| C86-1088 | first-order model structure . A proper | embedding | is a function from 1J / ~ to |
| D15-1200 | relat - edness , controlling for | embedding | dimen - sionality . We find that |
| C88-1033 | reformulated as the problem of finding an | embedding | function f from the representational |
| S15-2092 | hand-crafted features and message-level | embedding | fea - tures , and uses an SVM |
| S15-2155 | work on using vector space word | embedding | models for hypernym-hyponym extraction |
| W15-3822 | method called Surrounding based | embedding | feature ( SBE ) , and two newly |
| W10-4104 | PClauses indicating the depth of the | embedding | and overlapping . PClause " fTfT |
| D15-1038 | completion impute missing facts by | embedding | knowledge graphs in vector spaces |
| S15-2094 | traditional features and word | embedding | features to perform sentiment |
| P10-1121 | HHMM framework , a new metric , | embedding | difference , is also proposed |
| P97-1060 | logic and tree automata and the | embedding | of MSO logic into a constraint |
| S14-2011 | provides dense , low-dimensional | embedding | for each fragment which allows |
| P15-1025 | with the variable size of word | embedding | vec - tors , we employ the framework |
| C80-1074 | operator ( Fill , FII 2 and FI21 ) , | embedding | operator fill and connecting |
| D15-1191 | proposes context-dependent KG | embedding | , a twostage scheme that takes |
| D15-1054 | is to explore the use of word | embedding | techniques to generate effective |
| W15-3822 | : Left-Right surrounding based | embedding | feature ( LR_SBE ) and MAX surrounding |
| J10-3010 | extrinsic evaluation is done by | embedding | the expansion systems into a |
| D14-1167 | Zheng Abstract We examine the | embedding | approach to reason new relational |
| D14-1113 | word sense discrimination and | embedding | learning , by non-parametrically |
