用于提高句子表示的动态元嵌入

Apr, 2018

Context-Attentive Embeddings for Improved Sentence Representations

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