Similar presentations:
Natural Language Processing
1. Natural Language Processing
12. Related Efforts
cTAKES,MetaMap,
QuickUMLS
BioBert
ClinicalBert
2
3. 1. Spacy
34. spaCy
45.
https://spacy.io/5
6.
67.
78. Features
89.
910.
1011.
1112. Start with SpaCy
1213. Tokenization
1314.
1415. Tokenization
1516. Get tokens without punctations or white space
https://spacy.io/api/16
17. Load headache notes
1718. Read headache notes
1819. Print all the headache notes
1920. Get tokens without punctations or white space – for all the notes
50 year old female presents after having fallen in the bathtub 4 days ago andhitting the back of her head. Since then she has had a massive headache" which
did not resolve with Tylenol. She states that she has a high threshold for pain
and did not realize how bad it was during the day while at work but then when
she got home at night she noticed it. The patient noticed ""silvery spects"" in her
vision and she had trouble with some simple tasks like finding the tags on the
back of her clothing in the morning. She reported that she had to check several
times to make sure she did not put her clothes on backwards. She has had some
dizziness, but no nausea or vomiting. Her speech has not been affected.
20
21. Lemmatization
2122. Lemmatization
2223. POS Tagging
2324. POS Tagging
2425.
https://universaldependencies.org/u/pos/all.html25
26. POS Tagging
2627. Named Entities
2728. Named Entities
2829. Entity recognition
2930. Entity Visualizer
3031. Sentence identifier
3132. Visualizing dependencies
3233.
3334.
3435.
3536.
3637. Scispacy
https://towardsdatascience.com/using-scispacy-for-named-entityrecognition-785389e7918dSCISPACY
37
38. SciSpacy
Spacy is not good at extracting entities inbiomedical domain.
SciSpacy is specialized for biomedical text
processing
https://allenai.github.io/scispacy/
38
39. Installing SciSpacy
3940. Pick up a pretrained model
After installing scispaCy, you next need to installone of their pre-trained models.
scispaCy models come in two flavors: Core and
NER.
The Core models come in three sizes (small, medium,
large) based on the amount of vocabulary stored, and
they identify entities but do not classify them.
The NER models, on the other hand, identify and
classify entities. There are 4 different NER models
built on different entity categories.
40
41. Pre-trained Model
2/24/202441
42. Pre-trained NER model
4243. Spacy vs. scispacy
What Spacy can do43
44. Spacy vs. scispacy
What SciSpacy can do44
45. Scispacy
4546. Different NERs
4647. Different NERs
4748. Different NERs
4849.
Thank you!49