Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,24 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
library_name: allennlp
|
| 5 |
+
pipeline_tag: token-classification
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
# Distilbert CoBaLD parser
|
| 9 |
+
|
| 10 |
+
This version of parser is based on XLM-R Base encoder. The encoder weights were initialized from `xlm-roberta-base` model.
|
| 11 |
+
|
| 12 |
+
## Usage
|
| 13 |
+
|
| 14 |
+
1. Clone https://github.com/CobaldAnnotation/CobaldParser, go to the repo directory and install requirements.
|
| 15 |
+
2. Download the `model.tag.gz` file. You can do it manually of via `git clone https://huggingface.co/CoBaLD/xlm-roberta-base-cobald-parser`.
|
| 16 |
+
3. Run `allennlp predict` with the following arguments on the conllu file you want to annotate with CoBaLD:
|
| 17 |
+
```
|
| 18 |
+
allennlp predict <PATH_TO_model.tar.gz> <INPUT_CONLLU_FILE> \
|
| 19 |
+
--output-file <OUTPUT_CONLLU_FILE> \
|
| 20 |
+
--include-package src \
|
| 21 |
+
--predictor morpho_syntax_semantic_predictor \
|
| 22 |
+
--use-dataset-reader
|
| 23 |
+
```
|
| 24 |
+
4. Now see the results in output conllu file you specified.
|