Update README.md
Browse files
README.md
CHANGED
|
@@ -6,8 +6,6 @@ pipeline_tag: token-classification
|
|
| 6 |
---
|
| 7 |
# bert-chunker-chinese
|
| 8 |
|
| 9 |
-
## Introduction
|
| 10 |
-
|
| 11 |
bert-chunker-chinese (中文分段器) is a Chinese version of [bert-chunker](https://huggingface.co/tim1900/bert-chunker). It's a Chinese text chunker based on BERT with a classifier head to predict the start token of chunks (for use in RAG, etc), and using a sliding window it cuts documents of any size into chunks. We see it as an alternative of [semantic chunker](https://github.com/FullStackRetrieval-com/RetrievalTutorials/blob/main/tutorials/LevelsOfTextSplitting/5_Levels_Of_Text_Splitting.ipynb). but specially, it not only works for the structured texts, but also the **unstructured and messy texts**.
|
| 12 |
|
| 13 |
It was finetuned on top of [bge-small-zh-v1.5](https://huggingface.co/BAAI/bge-small-zh-v1.5), dataset is synthesized from [chinese-c4](https://huggingface.co/datasets/shjwudp/chinese-c4).
|
|
|
|
| 6 |
---
|
| 7 |
# bert-chunker-chinese
|
| 8 |
|
|
|
|
|
|
|
| 9 |
bert-chunker-chinese (中文分段器) is a Chinese version of [bert-chunker](https://huggingface.co/tim1900/bert-chunker). It's a Chinese text chunker based on BERT with a classifier head to predict the start token of chunks (for use in RAG, etc), and using a sliding window it cuts documents of any size into chunks. We see it as an alternative of [semantic chunker](https://github.com/FullStackRetrieval-com/RetrievalTutorials/blob/main/tutorials/LevelsOfTextSplitting/5_Levels_Of_Text_Splitting.ipynb). but specially, it not only works for the structured texts, but also the **unstructured and messy texts**.
|
| 10 |
|
| 11 |
It was finetuned on top of [bge-small-zh-v1.5](https://huggingface.co/BAAI/bge-small-zh-v1.5), dataset is synthesized from [chinese-c4](https://huggingface.co/datasets/shjwudp/chinese-c4).
|