| E12-1043 | toolkit to compute the proposed | hybrid kernel | . The ratio of negative and positive |
| E12-1043 | depending on the corpus . The proposed | hybrid kernel | is valid according to the closure |
| E12-1043 | this paper , we propose a new | hybrid kernel | for RE . We apply the kernel |
| E12-1043 | results show that the proposed | hybrid kernel | attains considerably higher precision |
| E12-1043 | , the results of the proposed | hybrid kernel | are on par with the stateof-the-art |
| E12-1043 | the PET kernel . It allows the | hybrid kernel | to assign more ( or less ) weight |
| E12-1043 | used as a component of the new | hybrid kernel | . Empirical results show that |
| E12-1043 | extraction results of our proposed | hybrid kernel | with those of other state-of-the-art |
| E12-1043 | results show that the proposed | hybrid kernel | achieves considerably higher |
| N13-1093 | the PET kernel . It allows the | hybrid kernel | to assign more ( or less ) weight |
| P06-2010 | convolution tree kernel . Our | hybrid kernel | method using Voted Perceptron |
| N13-1093 | To verify whether our proposed | hybrid kernel | achieves state-of-the-art results |
| E12-1043 | results show that the proposed | hybrid kernel | attains considerably higher precision |
| E12-1043 | corpus LLL ) is much higher for the | hybrid kernel | than for the individual components |
| E12-1043 | among the results of the proposed | hybrid kernel | and its individual components |
| E12-1043 | Section 4 , we define our proposed | hybrid kernel | and describe its individual component |
| E12-1043 | paper , we have proposed a new | hybrid kernel | for RE that combines two vector |
| N13-1093 | this section , we propose a new | hybrid kernel | , KHybrid , for this purpose |
| E12-1043 | patterns in the performance of the | hybrid kernel | was not relevant ( as Tables |
| E12-1043 | is a component of the proposed | hybrid kernel | ) . Acknowledgments This work |
