BriefGPT.xyz
Jun, 2020
自动域适应优于手动域适应在预测财务业绩方面
Automatic Domain Adaptation Outperforms Manual Domain Adaptation for Predicting Financial Outcomes
HTML
PDF
Marina Sedinkina, Nikolas Breitkopf, Hinrich Schütze
TL;DR
本文研究使用情感词典预测金融收益，比较三种方法，并通过实验发现自动适应情感词典的预测能力优于人工适应，且基于上下文的标注方法比基于先验知识的方法更为准确。
Abstract
In this paper, we automatically create
sentiment dictionaries
for predicting
financial outcomes
. We compare three approaches: (I) manual adaptation of the domain-general dictionary H4N, (ii)
→