complete some task. �e central question is how to design an e�cient human/machine interface. By e�cient wemean that human productivity should be enhanced, and themachine should be able to self-correct its model by observing human interactions. We separate human productivity into two measurable components: translation time and quality. We �rst compare unaided translation to post-editing, the simplest form of machine assistance. Human translators manipulate machine output to arrive at a �nal translation. We �nd that simple post-editing decisively improves translation along both coordinates, a result that motivates more advanced machine assistance. However, it is widely observed in prior work that users regard post-editing as a tedious task. �e main contribution of this dissertation is therefore a more interactive mode of machine assistance that can improve both productivity and the user experience. We present Predictive Translation Memory (PTM), a new interactive, mixed-initiative translation system. �e machine suggests future translations based on previous interactions.