| tech,16-1-P05-1073,ak | work has largely used independent <term> | classifiers | </term> , possibly combined with separate | #10050 Despite much recent progress on accurate semantic role labeling, previous work has largely used independent classifiers , possibly combined with separate label sequence models via Viterbi decoding. | |
| other,21-2-P05-1073,ak | is a joint structure , with strong <term> | dependencies | </term> between <term> arguments </term> . We | #10084 This stands in stark contrast to the linguistic observation that a core argument frame is a joint structure, with strong dependencies between arguments. | |
| other,23-2-P05-1073,ak | strong <term> dependencies </term> between <term> | arguments | </term> . We show how to build a joint <term> | #10086 This stands in stark contrast to the linguistic observation that a core argument frame is a joint structure, with strong dependencies between arguments . | |
| other,14-3-P05-1073,ak | frames </term> , incorporating novel <term> | features | </term> that model these interactions into | #10102 We show how to build a joint model of argument frames, incorporating novel features that model these interactions into discriminative log-linear models. | |
| other,11-4-P05-1073,ak | error reduction </term> of 22 % on all <term> | arguments | </term> and 32 % on <term> core arguments </term> | #10123 This system achieves an error reduction of 22% on all arguments and 32% on core arguments over a state-of-the art independent classifier for gold-standard parse trees on PropBank. |
