tim1900 commited on
Commit
31c3a7b
·
verified ·
1 Parent(s): 7212aa2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -7,6 +7,8 @@ pipeline_tag: token-classification
7
  ---
8
  # bert-chunker-3
9
 
 
 
10
  bert-chunker-3 is a text chunker based on BertForTokenClassification 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**.
11
 
12
  Different from [bc-2](https://huggingface.co/tim1900/bert-chunker-2) and [bc](https://huggingface.co/tim1900/bert-chunker), to overcome the data distribution shift, our training data were labeled by a LLM and trainng pipeline was improved, therefore it is **more stable**.
 
7
  ---
8
  # bert-chunker-3
9
 
10
+ [GitHub](https://github.com/jackfsuia/bert-chunker/tree/main/bc3)
11
+
12
  bert-chunker-3 is a text chunker based on BertForTokenClassification 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**.
13
 
14
  Different from [bc-2](https://huggingface.co/tim1900/bert-chunker-2) and [bc](https://huggingface.co/tim1900/bert-chunker), to overcome the data distribution shift, our training data were labeled by a LLM and trainng pipeline was improved, therefore it is **more stable**.