BriefGPT.xyz
Oct, 2017
重新审视本地模型在日语谓词-论元结构分析中的设计问题
Revisiting the Design Issues of Local Models for Japanese Predicate-Argument Structure Analysis
HTML
PDF
Yuichiroh Matsubayashi, Kentaro Inui
TL;DR
本研究证明，采用最新的特征嵌入方法和基于神经网络的特征组合学习，可以显著提高复杂本地模型的性能，超越现有领先的全局模型在普遍标准数据集上的$F_1$性能表现。
Abstract
The research trend in
japanese
predicate-argument structure
(PAS) analysis is shifting from pointwise prediction models with local features to global models designed to search for globally optimal solutions. Howe
→