baidu / baidu/lac

“非货币性交易法则“ lac 模式比1.0版本退化

Open
#124 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
C++
Stars
4k
Forks
592
PR merge metrics
No merged PRs in 30d

Description

输入 “非货币性交易法则”,1.0的时候分词和词性貌似都正确,
{
"ret": 0,
"msg": "",
"content": {
"status": 0,
"version": "ver_1_0_0",
"results": [
{
"retcode": 0,
"text": "非货币性交易法则",
"items": [
{
"byte_length": 12,
"byte_offset": 0,
"item": "非货币性交易",
"type": "nz"
},
{
"byte_length": 4,
"byte_offset": 12,
"item": "法则",
"type": "n"
}
]
}
]
}
}

2.0 lac 模式不符合预期(['非货币', '性交易', '法则'], ['n', 'n', 'n']),seg模式正确(['非货币性交易', '法则'])。

Contributor guide

No contributing guide indexed for this repository

Research direction

Reproduce the reported input “非货币性交易法则” in lac 2.0 using both lac and seg modes, and compare the token and part-of-speech outputs with the 1.0 result shown in the issue. Start from the mode-specific segmentation and tagging entry points; done means lac mode matches the expected segmentation and tags while seg mode remains correct.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.