Open BrambleXu opened 3 years ago
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:
Paper information:
Notes:
原理是考虑前缀和后缀。但是这种方法有很大的问题:
Contextual Information
A Unified Structure for both Internal and Contextual Information
Model Graph:
Result::
Thoughts:
Next Reading:
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:
Paper information:
Notes:
原理是考虑前缀和后缀。但是这种方法有很大的问题:
Contextual Information
A Unified Structure for both Internal and Contextual Information
Model Graph:
Result::
Thoughts:
Next Reading: