前往小程序,Get更优阅读体验!
立即前往
首页
学习
活动
专区
工具
TVP
发布
社区首页 >专栏 >语言的信息瓶颈分析

语言的信息瓶颈分析

作者头像
CreateAMind
发布2018-12-26 17:20:18
5400
发布2018-12-26 17:20:18
举报
文章被收录于专栏:CreateAMind

Efficient human-like semantic representations via the Information Bottleneck principle

Noga Zaslavsky∗ Charles Kemp Terry Regier Naftali TishbyHebrew University Carnegie Mellon University UC Berkeley Hebrew University

UC Berkeley

Abstract

Maintaining efficient semantic representations of the environment is a major chal- lenge both for humans and for machines. While human languages represent useful solutions to this problem, it is not yet clear what computational principle could give rise to similar solutions in machines. In this work we propose an answer to this open question. We suggest that languages compress percepts into words by optimizing the Information Bottleneck (IB) tradeoff between the complexity and accuracy of their lexicons. We present empirical evidence that this principle may give rise to human-like semantic representations, by exploring how human languages categorize colors. We show that color naming systems across languages are near-optimal in the IB sense, and that these natural systems are similar to artificial IB color naming systems with a single tradeoff parameter controlling the cross-language variability. In addition, the IB systems evolve through a sequence of structural phase transitions, demonstrating a possible adaptation process. This work thus identifies a computational principle that characterizes human semantic systems, and that could usefully inform semantic representations in machines.

本文参与 腾讯云自媒体同步曝光计划,分享自微信公众号。
原始发表:2018-12-10,如有侵权请联系 cloudcommunity@tencent.com 删除

本文分享自 CreateAMind 微信公众号,前往查看

如有侵权,请联系 cloudcommunity@tencent.com 删除。

本文参与 腾讯云自媒体同步曝光计划  ,欢迎热爱写作的你一起参与!

评论
登录后参与评论
0 条评论
热度
最新
推荐阅读
领券
问题归档专栏文章快讯文章归档关键词归档开发者手册归档开发者手册 Section 归档