BriefGPT.xyz
Oct, 2020
关于知识增强数据对词向量嵌入的影响
On the Effects of Knowledge-Augmented Data in Word Embeddings
HTML
PDF
Diego Ramirez-Echavarria, Antonis Bikakis, Luke Dickens, Rob Miller, Andreas Vlachidis
TL;DR
本文研究了一种通过数据增强注入语言知识以改善单词嵌入的方法，并对其对词嵌入的内在特征和下游文本分类任务的影响进行了系统评估。
Abstract
This paper investigates techniques for
knowledge injection
into
word embeddings
learned from large corpora of unannotated data. These representations are trained with word cooccurrence statistics and do not commo
→