AutoX_NLP/ nlp_feature.py, OOV问题优化
未关闭
AutoX_NLP
call-for-contributions
- 主要语言
- Jupyter Notebook
- 星标
- 551
- 派生
- 143
- PR 合并指标
- 30 天内没有已合并 PR
描述
当前Word2Vec和Glove模型无法处理测试数据中未见过的词，需要对测试数据重新进行词表构建，对整体效果影响较大。
代码链接：[https://github.com/4paradigm/AutoX/blob/master/autox/autox_nlp/feature_engineer/nlp_feature.py](url)
贡献指南
这个仓库没有索引到贡献指南
调研方向
The issue points to nlp_feature.py in autox/autox_nlp/feature_engineer/. Examine how Word2Vec and GloVe models are built and applied, focusing on vocabulary handling for OOV (out-of-vocabulary) words. Look at the test data pipeline to see where the vocabulary is constructed. The goal is to modify the feature engineering to better handle unseen words, likely by adjusting the vocabulary building or embedding fallback strategy.
由索引模型根据 Issue 内容生成。
评估
- 技术栈
- machine-learning, python
- 领域
- machine-learning
- Issue 类型
- 缺陷
- 难度
- 4/5
- 预计耗时
- 3-5 天
- 活跃度
- 停滞
- 描述清晰度
- 基本清楚
- 新手友好度
- 30/100