BriefGPT.xyz
Nov, 2017
基于视觉语境的多模态词表示学习
Learning Multi-Modal Word Representation Grounded in Visual Context
HTML
PDF
Éloi Zablocki, Benjamin Piwowarski, Laure Soulier, Patrick Gallinari
TL;DR
本研究提出了一种同时利用文本和视觉上下文以学习多模态词嵌入的端到端方法，通过将视觉上下文元素整合到多模态skip-gram模型中，探索了何种因素可以作为视觉上下文，并进行了实验和分析。
Abstract
Representing the semantics of words is a long-standing problem for the
natural language processing
community. Most methods compute
word semantics
given their textual context in large corpora. More recently, resea
→