knowledge-graph-learning icon indicating copy to clipboard operation
knowledge-graph-learning copied to clipboard

COLING-2002-Language Independent NER using a Unified Model of Internal and Contextual Evidence

Open BrambleXu opened this issue 4 years ago • 0 comments

Summary:

基于 iterative learning in a co-training fashion 的跨语言NER模型,创新点在于使用word-internal和contextual information作为独立的信息来源。对象是西班牙语和荷兰语。

Resource:

  • pdf
  • [code](
  • [paper-with-code](

Paper information:

  • Author:
  • Dataset:
  • keywords:

Notes:

  1. Entity-Internal Information

原理是考虑前缀和后缀。但是这种方法有很大的问题:

  • 一些拉丁语系的前缀和后缀意思变化很大
  • 如果是汉字语系的,效果不知道会怎么样。文中没有给出
  1. Contextual Information
  • 考虑entity的左边和右边的context
  1. A Unified Structure for both Internal and Contextual Information
  • Character-based

Model Graph:

Result:

Thoughts:

Next Reading:

BrambleXu avatar Apr 06 '21 23:04 BrambleXu