Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
-
|
| 2 |
---
|
| 3 |
language: ru
|
| 4 |
-
license: apache-2.0
|
| 5 |
library_name: transformers
|
| 6 |
tags:
|
| 7 |
- russian
|
|
@@ -9,8 +8,10 @@ tags:
|
|
| 9 |
- token-classification
|
| 10 |
- morphbert
|
| 11 |
- lightweight
|
|
|
|
|
|
|
|
|
|
| 12 |
pipeline_tag: token-classification
|
| 13 |
-
|
| 14 |
---
|
| 15 |
|
| 16 |
# MorphBERT-Tiny: Russian Morpheme Segmentation
|
|
@@ -89,4 +90,4 @@ The model achieves an approximate character-level accuracy of **0.975** on its e
|
|
| 89 |
|
| 90 |
* Performance may vary on out-of-vocabulary words, neologisms, or highly complex morphological structures not sufficiently represented in the training data.
|
| 91 |
* The model operates strictly at the character level; it does not incorporate broader lexical or syntactic context.
|
| 92 |
-
* Ambiguous cases in morpheme boundaries might be resolved based on patterns learned during training, which may not always align with linguistic conventions in edge cases.
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
language: ru
|
| 3 |
+
license: apache-2.0
|
| 4 |
library_name: transformers
|
| 5 |
tags:
|
| 6 |
- russian
|
|
|
|
| 8 |
- token-classification
|
| 9 |
- morphbert
|
| 10 |
- lightweight
|
| 11 |
+
- bert
|
| 12 |
+
- ru
|
| 13 |
+
- russ
|
| 14 |
pipeline_tag: token-classification
|
|
|
|
| 15 |
---
|
| 16 |
|
| 17 |
# MorphBERT-Tiny: Russian Morpheme Segmentation
|
|
|
|
| 90 |
|
| 91 |
* Performance may vary on out-of-vocabulary words, neologisms, or highly complex morphological structures not sufficiently represented in the training data.
|
| 92 |
* The model operates strictly at the character level; it does not incorporate broader lexical or syntactic context.
|
| 93 |
+
* Ambiguous cases in morpheme boundaries might be resolved based on patterns learned during training, which may not always align with linguistic conventions in edge cases.
|