BriefGPT.xyz
Apr, 2018
用于提高句子表示的动态元嵌入
Context-Attentive Embeddings for Improved Sentence Representations
HTML
PDF
Douwe Kiela, Changhan Wang, Kyunghyun Cho
TL;DR
介绍了一种通过神经网络自行学习嵌入向量的方法——动态元嵌入,该方法在同一模型类别下,在各种任务中实现了最先进的性能,并展示了该技术如何在NLP系统中应用嵌入向量。
Abstract
While one of the first steps in many
nlp systems
is selecting what embeddings to use, we argue that such a step is better left for
neural networks
to figure out by themselves. To that end, we introduce a novel, s
→