Home > tech, thoughts > IBM Watson VS human, tomorrow!

IBM Watson VS human, tomorrow!


估计watson对各类百科全书先作了个indexing , 当然是很smart的inverted index, 就是把
答案和问题反着作index,  然后作inference。

每个类别的问题可以允许watson prune掉大部分的knowledgebase, 然后作inference.

我感觉这个算法应该更类似于 information retrieval, 再加一点点first order logic, 或
者某种 bayesian 的变种。

大家讨论讨论,明天就比赛拉!而且我估计watson会再接再厉拿第一,人脑对这种死板问题的的检
索速度不可能比得上计算机。

Advertisements
Categories: tech, thoughts
  1. No comments yet.
  1. No trackbacks yet.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: