| W15-3820 | representations , also known as word | embedding /embedding/NN | , have been shown to improve |
| W15-3820 | performance of two state-of-the-art word | embedding /embedding/NN | methods , namely word2vec and |
| W15-3822 | method called Surrounding based | embedding /embed/VBG | feature ( SBE ) , and two newly |
| W15-3822 | : Left-Right surrounding based | embedding /embedding/NN | feature ( LR_SBE ) and MAX surrounding |
| W15-3822 | LR_SBE ) and MAX surrounding based | embedding /embed/VBG | feature ( MAX_SBE ) . We then |
| W15-3822 | Minnesota showed that neural word | embedding /embedding/NN | features improved the performance |
| W15-4005 | regression to learn the bilingual word | embedding /embedding/NN | using compositional distributional |
| W15-4310 | representation . Besides word | embedding /embedding/NN | , we use partof-speech ( POS |
| W96-0413 | set for the same variable in the | embedding /embedding/NN | structure . An inner quantifier |
| W97-0901 | reports on SRA 's experience in | embedding /embedding/NN | name recognition in these three |
| W98-1311 | Another aspect to consider is the | embedding /embedding/NN | of the single elements of the |
