深度分享：世界顶级计算语言学科学家Ken Church CCL 2018主旨报告（附PPT全文）

数据派THU

发布于 2018-12-27 15:37:58

5010

发布于 2018-12-27 15:37:58

文章被收录于专栏：数据派THU数据派THU

来源：TsinghuaNLP

本文多图，建议阅读10分钟。

本文为你分享世界顶级计算语言学科学家在CCL2018的报告内容。

报告人：Kenneth Ward Church (Baidu Research Fellow)

题目：Minsky, Chomsky & Deep Nets

摘要：When Minsky and Chomsky were at Harvard in the 1950s, they started out their careers questioning a number of machine learning methods that have since regained popularity. Their objections are remembered as too negative: ngrams can't do this and nets can't do that. But more constructively, their arguments led to what is now known as the Chomsky Hierarchy and time and space complexity. The deep nets literature needs a high-level organization like the Chomsky Hierarchy. There are so many results being published these days that it is hard to see the big picture.My colleagues at Baidu have proposed a metric for ranking deep net problems by a metric of difficulty. There is no data like more data, but more data helps more for some problems than others. Their ranking suggests that more data is particularly helpful for problems that people are really excited about in speech and vision, and less so for problems in computational linguistics.

PPT下载: 请点击“阅读原文”或复制以下网址在浏览器中下载。