diff --git a/README.md b/README.md
index e1761b02e50b3166a1767952e72d171d031d1f6a..055ba51e14c7b44d51eb3cf6ff3a71066e72036d 100644
--- a/README.md
+++ b/README.md
@@ -30,16 +30,7 @@ Examples of an input anf outputs are provided in `./data/examples/`
 
 Ziped folders of "unlized" XML files of the corpus are available in the ./data folder.
 
-:bangbang: For some reason a namespace attribute of the root node make the script crash on the documents of the corpus.
-Please modify the following :
-```
-<req_document xsi:schemaLocation="req_document.xsd" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="req_document.xsd">
-```
-to
-```
-<req_document xsi:schemaLocation="req_document.xsd" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
-```
-before submiting an xml of the corpus to the script.
+:bangbang: `unlizeXml.py` ignores namespaces in the XML document.
 
 First clone the repo (or at least download the scripts folder):
 ```
diff --git a/scripts/unlizeXml.py b/scripts/unlizeXml.py
index c16ce6d0195dd11c7a491177a5f210a62c22711b..210b736a3fcc27ccfca4ae39307c7ceb2a8f6501 100755
--- a/scripts/unlizeXml.py
+++ b/scripts/unlizeXml.py
@@ -7,6 +7,10 @@ import tempfile
 import os
 from subprocess import Popen, PIPE, STDOUT
 
+def remove_namespace(doc):
+    #Remove namespace in the passed document in place
+    for elem in doc.getiterator():
+        elem.tag=etree.QName(elem.tag).localname
 
 def unlize(text, lang, dry_run=False):
 
@@ -122,6 +126,7 @@ def unl2dot(text, path):
 def unlizeXml(input, output, lang, dry_run, svg, unltools_path):
 
     doc = etree.parse(input)
+    remove_namespace(doc)
     tags = ['title', 'text_body', 'term', 'meaning']
     for t in tags:
         for node in doc.xpath('//'+t):