增量训练是否会使得原分词/标注效果变差
Open
- Dominant language
- C++
- Stars
- 4k
- Forks
- 592
- PR merge metrics
- No merged PRs in 30d
Description
例如使用1个垂域的少量数据，大概几万条样本，进行增量训练。
是否会出现原分词/标注效果变差、而仅retrain的垂域效果好的问题？
Contributor guide
No contributing guide indexed for this repository
Research direction
No file, test, or entry point is named. Start by locating the incremental-training workflow and compare the original model's segmentation and tagging results with the domain-specific results. Done means producing a documented, reproducible answer about whether the original capabilities degrade.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100