Add TM summarization

src/year2/big-data-analytics-and-text-mining/metadata.json

@@ -0,0 +1,15 @@
+{
+    "name": "Big Data Analytics and Text Mining",
+    "year": 2,
+    "semester": 1,
+    "pdfs": [
+        {
+            "name": "Text mining",
+            "path": "module1/tm.pdf"
+        },
+        {
+            "name": "Big data analytics",
+            "path": "module2/bda.pdf"
+        }
+    ]
+}

src/year2/big-data-analytics-and-text-mining/module1/ainotes.cls

@@ -0,0 +1 @@
+../../../ainotes.cls

src/year2/big-data-analytics-and-text-mining/module1/sections/_summarization.tex

@@ -0,0 +1,138 @@
+\chapter{Automatic text summarization}
+
+\begin{description}
+    \item[Extractive summarization] \marginnote{Extractive summarization}
+        Select fragments of text.
+
+    \item[Abstractive summarization] \marginnote{Abstractive summarization}
+        Rephrase the content of the text.
+
+    \item[Hybrid summarization] \marginnote{Hybrid summarization}
+        Apply an extractive method followed by an abstractive one.
+\end{description}
+
+
+\begin{description}
+    \item[Generic vs query-focused] \phantom{}
+        \begin{description}
+            \item[Generic]
+                Summary of the whole document.
+            \item[Query-focused]
+                Summary that replies to given questions
+        \end{description}
+
+    \item[Technical vs lay] \phantom{}
+        \begin{description}
+            \item[Technical]
+                Summary using scientific language.
+            \item[Lay]
+                Summary using common language.
+        \end{description}
+
+    \item[Narrative vs bullet point] \phantom{}
+        \begin{description}
+            \item[Narrative]
+                Standard textual summary.
+            \item[Bullet point]
+                Set of key phrases.
+        \end{description}
+
+    \item[Single document vs multi document] \phantom{}
+        \begin{description}
+            \item[Single document]
+                Summary covering a single document.
+            \item[Multi document]
+                Summary covering multiple documents.
+        \end{description}
+
+    \item[Short document vs long document] \phantom{}
+        \begin{description}
+            \item[Short document]
+                Summary of a document with a few tokens.
+            \item[Long document]
+                Summary of a document with many tokens.
+        \end{description}
+\end{description}
+
+
+
+\section{Metrics}
+
+Summarization metrics can evaluate different levels:
+\begin{descriptionlist}
+    \item[Syntactic] 
+        Check word overlapping (e.g., ROUGE). 
+    \item[Semantic] 
+        Check semantic coverage (e.g., BERTScore). 
+    \item[Factuality] 
+        Check factuality to the source (e.g., BARTScore).
+    \item[Fluency] 
+        Check for redundancies (e.g., unique N-gram ratio).
+    \item[Efficiency] 
+        Measure trade-off between performance and costs (e.g., CARBURACY). 
+\end{descriptionlist}
+
+
+\subsection{Recall-Oriented Understudy for Gisting Evaluation (ROUGE)}
+
+\begin{description}
+    \item[ROUGE] \marginnote{ROUGE}
+        N-gram oriented metric that compares the generated summary and the ground truth.
+
+        \begin{description}
+            \item[ROUGE-1] Overlap of 1-grams.
+            \item[ROUGE-2] Overlap of 2-grams.
+            \item[ROUGE-L] Length of the common longest subsequence.
+        \end{description}
+\end{description}
+
+
+\begin{description}
+    \item[Precision] 
+        \[ \texttt{ROUGE}_\texttt{precision} = \frac{\vert \text{overlaps} \vert}{\vert \text{generated summary} \vert} \]
+
+    \item[Recall] 
+        \[ \texttt{ROUGE}_\texttt{recall} = \frac{\vert \text{overlaps} \vert}{\vert \text{ground truth} \vert} \]
+\end{description}
+
+
+\subsection{Limitations}
+
+\begin{itemize}
+    \item ROUGE only evaluates on a syntactic level.
+    \item ROUGE-2 and ROUGE-L are sensitive to the position of words.
+\end{itemize}
+
+
+
+\section{State-of-the-art generative summarizers}
+
+\subsection{BART}
+
+\begin{itemize}
+    \item \marginnote{BART} 
+        Encoder-decoder Transformer with an input size of 1024 tokens.
+    \item It is suited for short document summarization.
+    \item It is pre-trained using a denoising sequence-to-sequence approach.
+\end{itemize}
+
+
+\subsection{Longformer encoder-decoder} 
+
+\begin{itemize}
+    \item \marginnote{Longformer encoder-decoder}
+        Encoder-decoder Transformer with an input size of 16k tokens.
+    \item It is suited for long document summarization.
+    \item It uses a linear encoder self-attention based on global and local attention that reduces the quadratic complexity of the standard attention mechanism.
+\end{itemize}
+
+
+\subsection{PRIMERA}
+
+\begin{itemize}
+    \item \marginnote{PRIMERA}
+        Encoder-decoder Transformer based on Longformer with an input size of 4K tokens.
+    \item It is suited for long document summarization.
+    \item It has an ad-hoc pre-training for multi document summarization.
+\end{itemize}
+

src/year2/big-data-analytics-and-text-mining/module1/tm.tex

@@ -0,0 +1,13 @@
+\documentclass[11pt]{ainotes}
+
+\title{Big Data Analytics and Text Mining\\(Module 1)}
+\date{2024 -- 2025}
+\def\lastupdate{{PLACEHOLDER-LAST-UPDATE}}
+\def\giturl{{PLACEHOLDER-GIT-URL}}
+
+\begin{document}
+
+    \makenotesfront
+    \input{./sections/_summarization.tex}
+
+\end{document}

src/year2/big-data-analytics-and-text-mining/module2/ainotes.cls

@@ -0,0 +1 @@
+../../../ainotes.cls

src/year2/big-data-analytics-and-text-mining/module2/bda.tex

@@ -0,0 +1,12 @@
+\documentclass[11pt]{ainotes}
+
+\title{Big Data Analytics and Text Mining\\(Module 2)}
+\date{2024 -- 2025}
+\def\lastupdate{{PLACEHOLDER-LAST-UPDATE}}
+\def\giturl{{PLACEHOLDER-GIT-URL}}
+
+\begin{document}
+
+    \makenotesfront
+
+\end{document}