Commits

Grzegorz Chrupała committed 493d7e1 Merge

CLIN docs

Comments (0)

Files changed (4)

doc/clin-2012/abstract.tex

+\documentclass[a4paper,11pt]{paper}
+\usepackage[utf8]{inputenc}
+%\documentclass[11pt,a4paper]{article}
+
+\title{Computational and cognitive aspects of word class learning}
+
+
+
+\begin{document}
+\maketitle
+\vskip -0.5cm
+\thispagestyle{empty}
+\noindent
+Lexical categories, also  known as word classes, are  commonly used to
+model  syntactic  and  semantic   word  properties  in  a  simple  and
+computationally efficient way. Learning them from distributional clues
+has been  researched from the  perspective of both  cognitive modeling
+and NLP  applications.  Whereas  incremental online learning  and good
+performance on simulations of human behavior are important criteria in
+cognitive   modeling   (Parisien   et   al.  2008),   efficiency   and
+effectiveness in semi-supervised  learning scenarios are essential for
+NLP applications  (Turian et al  2010).  In this research  we evaluate
+versions of recently developed  word class learning algorithms on both
+sets of criteria.  First  we consider the online information theoretic
+model  for category  acquisition of  Chrupala and  Alishahi  2010, and
+explore two modifications \begin{itemize} \item
+vary  the greediness of the algorithm by
+introducing a  version with  a beam search, \item vary  the tradeoff
+between  informativeness  and   parsimony.\end{itemize}   Second,  we  compare  the
+performance  of  this family  of  models  with  the recently  proposed
+efficient   word  class  induction   method  using   Latent  Dirichlet
+Allocation  (Chrupala 2011),  and  with incremental  versions of  this
+approach.  We evaluate on both human behavior simulations such as word
+prediction   and  grammaticality   judgment,  as   well   as  standard
+semi-supervised NLP tasks.
+
+\section*{References}   
+
+C. Parisien, A. Fazly, and S. Stevenson. An incremental Bayesian model
+for learning syntactic categories. CoNLL 2008. \vskip 0.3cm
+
+\noindent
+J. Turian, L. Ratinov, Y. Bengio. Word representations: a simple and
+general method for semi-supervised learning. ACL 2010. \vskip 0.3cm
+
+\noindent
+G. Chrupała and A. Alishahi.  Online Entropy-based Model of Lexical
+Category Acquisition. CoNLL 2010. \vskip 0.3cm
+
+\noindent
+G. Chrupała. Efficient induction of probabilistic word classes with
+LDA. IJCNLP 2011. \vskip 0.3cm
+\end{document}

doc/clin-2012/abstract.txt

+Computational and cognitive aspects of word class learning
+
+Lexical categories, also  known as word classes, are  commonly used to
+model  syntactic  and  semantic   word  properties  in  a  simple  and
+computationally efficient way. Learning them from distributional clues
+has been  researched from the  perspective of both  cognitive modeling
+and NLP  applications.  Whereas  incremental online learning  and good
+performance on simulations of human behavior are important criteria in
+cognitive   modeling   (Parisien   et   al.  2008),   efficiency   and
+effectiveness in semi-supervised  learning scenarios are essential for
+NLP applications  (Turian et al  2010).  In this research  we evaluate
+versions of recently developed  word class learning algorithms on both
+sets of criteria.  First  we consider the online information theoretic
+model  for category  acquisition of  Chrupala and  Alishahi  2010, and
+explore two modifications (i) vary  the greediness of the algorithm by
+introducing a  version with  a beam search  and (ii) vary  the tradoff
+between  informativeness  and   parsimony.   Second,  we  compare  the
+performance  of  this family  of  models  with  the recently  proposed
+efficient   word  class  induction   method  using   Latent  Dirichlet
+Allocation  (Chrupala 2011),  and  with incremental  versions of  this
+approach.  We evaluate on both human behavior simulations such as word
+prediction   and  grammaticality   judgment,  as   well   as  standard
+semi-superised NLP tasks.
+
+References:   
+
+C. Parisien, A. Fazly, and S. Stevenson. An incremental Bayesian model
+for learning syntactic categories. CoNLL 2008.
+
+J. Turian, L. Ratinov, Y. Bengio. Word representations: a simple and
+general method for semi-supervised learning. ACL 2010.
+
+G. Chrupała and A. Alishahi.  Online Entropy-based Model of Lexical
+Category Acquisition. CoNLL 2010.
+
+G. Chrupała. Efficient induction of probabilistic word classes with
+LDA. IJCNLP 2011.
+

doc/clin-2012/notes.txt

+Check out http://www.cs.princeton.edu/~mdhoffma/
+
+- Parametrization - Yevgen
+- Beam search - Yevgen (?)
+- Online Gibbs for LDA - Grzegorz
+- Evaluation on grammaticality judgment for real errors - Afra
+- Better way to do gj (full distro) - Afra ?
+

doc/clin-2012/slides.tex

+\documentclass[17pt]{beamer}
+\usefonttheme[onlymath]{serif}
+\usepackage{latexsym,amsmath,url}
+\usepackage{hyperref}
+\usepackage{color}
+\usepackage[utf8]{inputenc}
+\usepackage{framed}
+\DeclareSymbolFont{AMSb}{U}{msb}{m}{n}
+\DeclareMathOperator*{\argmax}{argmax}
+\mode<presentation>{ 
+  \usetheme{Boadilla}
+} \title[Word class learning]{Word class learning}
+\subtitle{Computational and cognitive aspects}
+
+\date[CLIN 2012]{CLIN 2012}
+\author[GC, AA, YM]{Grzegorz Chrupa{\l}a \and Afra Alishahi \\ \and Yevgen Matusevych}
+
+\institute[UdS, UvT]
+%{
+%UdS and UvT
+%}
+
+\begin{document}
+\frame{\titlepage}
+
+\begin{frame}\frametitle{Word classes}
+  \begin{block}{}
+    \begin{center}
+      \begin{tabular}{c}
+        \color{red} Berlin  Bangkok  Tokyo  Warsaw\\
+        \color{blue} Sarkozy  Merkel Obama  Berlusconi \\
+        \color{olive} Mr  Ms  President  Dr \\
+      \end{tabular}
+    \end{center}
+
+  \end{block}
+
+  \begin{itemize}
+  \item Groups of words sharing syntax/semantics
+  \item Useful for generalization and abstraction
+  \end{itemize}
+\end{frame}
+
+\end{document}