acin-interview/presentation.tex

\documentclass[12pt,t]{beamer}
\usepackage{graphicx}
\setbeameroption{hide notes}
\setbeamertemplate{note page}[plain]

% get rid of junk
\usetheme{default}
\beamertemplatenavigationsymbolsempty
\hypersetup{pdfpagemode=UseNone} % don't show bookmarks on initial view

% font
\usepackage{bm}
\usepackage{fontspec}
\setsansfont{TeX Gyre Heros}
\setbeamerfont{note page}{family*=pplx,size=\footnotesize} % Palatino for notes
% "TeX Gyre Heros can be used as a replacement for Helvetica"
% In Unix, unzip the following into ~/.fonts
% In Mac, unzip it, double-click the .otf files, and install using "FontBook"
%   http://www.gust.org.pl/projects/e-foundry/tex-gyre/heros/qhv2.004otf.zip

% restore a standard LaTeX-like math font
\usepackage{amsmath}
\usepackage{unicode-math}
\setmathfont{Latin Modern Math}

%\newfontfamily\emojifont{Noto Emoji}
\newcommand{\inlineemoji}[2][1.2em]{%
  \raisebox{-0.2em}{\includegraphics[height=#1]{#2}}%
}

%% named colors
%\definecolor{offwhite}{RGB}{249,242,215}
%\definecolor{foreground}{RGB}{255,255,255}
%\definecolor{background}{RGB}{24,24,24}
%\definecolor{title}{RGB}{107,174,214}
%\definecolor{gray}{RGB}{155,155,155}
%\definecolor{subtitle}{RGB}{102,255,204}
%\definecolor{hilight}{RGB}{102,255,204}
%\definecolor{vhilight}{RGB}{255,111,207}
%\definecolor{lolight}{RGB}{155,155,155}
%%\definecolor{green}{RGB}{125,250,125}

% named colors for white-background slides
\definecolor{offwhite}{RGB}{255,255,255}
\definecolor{foreground}{RGB}{34,34,34}
\definecolor{background}{RGB}{255,255,255}
\definecolor{title}{RGB}{0,82,155}
%\definecolor{gray}{RGB}{110,110,110}
\definecolor{gray}{RGB}{15,15,15}
\definecolor{subtitle}{RGB}{0,121,107}
\definecolor{hilight}{RGB}{0,121,107}
\definecolor{vhilight}{RGB}{180,0,102}
\definecolor{lolight}{RGB}{130,130,130}
%\definecolor{green}{RGB}{0,140,70}

% use those colors
\setbeamercolor{titlelike}{fg=title}
\setbeamercolor{subtitle}{fg=subtitle}
\setbeamercolor{institute}{fg=gray}
\setbeamercolor{normal text}{fg=foreground,bg=background}
\setbeamercolor{item}{fg=foreground} % color of bullets
\setbeamercolor{subitem}{fg=gray}
\setbeamercolor{itemize/enumerate subbody}{fg=gray}
\setbeamertemplate{itemize subitem}{{\textendash}}
\setbeamerfont{itemize/enumerate subbody}{size=\footnotesize}
\setbeamerfont{itemize/enumerate subitem}{size=\footnotesize}

% configure itemize spacing

% alas, it breaks itemize styling :(
%\usepackage{enumitem}
% second-level itemize (sub-itemize)
%\setlist[itemize,2]{itemsep=0.7em}

% page number
\setbeamertemplate{footline}{%
    \raisebox{5pt}{\makebox[\paperwidth]{\hfill\makebox[20pt]{\color{gray}
          \scriptsize\insertframenumber}}}\hspace*{5pt}}

% add a bit of space at the top of the notes page
\addtobeamertemplate{note page}{\setlength{\parskip}{12pt}}

% a few macros
\newcommand{\bi}{\begin{itemize}}
\newcommand{\ei}{\end{itemize}}
\newcommand{\ig}{\includegraphics}
\newcommand{\subt}[1]{{\footnotesize \color{subtitle} {#1}}}
\newcommand{\subtnc}[1]{{\footnotesize #1}}

% title info
\title{AI-Enhanced High-Accuracy Robotics for Industrial Applications}
\subtitle{Application for PhD-Position (m/f/d) in Industrial Robotics}
\author{\href{https://abanbytes.eu}{David Madl}}
%\institute{\href{https://www.biostat.wisc.edu}{Biostatistics \& Medical Informatics} \\[2pt] \href{http://www.wisc.edu}{University of Wisconsin{\textendash}Madison}}
\date{%\href{http://kbroman.org}{\tt \scriptsize kbroman.org}
%\\[-4pt]
\href{https://github.com/cidermole}{\tt \scriptsize github.com/cidermole}
}


\begin{document}

% title slide
{
\setbeamertemplate{footline}{} % no page number here
\frame{
  \titlepage
  \note{
} } }

\begin{frame}{Me - personal interests}

\vspace{24pt}

\bi
%\item{\emojifont🏐 Volleyball}
%\item{\emojifont🧗 Bouldering}
%\item{\emojifont💃 Tango Argentino}
%\item{\emojifont♘ Chess}
%\item{\emojifont🌎 South America}

\item{\inlineemoji{Images/volley.png} Volleyball}
\item{\inlineemoji{Images/boulder.png} Bouldering}
\item{\inlineemoji{Images/tango.png} Tango Argentino}
\item{\inlineemoji{Images/chess.png} Chess}
\item{\inlineemoji{Images/sa.png} South America}
\ei

\end{frame}


\begin{frame}{MSc Thesis}
\subt{Handling out-of-vocabulary words in a domain adaptation setting in SMT}

%\vspace{12pt}

\begin{itemize}
  \item{Phrase-based Statistical Machine Translation\vspace{0.5em}}
  \begin{itemize}
    \addtolength{\itemsep}{0.7em}
    \item{Warren Weaver (1947):\\[0.5em]
    \textit{``This [article in Russian] is really written in English, but it has been coded in some strange symbols. I will now proceed to decode.''}}
    \item{Bayes Theorem \& independence assumption:\\[0.5em]
    $P(\text{en}|\text{ru}) = \frac{P(\text{ru}|\text{en}) P(\text{en})}{P(\text{ru})}$\\[0.5em]
    $P(\text{ru}|\text{en}) = \prod_{i}^{M} P(\text{phrase\_ru}_{i}|\text{en})$ \hspace{0.5em} translation model\\[0.5em]
    $P(\text{en}) = \prod_{k}^{L} P(w_{k}|w_{k-n}...w_{k-1})$ \hspace{0.5em} language model\\[0.5em]
    $P(\text{ru})$ \hspace{0.5em} dropped normalization factor
    }
  \end{itemize}
\end{itemize}

{\tiny see e.g. (Koehn et al 2003, ``Statistical phrase-based translation'')}

\note{
  The rules for the translation model are more complex than shown here, because of the possibility of phrase splits at different word boundaries.

  The probabilities on the \textbf{right-hand side} are estimated from a training corpus. 
  The language model is estimated as transitions of an n-state \textbf{Hidden Markov Model}. 
  The translation model obtains phrases from a previous optimization called \textbf{Word Alignment}.
}

% {\color{hilight} b}

\end{frame}


\begin{frame}{MSc Thesis - Domain Adaptation 1}
\subtnc{Handling out-of-vocabulary words in a domain adaptation setting in SMT}

\vspace{12pt}

\bi
  \item{{\color{hilight} test} and {\color{vhilight} train} datasets}\\[0.5em]
  \item{{\color{hilight} medical} and {\color{vhilight} political} domains}\\[0.5em]
  \item{{\color{hilight} 5 M} and {\color{vhilight} 50 M} word tokens}\\[0.5em]
  \item{Domain adaptation:\\[0.5em]
    ${\color{hilight} P(\text{en}|\text{ru})} = \frac{\color{vhilight} P(\text{ru}|\text{en}) P(\text{en})}{P(\text{ru})}$\\[0.5em]
    ${\color{vhilight} P(\text{ru}|\text{en}) = \prod_{i}^{M} P(\text{phrase\_ru}_{i}|\text{en})}$ \hspace{0.5em} translation model\\[0.5em]
    ${\color{vhilight} P(\text{en}) = \prod_{k}^{L} P(w_{k}|w_{k-n}...w_{k-1})}$ \hspace{0.5em} language model\\[0.5em]
  }
\ei

\note{
  In domain adaptation, we have a distributional mismatch between training and test data. 
  Simply appending target domain text to a large training dataset is not optimal. 
  This is because the statistics of the original domain dominate.
}

\end{frame}


\begin{frame}{MSc Thesis - Domain Adaptation 2}
\subtnc{Handling out-of-vocabulary words in a domain adaptation setting in SMT}

\vspace{12pt}

\bi
  \item{{\color{hilight} medical} and {\color{vhilight} political} domains}\\[0.5em]
  \item{Mixture model:\\[0.5em]
    $P(\text{ru}|\text{en}) = \alpha_1 {\color{hilight} P_1(\text{ru}|\text{en})} + \alpha_2 {\color{vhilight} P_2(\text{ru}|\text{en})} $\\[0.5em]
    $P(\text{en}) = \alpha_1 {\color{hilight} P_1(\text{en})} + \alpha_2 {\color{vhilight} P_2(\text{en})} $\\[0.5em]
  }
  \item{Optimize quality measure:\\[0.5em]
    $argmax_{\symbf{\alpha}} \text{BLEU}(\symbf{\alpha})$, $\sum_i \alpha_i = 1$}
\ei

\note{
  We can do better by estimating two models, one on each domain. 
  Then we optimize the resulting translation quality based on the mixture parameters.
}

\end{frame}


\begin{frame}{MSc Thesis - Word Alignment oracle}
\subt{Handling out-of-vocabulary words in a domain adaptation setting in SMT}

\begin{center}
\ig[width=0.6\textwidth]{Images/oov.png}
\end{center}

{\tiny source: Figure 6.1.3b, MSc Thesis}

\note{
  The thesis topic I was assigned was to investigate words which could not be translated. 
  The oracle experiments are the most insightful. This one shows, for different training set sizes:
  * in green, the **theoretical limit** from training data,
  * in red, if **Word Alignment** had full statistics,
  * in blue, the actual errors.
}

\end{frame}


\end{document}