apjanco
commited on
Commit
•
5e74ada
1
Parent(s):
9f20055
working on plan
Browse files
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
title: Bolete
|
| 3 |
-
emoji:
|
| 4 |
colorFrom: green
|
| 5 |
colorTo: red
|
| 6 |
sdk: streamlit
|
|
@@ -14,4 +14,11 @@ license: mit
|
|
| 14 |
An information extraction and exploration app. Upload files with text. Bolete will then extract text, identify common keywords and entities, and create a simple search interface to explore the corpus.
|
| 15 |
|
| 16 |
- Search of collection texts
|
|
|
|
|
|
|
| 17 |
- Entities and frequencies
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
title: Bolete
|
| 3 |
+
emoji: 🍄
|
| 4 |
colorFrom: green
|
| 5 |
colorTo: red
|
| 6 |
sdk: streamlit
|
|
|
|
| 14 |
An information extraction and exploration app. Upload files with text. Bolete will then extract text, identify common keywords and entities, and create a simple search interface to explore the corpus.
|
| 15 |
|
| 16 |
- Search of collection texts
|
| 17 |
+
- how best to search collection?
|
| 18 |
+
- Holmes?
|
| 19 |
- Entities and frequencies
|
| 20 |
+
- TODO run ner, return filters for most frequent ents in corpus
|
| 21 |
+
|
| 22 |
+
- Fun
|
| 23 |
+
- use with scispaCy rather than generic model
|
| 24 |
+
en_core_sci_lg + en_core_sci_scibert
|