Abstract | ||
---|---|---|
MSR-MT is an advanced research MT prototype that combines rulebased and statistical techniques with example-based transfer. This hybrid, large-scale system is capable of learning all its knowledge of lexical and phrasal translations directly from data. MSR-MT has undergone rigorous evaluation showing that, trained on a corpus of technical data similar to the test corpus, its output surpasses the quality of best-of-breed commercial MT systems. |
Year | Venue | Keywords |
---|---|---|
2002 | AMTA | phrasal translation,technical data,statistical technique,microsoft research machine translation,advanced research mt prototype,test corpus,best-of-breed commercial mt system,rigorous evaluation,example-based transfer,large-scale system,machine translation,rule based |
Field | DocType | Volume |
Computer science,Expert system,Machine translation system,Machine translation,Technical information,Speech recognition,Artificial intelligence,Natural language processing,Knowledge base,Automatic translation,Hybrid system,Statistical analysis | Conference | 2499 |
ISSN | ISBN | Citations |
0302-9743 | 3-540-44282-0 | 6 |
PageRank | References | Authors |
0.60 | 7 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bill Dolan | 1 | 2137 | 132.21 |
Jessie Pinkham | 2 | 35 | 5.16 |
Stephen D. Richardson | 3 | 282 | 39.22 |