Yuhuan Jiang edited Word Based Models.md  over 10 years ago

Commit id: bb4f70c2e05564d4227512de164178bebd33574c

deletions | additions      

       

The probability of translating one sentence to another sentence is:  \[p({\bf{t}}|{\bf{s}})\]  where $\bf{t}$ is the $ert$  word sequence (represented by a vector of words) of the target language, and $\bf{s}$ is the word sequence of the source language. In a Chinese to English translation task, the source language is Chinese, and the target language is English.