BrambleXu / knowledge-graph-learning

A curated list of awesome knowledge graph tutorials, projects and communities.
MIT License
735 stars 120 forks source link

EMNLP-2009-Generating High-Coverage Semantic Orientation Lexicons From Overtly Marked Words and a Thesaurus #300

Open BrambleXu opened 4 years ago

BrambleXu commented 4 years ago

Summary:

基于lexicon的方法计算太耗时了,所以提出一个简单的方案能生成 high-coverage semantic orientation lexicon

Resource:

Paper information:

Notes:

4 Evaluation

We evaluated the semantic orientation lexicons both intrinsically (by comparing their entries to the General Inquirer) and extrinsically (by using them in a phrase polarity annotation task).

这里提到的是从内部和外部两种方式来检测lexicon。intrinsically的方式其实就是直接计算覆盖率的方法,而extrinsically的方式其实就是用NER的方式来进行计算。(只不过用于我的研究的话,recall的部分有重复。前者用一个百分比来对比,后者用一个task来对比)

image

image

Model Graph:

Result:

Thoughts:

Next Reading: