From 534df2ab398285756f7d11b36015e97a0d58e06c Mon Sep 17 00:00:00 2001
From: Stephan Porada <sporada@techfak.uni-bielefeld.de>
Date: Tue, 26 Feb 2019 19:51:54 +0100
Subject: [PATCH] Update README.md

---
 README.md | 54 +++++++++++++++++++++++++++---------------------------
 1 file changed, 27 insertions(+), 27 deletions(-)

diff --git a/README.md b/README.md
index 0c455f1..18c28ed 100644
--- a/README.md
+++ b/README.md
@@ -16,11 +16,11 @@ Structure:
 │   ├── backup_raw_xml  # Zip files of all original protocols.
 │   ├── current_official_protocols_xml  # Example file of the new official markup.
 │   ├── development_data_xml  # Set of original xml protocols used for development.
-│   ├── faulty_raw_xml  # A original protocolls with errors. The Bundesregierung should have fixed those by now. The Software mentioned above used these faulty ones though because the new ones were not available back then.
+│   ├── faulty_raw_xml  # All original protocolls with errors. The Bundesregierung should have fixed those by now. The Software mentioned above used these faulty ones though because the new ones were not available back then.
 │   │   ├── 15_Wahlperiode_2002-2005
 │   │   ├── 16_Wahlperiode_2005-2009
 │   │   └── 17_Wahlperiode_2009-2013
-│   ├── protocols_raw_xml
+│   ├── protocols_raw_xml  # Unziped original protocols.
 │   │   ├── 01_Wahlperiode_1949-1953
 │   │   ├── 02_Wahlperiode_1953-1957
 │   │   ├── 03_Wahlperiode_1957-1961
@@ -36,17 +36,17 @@ Structure:
 │   │   ├── 13_Wahlperiode_1994-1998
 │   │   ├── 14_Wahlperiode_1998-2002
 │   │   └── 18_Wahlperiode_2013-2017
-│   └── test_data_xml
-├── MdB_data
-├── outputs
-│   ├── markup
-│   │   ├── dev_data
-│   │   │   ├── beautiful_xml
-│   │   │   ├── clear_speech_markup
-│   │   │   ├── complex_markup
-│   │   │   ├── new_metadata
-│   │   │   └── simple_xml
-│   │   ├── full_periods
+│   └── test_data_xml  # Set of original protocols fpr testin purposes.
+├── MdB_data  # The official Stammdaten of every MdB can be found here.
+├── outputs  # These are the files an data produced using the software from https://gitlab.ub.uni-bielefeld.de/sporada/bundesdata_markup_nlp_software
+│   ├── markup  # Contains all automatically marked protocols.
+│   │   ├── dev_data  # Automatically marked dev_data protocols.
+│   │   │   ├── beautiful_xml  # Final output: humanreadable automatically marked protocolls.
+│   │   │   ├── clear_speech_markup  # Tmp data 
+│   │   │   ├── complex_markup  # Tmp data
+│   │   │   ├── new_metadata  # Tmp data
+│   │   │   └── simple_xml  # Tmp data
+│   │   ├── full_periods    # Automatically marked protocols form all periods.
 │   │   │   ├── 01_Wahlperiode_1949-1953
 │   │   │   ├── 02_Wahlperiode_1953-1957
 │   │   │   ├── 03_Wahlperiode_1957-1961
@@ -65,37 +65,37 @@ Structure:
 │   │   │   ├── 16_Wahlperiode_2005-2009_faulty
 │   │   │   ├── 17_Wahlperiode_2009-2013_faulty
 │   │   │   └── 18_Wahlperiode_2013-2017
-│   │   └── test_data
-│   │       ├── beautiful_xml
-│   │       ├── clear_speech_markup
-│   │       ├── complex_markup
-│   │       ├── new_metadata
-│   │       └── simple_xml
-│   └── nlp
-│       └── full_periods
-│           ├── n-grams
-│           │   ├── lm_ns_speaker
+│   │   └── test_data    # Automatically marked test_data protocols.
+│   │       ├── beautiful_xml # Final output: humanreadable automatically marked protocolls.
+│   │       ├── clear_speech_markup  # Tmp data
+│   │       ├── complex_markup  # Tmp data
+│   │       ├── new_metadata  # Tmp data
+│   │       └── simple_xml  # Tmp data
+│   └── nlp  # All data created from the automatically marked protocolls.
+│       └── full_periods  # Contains data created from all protocolls.
+│           ├── n-grams  # N-Gramm data based on protocolls (sibling of this folder).
+│           │   ├── lm_ns_speaker  # N-grams from lemmatized protocols without stop words counted by speaker.
 │           │   │   ├── 1_grams
 │           │   │   ├── 2_grams
 │           │   │   ├── 3_grams
 │           │   │   ├── 4_grams
 │           │   │   └── 5_grams
-│           │   ├── lm_ns_year
+│           │   ├── lm_ns_year  # N-grams from lemmatized protocols without stop words counted by year.
 │           │   │   ├── 1_grams
 │           │   │   ├── 2_grams
 │           │   │   ├── 3_grams
 │           │   │   ├── 4_grams
 │           │   │   └── 5_grams
-│           │   ├── tk_ws_speaker_(1-3)
+│           │   ├── tk_ws_speaker_(1-3)  # N-grams from tokenized protocols with stop words counted by speaker.
 │           │   │   ├── 1_grams
 │           │   │   ├── 2_grams
 │           │   │   └── 3_grams
-│           │   └── tk_ws_year_(1-4)
+│           │   └── tk_ws_year_(1-4)  # N-grams from tokenized protocols with stop words counted by year.
 │           │       ├── 1_grams
 │           │       ├── 2_grams
 │           │       ├── 3_grams
 │           │       └── 4_grams
-│           └── protocols
+│           └── protocols  # Lemmatized and tokenized protocols used for n-gramm caalculation.
 │               ├── protocols_lemmatized_without_stopwords
 │               └── protocols_tokenized_with_stopwords
 └── protocol_DTD