D13-1178 developed a probabilistic solution for template generation . However , their approach requires
A00-1011 refer to the same event . The Template Generation module uses a set of declarative
A00-1011 Template Generation Module A typical template generation module is a hard-coded post-processing
D14-1087 this paper has its own merit in template generation . Finally , by comparing the
D14-1087 is needed in this approach for templates generation . Li et al. ( 2013 ) proposed
D14-1087 extracted from a web corpus to improve template generation . A nonlinear scoring function
A00-1011 resolution module , and a configurable template generation module . We report quantitative
J14-4004 Therefore , when following our template generation strategy , SRL information contributes
J14-4004 decision tree . When following our template generation method , they are the most discriminative
D14-1087 are quite effective in improving template generation . Fourth , the best performance
D14-1087 and term clusters ) to improve template generation . Second , we propose a nonlinear
H01-1009 extraction system with appropriate template generation , etc. . However , finding a
A00-1011 and events without changing the template generation code . REES maps XML-tagged output
D14-1087 only one of the two stages of template generation . The tagging results are for
A00-1011 module ( cf. Section 2.2 ) , and a template generation module ( cf. Section 2.3 ) .
A00-1011 of template . By contrast , our Template Generation module is unique as it uses declarative
C94-2173 slot . \ -RSB- ? inally , l.he template generation pro ( : ess assembles the extracted
D13-1045 different from ours . 2.2 Query Template Generation The concept of query template
H93-1111 templates to train classifiers for template generation . No further human intervention
A97-1031 systematic ( but still shallow ) way . Template generation An FCP expresses restrictions
hide detail