\documentclass[10pt,a4paper]{article}

% Packages
\usepackage{fancyhdr}           % For header and footer
\usepackage{multicol}           % Allows multicols in tables
\usepackage{tabularx}           % Intelligent column widths
\usepackage{tabulary}           % Used in header and footer
\usepackage{hhline}             % Border under tables
\usepackage{graphicx}           % For images
\usepackage{xcolor}             % For hex colours
%\usepackage[utf8x]{inputenc}    % For unicode character support
\usepackage[T1]{fontenc}        % Without this we get weird character replacements
\usepackage{colortbl}           % For coloured tables
\usepackage{setspace}           % For line height
\usepackage{lastpage}           % Needed for total page number
\usepackage{seqsplit}           % Splits long words.
%\usepackage{opensans}          % Can't make this work so far. Shame. Would be lovely.
\usepackage[normalem]{ulem}     % For underlining links
% Most of the following are not required for the majority
% of cheat sheets but are needed for some symbol support.
\usepackage{amsmath}            % Symbols
\usepackage{MnSymbol}           % Symbols
\usepackage{wasysym}            % Symbols
%\usepackage[english,german,french,spanish,italian]{babel}              % Languages

% Document Info
\author{samshamsan}
\pdfinfo{
  /Title (nlp-for-arabic.pdf)
  /Creator (Cheatography)
  /Author (samshamsan)
  /Subject (NLP For Arabic Cheat Sheet)
}

% Lengths and widths
\addtolength{\textwidth}{6cm}
\addtolength{\textheight}{-1cm}
\addtolength{\hoffset}{-3cm}
\addtolength{\voffset}{-2cm}
\setlength{\tabcolsep}{0.2cm} % Space between columns
\setlength{\headsep}{-12pt} % Reduce space between header and content
\setlength{\headheight}{85pt} % If less, LaTeX automatically increases it
\renewcommand{\footrulewidth}{0pt} % Remove footer line
\renewcommand{\headrulewidth}{0pt} % Remove header line
\renewcommand{\seqinsert}{\ifmmode\allowbreak\else\-\fi} % Hyphens in seqsplit
% This two commands together give roughly
% the right line height in the tables
\renewcommand{\arraystretch}{1.3}
\onehalfspacing

% Commands
\newcommand{\SetRowColor}[1]{\noalign{\gdef\RowColorName{#1}}\rowcolor{\RowColorName}} % Shortcut for row colour
\newcommand{\mymulticolumn}[3]{\multicolumn{#1}{>{\columncolor{\RowColorName}}#2}{#3}} % For coloured multi-cols
\newcolumntype{x}[1]{>{\raggedright}p{#1}} % New column types for ragged-right paragraph columns
\newcommand{\tn}{\tabularnewline} % Required as custom column type in use

% Font and Colours
\definecolor{HeadBackground}{HTML}{333333}
\definecolor{FootBackground}{HTML}{666666}
\definecolor{TextColor}{HTML}{333333}
\definecolor{DarkBackground}{HTML}{A3A3A3}
\definecolor{LightBackground}{HTML}{F3F3F3}
\renewcommand{\familydefault}{\sfdefault}
\color{TextColor}

% Header and Footer
\pagestyle{fancy}
\fancyhead{} % Set header to blank
\fancyfoot{} % Set footer to blank
\fancyhead[L]{
\noindent
\begin{multicols}{3}
\begin{tabulary}{5.8cm}{C}
    \SetRowColor{DarkBackground}
    \vspace{-7pt}
    {\parbox{\dimexpr\textwidth-2\fboxsep\relax}{\noindent
        \hspace*{-6pt}\includegraphics[width=5.8cm]{/web/www.cheatography.com/public/images/cheatography_logo.pdf}}
    }
\end{tabulary}
\columnbreak
\begin{tabulary}{11cm}{L}
    \vspace{-2pt}\large{\bf{\textcolor{DarkBackground}{\textrm{NLP For Arabic Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{samshamsan} via \textcolor{DarkBackground}{\uline{cheatography.com/124093/cs/23656/}}}
\end{tabulary}
\end{multicols}}

\fancyfoot[L]{ \footnotesize
\noindent
\begin{multicols}{3}
\begin{tabulary}{5.8cm}{LL}
  \SetRowColor{FootBackground}
  \mymulticolumn{2}{p{5.377cm}}{\bf\textcolor{white}{Cheatographer}}  \\
  \vspace{-2pt}samshamsan \\
  \uline{cheatography.com/samshamsan} \\
  \end{tabulary}
\vfill
\columnbreak
\begin{tabulary}{5.8cm}{L}
  \SetRowColor{FootBackground}
  \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Cheat Sheet}}  \\
   \vspace{-2pt}Published 5th July, 2020.\\
   Updated 6th July, 2020.\\
   Page {\thepage} of \pageref{LastPage}.
\end{tabulary}
\vfill
\columnbreak
\begin{tabulary}{5.8cm}{L}
  \SetRowColor{FootBackground}
  \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Sponsor}}  \\
  \SetRowColor{white}
  \vspace{-5pt}
  %\includegraphics[width=48px,height=48px]{dave.jpeg}
  Measure your website readability!\\
  www.readability-score.com
\end{tabulary}
\end{multicols}}




\begin{document}
\raggedright
\raggedcolumns

% Set font size to small. Switch to any value
% from this page to resize cheat sheet text:
% www.emerson.emory.edu/services/latex/latex_169.html
\footnotesize % Small font.

\begin{multicols*}{3}

\begin{tabularx}{5.377cm}{x{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Arabic script}}  \tn
% Row 0
\SetRowColor{LightBackground}
36=28 consonants,6(ؤأإآءئ), Ta ة, ِAlif ى & NLP Task - Orthographic Transliteration: \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
19 letters shape \& ك والهمزة والنقاط & Backwlater Transliteration model \tn 
% Row Count 6 (+ 3)
% Row 2
\SetRowColor{LightBackground}
Lettershape: Initial, medial, final and isolate & NLP Task - Orthographic Normalization: \tn 
% Row Count 9 (+ 3)
% Row 3
\SetRowColor{white}
Cursive connected style & encoding cleanup-\textgreater{}complex ligature, ك \tn 
% Row Count 11 (+ 2)
% Row 4
\SetRowColor{LightBackground}
Ligtures & Tatweel and diacritics remove \tn 
% Row Count 13 (+ 2)
% Row 5
\SetRowColor{white}
Diacritic (Vowel, Nunation, Shadda, Dagger) & Letter normalization: أإآ-{}-\textgreater{} ا \tn 
% Row Count 16 (+ 3)
% Row 6
\SetRowColor{LightBackground}
Digits (Westren and eastren) - LTR & Hand writing - MADCAT \tn 
% Row Count 18 (+ 2)
% Row 7
\SetRowColor{white}
Punctuation {[}: . !"{]} {[}؟،{]} Tatweel & Automatic Diacritization  - Only 1.5\% \tn 
% Row Count 20 (+ 2)
% Row 8
\SetRowColor{LightBackground}
Typography, growing font library & Other Languages Letter: Persian, Kurdish \tn 
% Row Count 22 (+ 2)
% Row 9
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{Encoding: Unicode, ISO-8859, CP-1256} \tn 
% Row Count 23 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Challenges to Arabic NLP}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{Orthographic ambiguity} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{Orthographic inconsistency} \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{Morphological Complexity} \tn 
% Row Count 3 (+ 1)
% Row 3
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{Dialect Variation} \tn 
% Row Count 4 (+ 1)
% Row 4
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{Annotated resource poverty} \tn 
% Row Count 5 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.24425 cm} x{3.73275 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Arabic Phonolgy}}  \tn
% Row 0
\SetRowColor{LightBackground}
Phonem: & Minimal pair: /k//g/ قلب \& كلب \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
MSA - ق /q/ & /q/, /k/, /ʔ/, /g/, /ʤ/, /ɢ/ \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
ث /θ/ & /θ/, /t/, /s/ \tn 
% Row Count 5 (+ 1)
% Row 3
\SetRowColor{white}
ذ /δ/ & /δ/, /d/, /z/ \tn 
% Row Count 6 (+ 1)
% Row 4
\SetRowColor{LightBackground}
ج /ʤ/ & /ʤ/, /g/, /ʒ/ \tn 
% Row Count 7 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Orthography Connected to Phoneme}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{p{5.377cm}}{\vspace{1px}\centerline{\includegraphics[width=5.1cm]{/web/www.cheatography.com/public/uploads/samshamsan_1593979567_Screen Shot 2020-07-05 at 1.00.16 PM.png}}} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.38896 cm} x{2.58804 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Orthography - Ambiguity}}  \tn
% Row 0
\SetRowColor{LightBackground}
Optional Diacritization & Complex = No vowels? long vowels, initial \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
Arabic words has on average: & 12.3 Analysis \& 6.8 Diacritics \& 2.7 lama \tn 
% Row Count 6 (+ 3)
% Row 2
\SetRowColor{LightBackground}
Morpho-Phonemic Spelling issue 1: & الشمسية والقمرية  || ة -\textgreater{} ه  || عصا -\textgreater{} عصى \tn 
% Row Count 10 (+ 4)
% Row 3
\SetRowColor{white}
Morpho-Phonemic Spelling issue 2: & التنوين ينطق نون - ألف واو الجماعة لاينطق \tn 
% Row Count 14 (+ 4)
% Row 4
\SetRowColor{LightBackground}
Standardization Issue & سوريا وسورية || فيلم وفلم || أفريقية وأفريقيا \tn 
% Row Count 18 (+ 4)
% Row 5
\SetRowColor{white}
NLP Task: & Proper Name Transliteration \tn 
% Row Count 20 (+ 2)
% Row 6
\SetRowColor{LightBackground}
Qaddafi problem (Kadafi, Qadafi.....) & Schwarzenegger Problem (شوارزينجر , شوارزينغر) \tn 
% Row Count 24 (+ 4)
% Row 7
\SetRowColor{white}
Hassan Problem & Marie problem -{}-{}-\textgreater{} Los it to ماري \tn 
% Row Count 26 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.93643 cm} x{2.04057 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Arabic Spelling}}  \tn
% Row 0
\SetRowColor{LightBackground}
Hamzated Alif and Alif maqsura 11\% & Penn Arabic bank tree \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
(30\%) of words have errors/out of 2M words & Qatar Arabic Language Bank \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
Arabic spelling errors are a big challenge & GIGO: Garbage In Garbage Out \tn 
% Row Count 6 (+ 2)
% Row 3
\SetRowColor{white}
Inconsistencies in Dialectal Arabic !=standard & \seqsplit{مابيقولهاش} \tn 
% Row Count 8 (+ 2)
% Row 4
\SetRowColor{LightBackground}
َو+ ب+أدلة+ها & \seqsplit{َو+بَادَلت+ها} \tn 
% Row Count 10 (+ 2)
% Row 5
\SetRowColor{white}
العَيـن = (eye, water spring, Alain city) & Spelling variants \tn 
% Row Count 13 (+ 3)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Arabic Morphology}}  \tn
% Row 0
\SetRowColor{LightBackground}
Morphological Complexity & A core word has many inflected forms \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
Gender(2), Number(3), Person(3), Aspect(3) & Tense particle (2), Mood(3), Voice(2), \tn 
% Row Count 5 (+ 3)
% Row 2
\SetRowColor{LightBackground}
Pronominal clitic(12), Conjunction clitic(3) & وسنقولها =/wasanaqūluhā/= و+ س+ ن+ قول + ها \tn 
% Row Count 9 (+ 4)
% Row 3
\SetRowColor{white}
go went going gone go goes & VB VBD VBG VBN VBP VBZ \tn 
% Row Count 11 (+ 2)
% Row 4
\SetRowColor{LightBackground}
Arabic POS tags: 22,400 tags & English POS tags: 48 tags \tn 
% Row Count 13 (+ 2)
% Row 5
\SetRowColor{white}
12.3 analyses and 2.7 lemmas per word & Functional Morphology جمع تكسير \tn 
% Row Count 15 (+ 2)
% Row 6
\SetRowColor{LightBackground}
Form based morphology التصريف الطبيعي & علم العروض. الفراهيدي - الكتابة العروضية \tn 
% Row Count 19 (+ 4)
% Row 7
\SetRowColor{white}
الكتاب الرمزية - /0//00 & التنوين, الشدة, الاشباع والألف :هندن أخلل يحرمي هاذا \tn 
% Row Count 24 (+ 5)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{0.9954 cm} x{3.9816 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Tools and Papers}}  \tn
% Row 0
\SetRowColor{LightBackground}
\seqsplit{MADAMIRA} & State-of-the-art Arabic and Arabic Dialect processing \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
MADAR & Multi-Arabic Dialect Applications and resources \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
SAMER & Simplification of Arabic Masterpieces for Extensive \tn 
% Row Count 6 (+ 2)
% Row 3
\SetRowColor{white}
CODA & A conventional orthography for Dialectal Arabic \tn 
% Row Count 8 (+ 2)
% Row 4
\SetRowColor{LightBackground}
\seqsplit{tashaphyne} & Arabic lite Stemmer \tn 
% Row Count 10 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.38896 cm} x{2.58804 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{POS For Arabic}}  \tn
% Row 0
\SetRowColor{LightBackground}
Stanford Arabic parser tagset & Morphological annotation Quranic Arabic corpus \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
Arabic MADA system tagset & POS tag set for Modern Standard Arabic \tn 
% Row Count 5 (+ 2)
% Row 2
\SetRowColor{LightBackground}
The APT tagger (Khoja, 2001) / hybrid & The Qutuf (Altabba et al., 2010) tagger \tn 
% Row Count 7 (+ 2)
% Row 3
\SetRowColor{white}
Al-Dahdah (1989), & TreeTagger by Schmid (1995)) - 20+ lang \tn 
% Row Count 9 (+ 2)
% Row 4
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{Noun (اِسْم)\textless{}Aisom\textgreater{}, Verb (فِعْل)\textless{}fiEol\textgreater{}, and Particle (حَرْف)\textless{}Harof\textgreater{}.} \tn 
% Row Count 11 (+ 2)
% Row 5
\SetRowColor{white}
\mymulticolumn{2}{x{5.377cm}}{Each one of these categories has many subcategories.} \tn 
% Row Count 13 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}


% That's all folks
\end{multicols*}

\end{document}