tex-projects/LaTeX-examples
2
0
Fork 0
mirror of https://github.com/MartinThoma/LaTeX-examples.git synced 2025-04-19 11:38:05 +02:00
Code Activity

added bachelor proposal

Browse source
This commit is contained in:
Martin Thoma 2014-01-09 22:37:16 +01:00
parent 9140b59586
commit 0810c80f7a
5 changed files with 1580 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

10
documents/bachelor-proposal/Makefile Normal file
View file

@ -0,0 +1,10 @@
SOURCE = bachelor-proposal
make:
pdflatex $(SOURCE).tex -output-format=pdf
bibtex $(SOURCE)
pdflatex $(SOURCE).tex -output-format=pdf # Referenzen einbinden
pdflatex $(SOURCE).tex -output-format=pdf # Referenzen einbinden
make clean
clean:
rm -rf $(TARGET) *.class *.html *.log *.aux *.out *.bcf *.bbl *.blg

160
documents/bachelor-proposal/bachelor-proposal.tex Normal file
View file

@ -0,0 +1,160 @@
\documentclass[a4paper]{scrartcl}
\usepackage{amssymb, amsmath} % needed for math
\usepackage[utf8]{inputenc} % this is needed for umlauts
\usepackage[english]{babel} % this is needed for umlauts
\usepackage[T1]{fontenc} % this is needed for correct output of umlauts in pdf
\usepackage[margin=2.5cm]{geometry} %layout
\usepackage{hyperref} % links im text
\usepackage{color}
\usepackage{framed}
\usepackage{enumerate} % for advanced numbering of lists
\usepackage{csquotes}
\usepackage{ifxetex,ifluatex}
\usepackage{etoolbox}
\usepackage[svgnames]{xcolor}
\usepackage{tikz}
\usepackage{framed}
\usepackage{parskip}
\usepackage{cite}
\usepackage{mystyle}
\clubpenalty = 10000 % Schusterjungen verhindern
\widowpenalty = 10000 % Hurenkinder verhindern
\hypersetup{
pdfauthor = {Martin Thoma},
pdfkeywords = {Bachelor proposal: },
pdftitle = {Bachelor proposal}
}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\begin{document}
\title{Proposal for a Bachelor of Science Thesis:\\Recognition of mathematical formulae in the Context of Lecture Translation}
\author{Martin Thoma}
\maketitle
\section{The problem backgound}
The KIT Lecture Translator, CMUSphinx, Android voice typing and
many other speech recognition systems have proven that it is possible to
recognize speech. But at the moment, there seems not to be a single
system that manages to recognize natural language math speech
recognition. For example, a term like
\[\sum_{n=1}^\infty \frac{1}{n^2} \rightarrow \infty \]
would naturally be spoken as
\begin{shadequote}[l]{}
The sum of one divided by n squared for n from one to infinity diverges to infinity.
\end{shadequote}
in natural language. Today, speech recognition systems do only
recognize the words spoken. They don't recognize that it was a
mathematical term which could and should be expressed with symbols.
One way to extend an existing speech recognition $A$ systems would be
by the following steps:
\begin{enumerate}
\item $A$ recognizes speech and returns a text $T$. This text
has to contain anotations that indicate at which time
in the original recording the various parts of speech
were detected.
\item A math detecter parses $T$ and returns the time intervalls $I$
when math was detected.
\item A math parser tries to parse speech in $I$. This parser
can make use of a language model dedicated to math. It
returns weighted hypotheses which terms might have
been spoken.
\item Finally, a program compares the hypotheses with math
in a formula database. Many formulas might already been
written in \TeX{}, e.g. on Wikipedia, math.stackexchange.com
or in freely available \LaTeX{} / \TeX{} files.
\end{enumerate}
\break
\section{The problem statement}
The bachelor's thesis at KIT is worth 15 ECTS. It should be
created within 4 months and at most 450 hours.
This aim of this bachelor's thesis is to answer the following
questions:
\begin{itemize}
\item \textbf{Representation of Math:} How can math be expressed
for speech recognition in a textual way?
Especially:
\begin{itemize}
\item What reasons are there to use \TeX{}, which
reasons are there for MathML?
\item Are there alternatives?
\end{itemize}
\item \textbf{Detection:} How can parts of speech be detected
that contain math?
\begin{itemize}
\item Which keywords indicate mathematics?
\item Is a keyword-density based approach sufficient?
\end{itemize}
\item \textbf{Evalution of math recognition strength}:
\begin{itemize}
\item How can speech recognition systems be evaluated
for their strength in math recognition?
\item Is the \textbf{W}ord \textbf{E}rror \textbf{R}ate
to measure how well the recognition worked?
\end{itemize}
\item \textbf{Literature research:}
\begin{itemize}
\item Can \TeX{} be used as a grammar to recognize math speech?
\item Can MathML be used as a grammar to recognize math speech?
\end{itemize}
\end{itemize}
Follow-up tasks, that will not be part of this bachelor's thesis,
include:
\begin{itemize}
\item \textbf{Other languages}: This thesis will focus on math
recognition for the English language. Follow-up work might
try to deal with math independant of the language.
\item \textbf{Implementation}: The aim of this thesis is not
to create a working math recognition.
\end{itemize}
\section{Significance}
This thesis will create a basis for follow-up work in speech recognition
that contains mathematical content. It will enable people to evaluate
various speech2math recognition ideas. Also, it will give an overview
of the current state of art in math speech recognition and which
questions need to be tackled in feature.
\section{Time schedule}
\begin{itemize}
\item[10h] Research of ways to represent math
\item[20h] Research ways how \TeX{} deals with math
\item[20h] Research how MathML deals with math
\item[50h] Recording math lectures
\item[100h] Annotating math lectures; writing the best
representation for mathematical terms contained in
these lectures
\item[10h] Finding keywords that indicate mathematical formulas
\item[5h] Test the keyword-approach with the annotated lectures
\end{itemize}
\renewcommand\refname{Related Literature}
\nocite{*}
\bibliographystyle{itmalpha}
\bibliography{literatur}
\section{Hypotheses}
I think that MathML will be the best way to represent math, because
it was designed to do this. MathML~3.0, the most recent version,
is a W3C recommendation since October 2001.
\TeX{} in contrast is great in rendering mathematical equations,
but it grew over time. It existed even before the web was invented.
Another reason why I think MathML might be favorable for internal
representation is that it was created to be parsed and written by
machines. It is an XML standard and as such you can apply XML tools
and libraries to parse it. \TeX{} on the other hand was created
to be written by humans.
I'm pretty sure that it is hopless to create a grammar for math
in it's general form. But for some areas like boolean logic, arithmetic
or analysis it might work pretty well.
\end{document}

1325
documents/bachelor-proposal/itmalpha.bst Normal file
View file

File diff suppressed because it is too large Load diff

20
documents/bachelor-proposal/literatur.bib Normal file
View file

@ -0,0 +1,20 @@
% This file was created with JabRef 2.3.1.
% Encoding: Cp1252
@article{lakra,
author = {Sachin Lakra AND T. V. Prasad AND Deepak Kumar Sharma AND Shree Harsh Atrey AND Anubhav Kumar Sharma},
title = {Application of Fuzzy Mathematics to Speech-to-Text Conversion by Elimination of Paralinguistic Content},
version = {1},
date = {2012-09-20},
eprinttype = {arxiv},
eprintclass = {cs.AI},
eprint = {http://arxiv.org/abs/1209.4535v1}
}
@MISC{Fateman06howcan,
author = {Richard Fateman},
title = {How can we speak math?},
year = {2006},
doi = {10.1.1.73.5028},
url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.73.5028},
}

65
documents/bachelor-proposal/mystyle.sty Normal file
View file

@ -0,0 +1,65 @@
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% conditional for xetex or luatex
\newif\ifxetexorluatex
\ifxetex
\xetexorluatextrue
\else
\ifluatex
\xetexorluatextrue
\else
\xetexorluatexfalse
\fi
\fi
%
\ifxetexorluatex%
\usepackage{fontspec}
\usepackage{libertine} % or use \setmainfont to choose any font on your system
\newfontfamily\quotefont[Ligatures=TeX]{Linux Libertine O} % selects Libertine as the quote font
\else
\usepackage[utf8]{inputenc}
\usepackage[T1]{fontenc}
\usepackage{libertine} % or any other font package
\newcommand*\quotefont{\fontfamily{LinuxLibertineT-LF}} % selects Libertine as the quote font
\fi
\newcommand*\quotesize{60} % if quote size changes, need a way to make shifts relative
% Make commands for the quotes
\newcommand*{\openquote}
{\tikz[remember picture,overlay,xshift=-4ex,yshift=-2.5ex]
\node (OQ) {\quotefont\fontsize{\quotesize}{\quotesize}\selectfont``};\kern0pt}
\newcommand*{\closequote}[1]
{\tikz[remember picture,overlay,xshift=4ex,yshift={#1}]
\node (CQ) {\quotefont\fontsize{\quotesize}{\quotesize}\selectfont''};}
% select a colour for the shading
\colorlet{shadecolor}{white}
\newcommand*\shadedauthorformat{\emph} % define format for the author argument
% Now a command to allow left, right and centre alignment of the author
\newcommand*\authoralign[1]{%
\if#1l
\def\authorfill{}\def\quotefill{\hfill}
\else
\if#1r
\def\authorfill{\hfill}\def\quotefill{}
\else
\if#1c
\gdef\authorfill{\hfill}\def\quotefill{\hfill}
\else\typeout{Invalid option}
\fi
\fi
\fi}
% wrap everything in its own environment which takes one argument (author) and one optional argument
% specifying the alignment [l, r or c]
%
\newenvironment{shadequote}[2][l]%
{\authoralign{#1}
\ifblank{#2}
{\def\shadequoteauthor{}\def\yshift{-2ex}\def\quotefill{\hfill}}
{\def\shadequoteauthor{\par\authorfill\shadedauthorformat{#2}}\def\yshift{2ex}}
\begin{snugshade}\begin{quote}\openquote}
{\shadequoteauthor\quotefill\closequote{\yshift}\end{quote}\end{snugshade}}