Home > Taxonomy > Research > Machine Translation

Machine Translation

Title: Semantic and Stylistic Variations in Machine Translation

Abstract: While parallel texts represent invaluable resources for machine translation, they inevitably introduce biases in the cross-lingual mappings learned by machine translation models.  In addition to the domain bias and translationese bias studied in past work, we argue that another form of bias arises from subtle choices in content and style made by translators to appropriately convey the meaning of the source to their target audience.

A question-answering system designed by researchers from UMD and the University of Colorado holds its own against a top human team.

Language Science Day 2014

LSD marked the 1-year anniversary of the Maryland Language Science Center, showcasing many ideas and initiatives launched over the past year.

National security challenges demand leaders who can speak in uncommon languages.

The language science initiative lets students create individualized programs of study.

Language Science Day (LSD) is a signature annual event for Maryland's language science community. Each Fall, LSD brings together up to 200 students and faculty from across the University and affiliated centers, providing opportunities for participants to exchange ideas, showcase new or ongoing projects, find out about research and training opportunities, spark potential collaborations, and get to know their fellow language scientists.

Our technology depends on a sophisticated understanding of speech and language.

Language Science Day

Visit our website to register for the 5th annual Language Science Day taking place Friday, September 19th, from 12 – 5pm, at the Stamp Student Union.

Subscribe to Machine Translation