Joint Learning Improves Semantic Role Labeling
[作者] Kristina Toutanova Aria Haghighi Christopher D. Manning
[单位] Stanford University
[摘要] 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. This stands in…
[关键词] Joint Learning Semantic Role Labeling
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. This stands in stark contrast to the linguistic observation that a core argument frame is a joint structure, with strong dependencies between arguments. We show how to build a joint model of argument frames, incorporating novel features that model these interactions into discriminative loglinear models. This system achieves an error reduction of 22% on all arguments and 32% on core arguments over a stateof-the art independent classifier for goldstandard parse trees on PropBank.
存档附件原文地址
原文发布时间:2015/6/12
引用本文:
Kristina Toutanova;Aria Haghighi;Christopher D. Manning.Joint Learning Improves Semantic Role Labeling.http://hftc.firstlight.cn/View.aspx?infoid=3509873&cb=Z07870000000.
发布时间:2015/6/12.检索时间:2024/12/15