Author: University of Illinois at Urbana-Champaign、Google Research
Dataset:
keywords:
Notes:
两大技术:
Robust Positive-Only Distant Training。从general kb里收集高质量的phrase。We independently build samples of positive labels from general knowledge bases and negative labels from the given domain corpora, and train a number of base classifiers. We then aggregate the predictions from these classifiers, whose independence helps reduce the noise from negative labels.
这篇论文假设需要两个数据: a general knowledge base together with a pre-trained POS tagger.
Model Graph:
we propose a robust positive-only distant training to minimize the human effort and develop a POS-guided phrasal segmentation model to improve the model performance.
A phrase is defined as a sequence of words that appear consecutively in the text, forming a complete semantic unit in certain contexts of the given documents [8]. The phrase quality is defined to be the probability of a word sequence being a complete semantic unit, meeting the following criteria:
Popularity: 出现次数够多
Concordance: 一致性
Informativeness: 能说明一个具体的topic或concept
Completeness: subsequence也算。 For example, “relational database system”, “relational database” and “database system” can all be valid in certain context. (这一点适用于去掉合法form的公司名)
Summary:
通过从公开的KB里获取大量quality phrasees,来自动化phrase mining。AutoPhrase可以支持任意的语言。用户需要提供两种数据: a general knowledge base together with a pre-trained POS tagger.
Resource:
Paper information:
Notes:
两大技术:
这篇论文假设需要两个数据: a general knowledge base together with a pre-trained POS tagger.
Model Graph:
we propose a robust positive-only distant training to minimize the human effort and develop a POS-guided phrasal segmentation model to improve the model performance.
A phrase is defined as a sequence of words that appear consecutively in the text, forming a complete semantic unit in certain contexts of the given documents [8]. The phrase quality is defined to be the probability of a word sequence being a complete semantic unit, meeting the following criteria:
满足上面所有条件的才会被认为是quality phrases.
Result::
Thoughts:
构建一个日本business kb from wiki。
Next Reading: