From 51be66807bc514b22cddff95eb3adf9201030b91 Mon Sep 17 00:00:00 2001
From: Mateusz Klimaszewski <mk.klimaszewski@gmail.com>
Date: Fri, 11 Dec 2020 13:50:50 +0100
Subject: [PATCH] Add documentation EUD model training.
---
docs/training.md | 22 +++++++++++++++++++++-
1 file changed, 21 insertions(+), 1 deletion(-)
diff --git a/docs/training.md b/docs/training.md
index 9dc430a..f4b6d38 100644
--- a/docs/training.md
+++ b/docs/training.md
@@ -43,7 +43,27 @@ Examples (for clarity without training/validation data paths):
```bash
combo --mode train --targets head,deprel --features token,char,upostag
```
-
+
+## Enhanced UD
+
+Training a model with Enhanced UD prediction **requires** data pre-processing.
+
+```bash
+combo --mode train \
+ --training_data_path your_preprocessed_training_path \
+ --validation_data_path your_preprocessed_validation_path \
+ --targets feats,upostag,xpostag,head,deprel,lemma,deps \
+ --config_path config.graph.template.jsonnet
+```
+### Data pre-processing
+Download data from [IWPT20 Shared Task](https://universaldependencies.org/iwpt20/data.html).
+It contains `enhanced_collapse_empty_nodes.pl` script which is required as pre-processing step.
+Apply this script to training and validation data.
+
+```bash
+perl enhanced_collapse_empty_nodes.pl training.conllu > training.fixed.conllu
+```
+
## Configuration
### Advanced
--
GitLab