From 7568cd6bf8a156a37e3c254ea65f5a479102c424 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Rapha=C3=ABl=20Bournhonesque?= <raphael@bournhonesque.eu>
Date: Tue, 21 Mar 2017 23:00:13 +0100
Subject: [PATCH 1/2] Split CONLLX file using tabs and not default split
 separators

---
 bin/parser/train_ud.py | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/bin/parser/train_ud.py b/bin/parser/train_ud.py
index c87f40680..98a93dd88 100644
--- a/bin/parser/train_ud.py
+++ b/bin/parser/train_ud.py
@@ -1,18 +1,13 @@
 from __future__ import unicode_literals
 import plac
 import json
-from os import path
-import shutil
-import os
 import random
-import io
 import pathlib
 
 from spacy.tokens import Doc
 from spacy.syntax.nonproj import PseudoProjectivity
 from spacy.language import Language
 from spacy.gold import GoldParse
-from spacy.vocab import Vocab
 from spacy.tagger import Tagger
 from spacy.pipeline import DependencyParser, BeamDependencyParser
 from spacy.syntax.parser import get_templates
@@ -23,7 +18,6 @@ import spacy.attrs
 import io
 
 
-
 def read_conllx(loc, n=0):
     with io.open(loc, 'r', encoding='utf8') as file_:
         text = file_.read()
@@ -35,7 +29,8 @@ def read_conllx(loc, n=0):
                 lines.pop(0)
             tokens = []
             for line in lines:
-                id_, word, lemma, pos, tag, morph, head, dep, _1, _2 = line.split()
+                id_, word, lemma, pos, tag, morph, head, dep, _1, \
+                _2 = line.split('\t')
                 if '-' in id_ or '.' in id_:
                     continue
                 try:

From 08346dba1a94989c6a286e51a122a0f2661592d3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Rapha=C3=ABl=20Bournhonesque?= <raphael@bournhonesque.eu>
Date: Tue, 21 Mar 2017 23:18:54 +0100
Subject: [PATCH 2/2] Use specific language class instead of base Language
 class

---
 bin/parser/train_ud.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/bin/parser/train_ud.py b/bin/parser/train_ud.py
index 98a93dd88..afc4491cb 100644
--- a/bin/parser/train_ud.py
+++ b/bin/parser/train_ud.py
@@ -129,7 +129,7 @@ def main(lang_name, train_loc, dev_loc, model_dir, clusters_loc=None):
         random.shuffle(train_sents)
         scorer = score_model(vocab, tagger, parser, read_conllx(dev_loc))
         print('%d:\t%.3f\t%.3f\t%.3f' % (itn, loss, scorer.uas, scorer.tags_acc))
-    nlp = Language(vocab=vocab, tagger=tagger, parser=parser)
+    nlp = LangClass(vocab=vocab, tagger=tagger, parser=parser)
     nlp.end_training(model_dir)
     scorer = score_model(vocab, tagger, parser, read_conllx(dev_loc))
     print('%d:\t%.3f\t%.3f\t%.3f' % (itn, scorer.uas, scorer.las, scorer.tags_acc))