Breakthrough in Simultaneous Translation is coming at 02/04/2019 - 4:00pm Weniger Hall 151 Mon, 02/04/2019 - 4:00pm
Liang Huang Assistant Professor, Oregon State University Abstract: Simultaneous translation, which translates sentences before they are finished, is useful in many scenarios but is notoriously difficult due to word-order differences. While the conventional seq-to-seq framework is only suitable for full-sentence translation, we propose a novel prefix-to-prefix framework for simultaneous translation that seamlessly integrates anticipation and translation. Within this framework, we present a very simple yet surprisingly effective “wait-k” model trained to generate the target sentence concurrently with the source sentence, but always k words behind, for any given k. We also formulate a new latency metric that addresses the deficiencies of previous ones. Experiments show our strategy achieves low latency and reasonable quality (compared to full-sentence translation) on 4 directions: Chinese<->English and German<->English. This technique has been successfully deployed to simultaneously translate Chinese speeches into English subtitles at the 2018 Baidu World Conference. It has also been covered by numerous media reports: https://simultrans-demo.github.io/ [1] [1]. Bio: Read more: https://eecs.oregonstate.edu/colloquium/breakthrough-simultaneous-transl... [2] [1] https://simultrans-demo.github.io/ [3] [1] https://simultrans-demo.github.io/ [2] https://eecs.oregonstate.edu/colloquium/breakthrough-simultaneous-translation [3] https://simultrans-demo.github.io/
_______________________________________________ Colloquium mailing list [email protected] https://secure.engr.oregonstate.edu/mailman/listinfo/colloquium
