wbi-sg commited on
Commit
512ba11
1 Parent(s): f646d74

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -50,7 +50,8 @@ As an alternative to downloading the already precomputed model (much storage). Y
50
  and compute the embeddings for the dataset using:
51
 
52
  ```python
53
- linker = EntityMentionLinker.build("cambridgeltl/SapBERT-from-PubMedBERT-fulltext", dictionary_name_or_path="ncbi-taxonomy", entity_type="species", hybrid_search=False)
 
54
  ```
55
 
56
  This will reduce the download requirements, at the cost of computation. Note `hybrid_search=False` as SapBERT unlike BioSyn is trained only for dense retrieval.
 
50
  and compute the embeddings for the dataset using:
51
 
52
  ```python
53
+ from flair.models.entity_mention_linking import BioSynEntityPreprocessor
54
+ linker = EntityMentionLinker.build("cambridgeltl/SapBERT-from-PubMedBERT-fulltext", dictionary_name_or_path="ncbi-taxonomy", entity_type="species", preprocessor=BioSynEntityPreprocessor(), hybrid_search=False)
55
  ```
56
 
57
  This will reduce the download requirements, at the cost of computation. Note `hybrid_search=False` as SapBERT unlike BioSyn is trained only for dense retrieval.