diff --git a/.gitattributes b/.gitattributes
index e802ffc530d7ff05bb1f95b886f681b2a637fd72..976aa3ea4f49fbe4d85357c19a4d69cfbfb4913f 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -1,232 +1,246 @@
 data/AB/*/*tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1891/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1892/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1893/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1891/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1891/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1891/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1892/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1893/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1894/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1895/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1896/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1897/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1898/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1899/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1900/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1901/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1902/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1903/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1904/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1905/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1906/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1907/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1908/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1909/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1910/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1911/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1912/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1913/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1914/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1915/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1916/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1917/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1918/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1919/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1920/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1921/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1922/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1923/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1924/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1925/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1892/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1892/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1893/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1893/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1893/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1894/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1894/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1895/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1895/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1896/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1896/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1897/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1897/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1898/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1898/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1899/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1899/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1900/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1900/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1901/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1901/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1902/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1902/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1903/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1903/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1904/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1904/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1905/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1905/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1906/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1906/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1907/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1907/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1908/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1908/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1909/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1909/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1910/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1910/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1911/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1911/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1912/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1912/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1913/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1913/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1914/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1914/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1915/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1915/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1916/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1916/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1917/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1917/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1918/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1918/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1919/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1919/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1920/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1920/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1921/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1921/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1922/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1922/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1923/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1923/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1924/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1924/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1925/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1925/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1926/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1927/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1928/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1929/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1930/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1931/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1932/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1933/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1934/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1935/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1936/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1937/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1938/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1939/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1940/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1941/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1942/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1943/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1944/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1945/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1946/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1947/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1948/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1949/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1950/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1926/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1927/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1928/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1929/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1930/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1931/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1932/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1933/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1934/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1891/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1935/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1936/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1937/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1938/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1939/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1940/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1951/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1952/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1953/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1954/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1955/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1956/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1957/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1958/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1959/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1960/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1961/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1962/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1963/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1964/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1965/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1966/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1967/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1968/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1969/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1970/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1971/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1972/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1973/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1974/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1941/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1942/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1943/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1944/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1945/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1946/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1947/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1948/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1949/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1950/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1951/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1952/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1953/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1954/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1955/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1956/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1957/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1958/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1959/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1960/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1961/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1962/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1963/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1964/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1965/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1966/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1967/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1968/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1969/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/train_NER/20190109_train_NER.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1970/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1971/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/train_NER/20190116_train_NER_french.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1972/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1926/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1926/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1927/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1927/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1927/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1928/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1928/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1928/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1929/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1929/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1929/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1930/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1930/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1930/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1931/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1931/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1931/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1932/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1932/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1932/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1933/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1933/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1933/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1934/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1934/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1934/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1935/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1935/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1935/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1936/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1936/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1936/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1937/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1937/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1937/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1938/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1938/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1938/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1939/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1939/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1939/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1940/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1940/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1940/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1941/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1941/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1941/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1942/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1942/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1942/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1943/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1943/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1943/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1944/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1944/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1944/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1945/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1945/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1945/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1946/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1946/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1946/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1947/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1947/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1947/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1948/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1948/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1948/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1949/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1949/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1949/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1950/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1950/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1950/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1951/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1951/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1951/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1952/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1952/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1952/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1953/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1953/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1953/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1954/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1954/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1954/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1955/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1955/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1955/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1956/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1956/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1956/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1957/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1957/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1957/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1958/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1958/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1958/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1959/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1959/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1959/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1960/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1960/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1960/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1961/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1961/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1961/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1962/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1962/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1962/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1963/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1963/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1963/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1964/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1964/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1964/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1965/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1965/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1965/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1966/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1966/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1966/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1967/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1967/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1967/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1968/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1968/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1968/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1969/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1969/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1969/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1970/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1970/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1970/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1971/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1971/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1971/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1972/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1972/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1972/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1973/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1973/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1973/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1974/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1974/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1974/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1975/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1975/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1975/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1976/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1976/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1976/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1977/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1977/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1977/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1978/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1978/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1978/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1979/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1979/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1979/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1980/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1980/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1981/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1981/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1982/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1982/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1983/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1983/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1984/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1985/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
@@ -235,29 +249,16 @@ data/AB/1987/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1988/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1989/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1990/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1991/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1991/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1991/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1992/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1993/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1994/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1995/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/lists/all_titles.csv filter=lfs diff=lfs merge=lfs -text
+data/lists/dict_overlaps.pickle filter=lfs diff=lfs merge=lfs -text
 data/politicians/MPs_after1890.csv filter=lfs diff=lfs merge=lfs -text
 data/politicians/lastnames/** filter=lfs diff=lfs merge=lfs -text
-data/AB/1973/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1975/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1976/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1974/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1980/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1981/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1977/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1982/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1983/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1991/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1991/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/lists/dict_overlaps.pickle filter=lfs diff=lfs merge=lfs -text
-data/lists/all_titles.csv filter=lfs diff=lfs merge=lfs -text
-data/AB/1978/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1979/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1976/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1977/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1975/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
-data/AB/1978/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/train_NER/20190109_train_NER.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/train_NER/20190116_train_NER_french.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/84bd2a055b9e45099e83b07da519ff7b_python.cwl b/.renku/workflow/84bd2a055b9e45099e83b07da519ff7b_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..198c7be5bb68a5c469b228486a2979552a91afa8
--- /dev/null
+++ b/.renku/workflow/84bd2a055b9e45099e83b07da519ff7b_python.cwl
@@ -0,0 +1,51 @@
+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_correctxml.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/AB/1979/02_extractedxml.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1979/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_3)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1979
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1979/04_correctedxml.tar.gz b/data/AB/1979/04_correctedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..b5cb4ba49e4358bc61b3662bf4074582ae3c4452
--- /dev/null
+++ b/data/AB/1979/04_correctedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c13eccfc20b68b835c0f32c9d42fb3cb6f9051b67c144bfb518eba30adc5eb37
+size 21883464