The new model measures distances between words with similar meanings in “word embeddings,” and then aligns the words in both embeddings that are most closely correlated by relative distances, meaning they’re most likely to be direct translations of one another.

Model paves way for faster, more efficient translations of more languages

MIT News Office | October 30, 2018

MIT Institute for Data, Systems, and Society
Massachusetts Institute of Technology
77 Massachusetts Avenue
Cambridge, MA 02139-4307
617-253-1764