Commit
•
eec1a9a
1
Parent(s):
de245bc
Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,17 @@
|
|
1 |
---
|
2 |
license: cc-by-4.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
4 |
# A Named Entity Recognition Model for Kazakh
|
5 |
- The model was inspired by the [LREC 2022](https://lrec2022.lrec-conf.org/en/) paper [*KazNERD: Kazakh Named Entity Recognition Dataset*](https://aclanthology.org/2022.lrec-1.44).
|
@@ -15,4 +27,4 @@ KazNERD (Cleaned) | Sentence | 88,540 (80.00%) | 11,067 (10.00%) | 11,068 (10.00
|
|
15 |
KazNERD (Original)| Token | 1,043,305 (80.11%) | 129,223 (9.92%)| 129,824 (9.97%) | 1,302,352 (100%) |
|
16 |
KazNERD (Cleaned) | Token | 1,088,461 (80.04%) | 136,021 (10.00%) | 135,426 (9.96%) | 1,359,908 (100%) |
|
17 |
KazNERD (Original)| NE | 109,342 (80.20%) | 13,483 (9.89%)| 13,508 (9.91%) | 136,333 (100%) |
|
18 |
-
KazNERD (Cleaned) | NE | 106,148 (80.17%) | 13,189 (9.96%) | 13,072 (9.87%) | 132,409 (100%) |
|
|
|
1 |
---
|
2 |
license: cc-by-4.0
|
3 |
+
language:
|
4 |
+
- kk
|
5 |
+
metrics:
|
6 |
+
- f1
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
pipeline_tag: token-classification
|
10 |
+
tags:
|
11 |
+
- Kazakh
|
12 |
+
- NER
|
13 |
+
- Named Entity Recognition
|
14 |
+
- XLM-RoBERTa
|
15 |
---
|
16 |
# A Named Entity Recognition Model for Kazakh
|
17 |
- The model was inspired by the [LREC 2022](https://lrec2022.lrec-conf.org/en/) paper [*KazNERD: Kazakh Named Entity Recognition Dataset*](https://aclanthology.org/2022.lrec-1.44).
|
|
|
27 |
KazNERD (Original)| Token | 1,043,305 (80.11%) | 129,223 (9.92%)| 129,824 (9.97%) | 1,302,352 (100%) |
|
28 |
KazNERD (Cleaned) | Token | 1,088,461 (80.04%) | 136,021 (10.00%) | 135,426 (9.96%) | 1,359,908 (100%) |
|
29 |
KazNERD (Original)| NE | 109,342 (80.20%) | 13,483 (9.89%)| 13,508 (9.91%) | 136,333 (100%) |
|
30 |
+
KazNERD (Cleaned) | NE | 106,148 (80.17%) | 13,189 (9.96%) | 13,072 (9.87%) | 132,409 (100%) |
|