Added SICK project

SICK/sujet2_SICK.tex

+\documentclass[french]{article}
+\usepackage[T1]{fontenc}
+\usepackage[utf8]{inputenc}
+\usepackage{lmodern}
+\usepackage[a4paper]{geometry}
+\usepackage{babel}
+\usepackage{url}
+\usepackage{dblfloatfix}
+\usepackage{booktabs}
+
+\begin{document}
+
+\begin{center}
+	\LARGE
+	{\bf Natural Language Inference} \\[5mm]
+	\Large
+	\bf Projet Apprentissage Automatique en Langues \\
+	{\bf 2018/2019} \\[2mm]
+\end{center}
+
+\vspace{1cm}
+
+\section{Project Description}
+
+This project actually contains 2 tasks: sentence entailment (classification task) and sentence relatedness (regression task)
+
+The task of sentence entailment (SICK-E) is to predict whether two sentences are \textbf{entailed}, \textbf{neutral} or \textbf{contradictory}. 
+The task of sentence relatedness (SICK-R) is to predict the \textbf{relatedness score} between two sentences. This score ranges from 0.0 to 5.0.
+
+The goal of this project is to implement a machine learning model for SICK-E and/or SICK-R. 
+
+
+\section{Data Description }
+
+Details for this dataset are available at the following address: \textrm{http://clic.cimec.unitn.it/composes/sick.html}
+
+File format (tab separated):
+
+{ \scriptsize
+\begin{center}
+\begin{tabular}{lllcc}
+pair\_ID & sentence\_A &      sentence\_B &      relatedness\_score &       entailment\_judgment \\
+93 &      A lone biker is jumping in the air &      A man is jumping into a full pool &       1.7     & NEUTRAL
+\end{tabular}
+\end{center}
+}
+
+The provided files are described in Table~\ref{table:data}.
+\begin{table}[htbp]
+\begin{center}
+\begin{tabular}{|c|l|c|}
+\toprule
+Name & File & \# Sent. pairs \\
+\midrule
+Train & SICK\_train.txt & 4501 \\
+Dev & SICK\_trial.txt & 501 \\
+Test & SICK\_test.txt & 4928 \\
+\bottomrule
+\end{tabular}
+\end{center}
+\caption{\label{table:data}Description of the data}
+\end{table}
+
+
+\section{Evaluation}
+
+For SICK-E, systems are evaluated on classification accuracy (the percent of labels that are predicted correctly) for every sentence pairs. 
+We are also interested in the precision/recall scores for each class as well as a confusion matrix. 
+
+For SICK-R, systems are evaluated using the Pearson correlation coefficient: see scipy.stats.pearsonr. 
+
+\section{Project Roadmap}
+\begin{enumerate}
+\item Preprocess and prepare the training data
+\item Train, optimize and evaluate a baseline deep recurrent neural network (RNN) using pytorch. \textbf{[one per group]}
+\item Each student should propose \textbf{one} enhancement to the baseline model (additional data, regularization, network initialization, new architecture, etc.) \textbf{[one per student]}
+\item Prepare the final defense: present your model and the obtained results 
+\end{enumerate}
+
+
+\section{References}
+\begin{itemize}
+\item SICK webpage: \textrm{http://clic.cimec.unitn.it/composes/sick.html}
+\item Conneau and Kiela, 2018 \textbf{SentEval: An Evaluation Toolkit for Universal Sentence Representations}  
+	\begin{itemize}
+		\item \textrm{https://arxiv.org/abs/1803.05449}
+	\end{itemize}
+\end{itemize}
+\end{document}
\ No newline at end of file