| tech,6-1-P05-1073,ak | Despite much recent progress on accurate <term> | semantic role labeling | </term> , previous work has largely used | #10040 Despite much recent progress on accuratesemantic role labeling, previous work has largely used independent classifiers, possibly combined with separate label sequence models via Viterbi decoding. | |
| 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 independentclassifiers, possibly combined with separate label sequence models via Viterbi decoding. | |
| model,22-1-P05-1073,ak | </term> , possibly combined with separate <term> | label sequence models | </term> via <term> Viterbi decoding </term> . | #10056 Despite much recent progress on accurate semantic role labeling, previous work has largely used independent classifiers, possibly combined with separatelabel sequence models via Viterbi decoding. | |
| tech,26-1-P05-1073,ak | <term> label sequence models </term> via <term> | Viterbi decoding | </term> . This stands in stark contrast to | #10060 Despite much recent progress on accurate semantic role labeling, previous work has largely used independent classifiers, possibly combined with separate label sequence models viaViterbi decoding. | |
| other,11-2-P05-1073,ak | the linguistic observation that a <term> | core argument frame | </term> is a joint structure , with strong | #10074 This stands in stark contrast to the linguistic observation that acore argument frame is a joint structure, with strong dependencies between arguments. | |
| 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 strongdependencies 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 betweenarguments. | |
| model,7-3-P05-1073,ak | </term> . We show how to build a joint <term> | model | </term> of <term> argument frames </term> , incorporating | #10095 We show how to build a jointmodel of argument frames, incorporating novel features that model these interactions into discriminative log-linear models. | |
| other,9-3-P05-1073,ak | build a joint <term> model </term> of <term> | argument frames | </term> , incorporating novel <term> features | #10097 We show how to build a joint model ofargument frames, incorporating novel features that model these interactions into discriminative log-linear models. | |
| 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 novelfeatures that model these interactions into discriminative log-linear models. | |
| model,20-3-P05-1073,ak | that model these interactions into <term> | discriminative log-linear models | </term> . This system achieves an <term> error | #10108 We show how to build a joint model of argument frames, incorporating novel features that model these interactions intodiscriminative log-linear models. | |
| measure(ment),4-4-P05-1073,ak | models </term> . This system achieves an <term> | error reduction | </term> of 22 % on all <term> arguments </term> | #10116 This system achieves anerror 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. | |
| 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 allarguments and 32% on core arguments over a state-of-the art independent classifier for gold-standard parse trees on PropBank. | |
| other,16-4-P05-1073,ak | all <term> arguments </term> and 32 % on <term> | core arguments | </term> over a state-of-the art independent | #10128 This system achieves an error reduction of 22% on all arguments and 32% oncore arguments over a state-of-the art independent classifier for gold-standard parse trees on PropBank. | |
| tech,23-4-P05-1073,ak | over a state-of-the art independent <term> | classifier | </term> for <term> gold-standard parse trees | #10135 This system achieves an error reduction of 22% on all arguments and 32% on core arguments over a state-of-the art independentclassifier for gold-standard parse trees on PropBank. | |
| other,25-4-P05-1073,ak | independent <term> classifier </term> for <term> | gold-standard parse trees | </term> on <term> PropBank </term> . Previous | #10137 This system achieves an error reduction of 22% on all arguments and 32% on core arguments over a state-of-the art independent classifier forgold-standard parse trees on PropBank. | |
| lr-prod,29-4-P05-1073,ak | gold-standard parse trees </term> on <term> | PropBank | </term> . Previous work has used <term> monolingual | #10141 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 onPropBank. |
