baidu / baidu/lac

单个姓氏标记为PER

Open
#161 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
C++
Stars
4k
Forks
592
PR merge metrics
No merged PRs in 30d

Description

我在实体提取的过程中发现,分词标记会将单个的姓氏标记为PER
原始句子:
“自徐姓祖先于南宋淳熙年间迁来定居,后高姓、张姓始祖相继迁入”

分词标记结果:
'自': 'p', '徐': 'PER', '姓': 'n', '祖先': 'n', '于南宋淳熙': 'PER', '年间': 'n', '迁': 'v', '来': 'v', '定居': 'v', '后': 'f', '高姓': 'n', '、': 'w', '张': 'PER', '始祖': 'n', '相继': 'd', '迁入': 'v'

这里“张”,“徐”都标记为PER。这种感觉不恰当,如果是在词典中直接加“张”、“徐”这些姓氏词语,就会导致人名“张学良”,被拆分为“张”、“学良”,所以也会存在问题。
所以请问一下这种目前有没有较好的解决方式?

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reproducing the reported sentence and comparing the entity-extraction output for “徐” and “张” with the full name “张学良”. The issue does not name files or tests; done would require an agreed approach that avoids misclassifying standalone surnames without breaking full-name recognition.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.