P13-1140 our method is able to learn some unknown word translations . From the induced phrase pairs
D15-1170 shows the results of applying unknown word translation . It shows that translating all
D15-1170 synthetic translation rules for unknown word translation . Given an unknown word wu ,
W04-3208 4 EM lexical learning to find unknown word translations from the extracted parallel sentences
W12-5604 words . Figure 2 shows the OOV or Unknown Words translation process in a flow chart . Proposed
D15-1170 parsing . Finally , we address the unknown word translation issue via synthetic translation
W09-0212 to the identification of yet - unknown word translations . The proposed algorithm is based
P13-1140 they can not learn idioms and unknown word translations from monolingual data . Obvi
P13-1140 not learn idiom translations and unknown word translations . The third is to estimate the
P13-1140 to learn idiom translation and unknown word translations . We will elaborate how to induce
D15-1170 size of unknown words , adding unknown word translation rules has a very limited impact
P15-1002 ( trans ) and after ( + unk ) unknown word translations . We also show the human translations
D15-1170 data with three alignments , and unknown word translation , obtains consistent improvement
P15-1002 words that are involved in the unknown word translation process . 5.4 Sample Translations
D15-1170 synthetic translation rules for unknown word translation . As a baseline , we simply skip
D15-1170 Synthetic Translation Rules for Unknown Word Translation Most NLP tasks face the problem
P13-1140 phrase pair ; 2 ) idioms ; and 3 ) unknown word translations . Table 1 gives examples for
W12-5604 does not use CSTs , WordNet and unknown words translation solutions . Currently from the
P15-1002 the graph ) . When applying our unknown word translation technique ( purple curve ) ,
P06-1081 in Academia Sinica is the first unknown word translation system based on web - mining
hide detail