last year's lecture material moved to directory 2025

2026-03-30 07:43:08 +02:00
parent 088f52a0f6
commit 9d0f650881
39 changed files with 0 additions and 0 deletions
--- a/lectures/2025/lecture-n-1/.gitignore
+++ b/lectures/2025/lecture-n-1/.gitignore
@@ -0,0 +1,94 @@
+## Core latex/pdflatex auxiliary files:
+*.aux
+*.lof
+*.log
+*.lot
+*.fls
+*.out
+*.toc
+
+## Intermediate documents:
+*.dvi
+# these rules might exclude image files for figures etc.
+# *.ps
+# *.eps
+# *.pdf
+
+## Bibliography auxiliary files (bibtex/biblatex/biber):
+*.bbl
+*.bcf
+*.blg
+*-blx.aux
+*-blx.bib
+*.run.xml
+
+## Build tool auxiliary files:
+*.fdb_latexmk
+*.synctex.gz
+*.synctex.gz(busy)
+*.pdfsync
+
+## Auxiliary and intermediate files from other packages:
+
+# algorithms
+*.alg
+*.loa
+
+# amsthm
+*.thm
+
+# beamer
+*.nav
+*.snm
+*.vrb
+
+# glossaries
+*.acn
+*.acr
+*.glg
+*.glo
+*.gls
+
+# hyperref
+*.brf
+
+# listings
+*.lol
+
+# makeidx
+*.idx
+*.ilg
+*.ind
+*.ist
+
+# minitoc
+*.maf
+*.mtc
+*.mtc0
+
+# minted
+*.pyg
+
+# nomencl
+*.nlo
+
+# sagetex
+*.sagetex.sage
+*.sagetex.py
+*.sagetex.scmd
+
+# sympy
+*.sout
+*.sympy
+sympy-plots-for-*.tex/
+
+# todonotes
+*.tdo
+
+# xindy
+*.xdy
+
+# useless files
+color_scheme.png
+identicon.png
+._wordcount_selection.tex
--- a/lectures/2025/lecture-n-1/beamerthemelucid.sty
+++ b/lectures/2025/lecture-n-1/beamerthemelucid.sty
@@ -0,0 +1,187 @@
+\usepackage{tikz}
+\usetikzlibrary{calc}
+
+% -------- COLOR SCHEME --------
+\definecolor{PrimaryColor}{RGB}{7,79,140} % primary color (blue)
+\definecolor{SecondaryColor}{RGB}{242,88,26} % bulleted lists
+\definecolor{BackgroundColor}{RGB}{255,255,255} % background & titles (white)
+\definecolor{TextColor}{RGB}{0,0,0} % text (black)
+\definecolor{ProgBarBGColor}{RGB}{175,175,175} % progress bar background (grey)
+
+
+% set colours
+\setbeamercolor{normal text}{fg=TextColor}\usebeamercolor*{normal text}
+\setbeamercolor{alerted text}{fg=PrimaryColor}
+\setbeamercolor{section in toc}{fg=PrimaryColor}
+\setbeamercolor{structure}{fg=SecondaryColor}
+\hypersetup{colorlinks,linkcolor=,urlcolor=SecondaryColor}
+
+% set fonts
+\setbeamerfont{itemize/enumerate body}{size=\large}
+\setbeamerfont{itemize/enumerate subbody}{size=\normalsize}
+\setbeamerfont{itemize/enumerate subsubbody}{size=\small}
+
+% make pixelated bullets
+\setbeamertemplate{itemize item}{
+	\tikz{
+		\draw[fill=SecondaryColor,draw=none] (0, 0) rectangle(0.1, 0.1);
+		\draw[fill=SecondaryColor,draw=none] (0.1, 0.1) rectangle(0.2, 0.2);
+		\draw[fill=SecondaryColor,draw=none] (0, 0.2) rectangle(0.1, 0.3);
+	}
+}
+\setbeamertemplate{itemize subitem}{
+	\tikz{
+		\draw[fill=SecondaryColor,draw=none] (0, 0) rectangle(0.075, 0.075);
+		\draw[fill=SecondaryColor,draw=none] (0.075, 0.075) rectangle(0.15, 0.15);
+		\draw[fill=SecondaryColor,draw=none] (0, 0.15) rectangle(0.075, 0.225);
+	}
+}
+\setbeamertemplate{itemize subsubitem}{
+	\tikz{
+		\draw[fill=SecondaryColor,draw=none] (0.050, 0.050) rectangle(0.15, 0.15);
+	}
+}
+
+% disable navigation
+\setbeamertemplate{navigation symbols}{}
+
+% disable the damn default logo!
+\setbeamertemplate{sidebar right}{}
+
+% custom draw the title page above
+\setbeamertemplate{title page}{}
+
+% again, manually draw the frame title above
+\setbeamertemplate{frametitle}{}
+
+% disable "Figure:" in the captions
+% TODO: somehow this doesn't work for md-generated slides
+%\setbeamertemplate{caption}{\tiny\insertcaption}
+%\setbeamertemplate{caption label separator}{}
+
+% add some space below the footnotes so they don't end up on the progress bar
+\setbeamertemplate{footnote}{ 
+	\parindent 0em
+	\noindent 
+	\raggedright 
+	\hbox to 0.8em{\hfil\insertfootnotemark}
+	\insertfootnotetext
+	\par
+	\vspace{2em}
+}
+
+% add the same vspace both before and after quotes 
+\setbeamertemplate{quote begin}{\vspace{0.5em}}
+\setbeamertemplate{quote end}{\vspace{0.5em}}
+
+% progress bar counters
+\newcounter{showProgressBar}
+\setcounter{showProgressBar}{1}
+\newcounter{showSlideNumbers}
+\setcounter{showSlideNumbers}{1}
+\newcounter{showSlideTotal}
+\setcounter{showSlideTotal}{1}
+
+% use \makeatletter for our progress bar definitions
+% progress bar idea from http://tex.stackexchange.com/a/59749/44221
+% slightly adapted for visual purposes here
+\makeatletter
+\newcount\progressbar@tmpcounta% auxiliary counter
+\newcount\progressbar@tmpcountb% auxiliary counter
+\newdimen\progressbar@pbwidth %progressbar width
+\newdimen\progressbar@tmpdim % auxiliary dimension
+
+\newdimen\slidewidth % auxiliary dimension
+\newdimen\slideheight % auxiliary dimension
+
+% make the progress bar go across the screen
+\progressbar@pbwidth=\the\paperwidth
+\slidewidth=\the\paperwidth
+\slideheight=\the\paperheight
+
+% draw everything with tikz
+\setbeamertemplate{background}{ % all slides
+	% progress bar stuff
+	\progressbar@tmpcounta=\insertframenumber
+	\progressbar@tmpcountb=\inserttotalframenumber
+	\progressbar@tmpdim=\progressbar@pbwidth
+	\divide\progressbar@tmpdim by 100
+	\multiply\progressbar@tmpdim by \progressbar@tmpcounta
+	\divide\progressbar@tmpdim by \progressbar@tmpcountb
+	\multiply\progressbar@tmpdim by 100
+
+	\begin{tikzpicture}
+		% set up the entire slide as the canvas
+		\useasboundingbox (0,0) rectangle(\the\paperwidth,\the\paperheight);
+
+		% background
+		\fill[color=BackgroundColor] (0,0) rectangle(\the\paperwidth,\the\paperheight);
+
+		\ifnum\thepage=1\relax % only title slides
+			% primary color rectangle
+			\fill[color=PrimaryColor] (0, 4cm) rectangle(\slidewidth,\slideheight);
+
+			% text (title, subtitle, author, date)
+			\node[anchor=south,text width=\slidewidth-1cm,inner xsep=0.5cm] at (0.5\slidewidth,4cm) {\color{BackgroundColor}\Huge\textbf{\inserttitle}};
+			\node[anchor=north east,text width=\slidewidth-1cm,align=right] at (\slidewidth-0.4cm,4cm) {\color{PrimaryColor}\large\textbf{\insertsubtitle}};
+			\node at (0.5\slidewidth,2cm) {\color{PrimaryColor}\LARGE\insertauthor};
+			\node at (0.5\slidewidth,1.25cm) {\color{PrimaryColor}\Large\insertinstitute};
+			\node[anchor=south east] at(\slidewidth,0cm) {\color{PrimaryColor}\tiny\insertdate};
+		\else % other slides
+			% title bar
+			\fill[color=PrimaryColor] (0, \slideheight-1cm) rectangle(\slidewidth,\slideheight);
+
+			% slide title
+			\node[anchor=north,text width=\slidewidth-0.75cm,inner xsep=0.5cm,inner ysep=0.25cm] at (0.5\slidewidth,\slideheight) {\color{BackgroundColor}\huge\textbf{\insertframetitle}};
+
+			% logo (TODO: autoscale; now it expects 350x350
+			\node[anchor=north east] at (\slidewidth-0.25cm,\slideheight+0.06cm){\insertlogo};
+
+			% show progress bar
+			\ifnum \value{showProgressBar}>0\relax%
+				% progress bar icon in the middle of the screen
+				\draw[fill=ProgBarBGColor,draw=none] (0cm,0cm) rectangle(\slidewidth,0.25cm);
+				\draw[fill=PrimaryColor,draw=none] (0cm,0cm) rectangle(\progressbar@tmpdim,0.25cm);
+
+				% bottom info
+				\node[anchor=south west] at(0cm,0.25cm) {\color{PrimaryColor}\tiny\vphantom{lp}\insertsection};
+				% if slide numbers are active
+				\ifnum \value{showSlideNumbers}>0\relax%
+					% if slide totals are active
+					\ifnum \value{showSlideTotal}>0\relax%
+						% draw both slide number and slide total
+						\node[anchor=south east] at(\slidewidth,0.25cm) {\color{PrimaryColor}\tiny\insertframenumber/\inserttotalframenumber};
+					\else
+						\node[anchor=south east] at(\slidewidth,0.25cm) {\color{PrimaryColor}\tiny\insertframenumber};
+					\fi
+				\fi
+			\else
+				% section title in the bottom left
+				\node[anchor=south west] at(0cm,0cm) {\color{PrimaryColor}\tiny\vphantom{lp}\insertsection};
+				% if we're showing slide numbers
+				\ifnum \value{showSlideNumbers}>0\relax%
+					% if slide totals are active
+					\ifnum \value{showSlideTotal}>0\relax%
+						% slide number and slide total
+						\node[anchor=south east] at(\slidewidth,0cm) {\color{PrimaryColor}\tiny\insertframenumber/\inserttotalframenumber};
+					\else
+						\node[anchor=south east] at(\slidewidth,0cm) {\color{PrimaryColor}\tiny\insertframenumber};
+					\fi
+				\fi
+			\fi
+		\fi
+	\end{tikzpicture}
+}
+\makeatother
+
+\AtBeginSection{\frame{\sectionpage}} % section pages
+\setbeamertemplate{section page}
+{
+	\begin{tikzpicture}
+		% set up the entire slide as the canvas
+		\useasboundingbox (0,0) rectangle(\slidewidth,\slideheight);
+		\fill[color=BackgroundColor] (-1cm, 2cm) rectangle (\slidewidth, \slideheight+0.1cm);
+		\fill[color=PrimaryColor] (-1cm, 0.5\slideheight-1cm) rectangle(\slidewidth, 0.5\slideheight+1cm);
+		\node[text width=\the\paperwidth-1cm,align=center] at (0.4\slidewidth, 0.5\slideheight) {\color{BackgroundColor}\Huge\textbf{\insertsection}};
+	\end{tikzpicture}
+}
--- a/lectures/2025/lecture-n-1/gu.png
+++ b/lectures/2025/lecture-n-1/gu.png
--- a/lectures/2025/lecture-n-1/img/argmining.png
+++ b/lectures/2025/lecture-n-1/img/argmining.png
--- a/lectures/2025/lecture-n-1/img/gfast.png
+++ b/lectures/2025/lecture-n-1/img/gfast.png
--- a/lectures/2025/lecture-n-1/img/machamp.png
+++ b/lectures/2025/lecture-n-1/img/machamp.png
--- a/lectures/2025/lecture-n-1/img/sets.png
+++ b/lectures/2025/lecture-n-1/img/sets.png
--- a/lectures/2025/lecture-n-1/img/sets.svg
+++ b/lectures/2025/lecture-n-1/img/sets.svg
--- a/lectures/2025/lecture-n-1/img/ud.conllu
+++ b/lectures/2025/lecture-n-1/img/ud.conllu
@@ -0,0 +1,6 @@
+1	the	the	DET	DT	Definite=Def|PronType=Art	3	det	_	TokenRange=0:3
+2	black	black	ADJ	JJ	Degree=Pos	3	amod	_	TokenRange=4:9
+3	cat	cat	NOUN	NN	Number=Sing	4	nsubj	_	TokenRange=10:13
+4	sees	see	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	0	root	_	TokenRange=14:18
+5	us	we	PRON	PRP	Case=Acc|Number=Plur|Person=1|PronType=Prs	4	obj	_	TokenRange=19:21
+6	now	now	ADV	RB	PronType=Dem	4	advmod	_	SpaceAfter=No|TokenRange=22:25
--- a/lectures/2025/lecture-n-1/img/ud.svg
+++ b/lectures/2025/lecture-n-1/img/ud.svg
@@ -0,0 +1,51 @@
+<svg width="317"
+     height="115"
+     viewBox="0 0 317 115"
+     version="1.1"
+     xmlns="http://www.w3.org/2000/svg">
+  <text x="5" y="108" font-size="16">the</text>
+  <text x="42" y="108" font-size="16">black</text>
+  <text x="97" y="108" font-size="16">cat</text>
+  <text x="143" y="108" font-size="16">sees</text>
+  <text x="189" y="108" font-size="16">us</text>
+  <text x="235" y="108" font-size="16">now</text>
+  <text x="5" y="93" font-size="10">DET</text>
+  <text x="42" y="93" font-size="10">ADJ</text>
+  <text x="97" y="93" font-size="10">NOUN</text>
+  <text x="143" y="93" font-size="10">VERB</text>
+  <text x="189" y="93" font-size="10">PRON</text>
+  <text x="235" y="93" font-size="10">ADV</text>
+  <path d="M 17 80 Q 17 47 50 47 L 72 47 Q 105 47 105 80"
+        stroke="black"
+        fill="none"/>
+  <line x1="17" y1="75" x2="17" y2="80" stroke="black"/>
+  <path d="M 17 80 14 74 20 74"/>
+  <text x="54" y="42" font-size="10">det</text>
+  <path d="M 55 80 Q 55 63 71 63 L 88 63 Q 104 63 104 80"
+        stroke="black"
+        fill="none"/>
+  <line x1="55" y1="75" x2="55" y2="80" stroke="black"/>
+  <path d="M 55 80 52 74 58 74"/>
+  <text x="71" y="58" font-size="10">amod</text>
+  <path d="M 110 80 Q 110 63 127 63 L 133 63 Q 150 63 150 80"
+        stroke="black"
+        fill="none"/>
+  <line x1="110" y1="75" x2="110" y2="80" stroke="black"/>
+  <path d="M 110 80 107 74 113 74"/>
+  <text x="119" y="58" font-size="10">nsubj</text>
+  <line x1="158" y1="20" x2="158" y2="80" stroke="black"/>
+  <path d="M 158 80 155 74 161 74"/>
+  <text x="163" y="28" font-size="10">root</text>
+  <path d="M 166 80 Q 166 63 183 63 L 189 63 Q 206 63 206 80"
+        stroke="black"
+        fill="none"/>
+  <line x1="206" y1="75" x2="206" y2="80" stroke="black"/>
+  <path d="M 206 80 203 74 209 74"/>
+  <text x="179" y="58" font-size="10">obj</text>
+  <path d="M 165 80 Q 165 47 198 47 L 220 47 Q 253 47 253 80"
+        stroke="black"
+        fill="none"/>
+  <line x1="253" y1="75" x2="253" y2="80" stroke="black"/>
+  <path d="M 253 80 250 74 256 74"/>
+  <text x="195" y="42" font-size="10">advmod</text>
+</svg>
--- a/lectures/2025/lecture-n-1/slides.md
+++ b/lectures/2025/lecture-n-1/slides.md
@@ -0,0 +1,219 @@
+---
+title: "Training and evaluating \\newline dependency parsers"
+subtitle: "(added to the course by popular demand)"
+author: "Arianna Masciolini"
+theme: "lucid"
+logo: "gu.png"
+date: "VT25"
+institute: "LT2214 Computational Syntax"
+---
+
+## Today's topic
+\bigskip \bigskip
+![](img/sets.png)
+
+# Parsing
+
+## A structured prediction task
+Sequence $\to$ structure, e.g.
+
+- natural language sentence $\to$ syntax tree
+- code $\to$ AST
+- argumentative essay $\to$ argumentative structure
+- ...
+
+## Example (argmining)
+
+> Språkbanken has better fika than CLASP: every fika, someone bakes. Sure, CLASP has a better coffee machine. On the other hand, there are more important things than coffee. In fact, most people drink tea in the afternoon.
+
+## Example (argmining)
+![](img/argmining.png)
+
+\footnotesize From "A gentle introduction to argumentation mining" (Lindahl et al., 2022)
+
+# Syntactic parsing
+
+## From sentence to tree
+From chapter 18 of _Speech and Language Processing_, (Jurafsky & Martin, January 2024 draft):
+
+> Syntactic parsing is the task of assigning a syntactic structure to a sentence
+
+- the structure is usually a _syntax tree_
+- two main classes of approaches:
+  - constituency parsing (e.g. GF)
+  - dependency parsing (e.g. UD)
+
+## Example (GF)
+```
+MicroLang> i MicroLangEng.gf 
+linking ... OK
+
+Languages: MicroLangEng
+7 msec
+MicroLang> p "the black cat sees us now"
+PredVPS (DetCN the_Det (AdjCN (PositA black_A) 
+(UseN cat_N))) (AdvVP (ComplV2 see_V2 (UsePron 
+we_Pron)) now_Adv)
+```
+
+## Example (GF)
+```haskell
+PredVPS 
+    (DetCN 
+        the_Det 
+        (AdjCN (PositA black_A) (UseN cat_N))
+    ) 
+    (AdvVP 
+        (ComplV2 see_V2 (UsePron we_Pron)) 
+        now_Adv
+    )
+```
+
+## Example (GF) 
+![](img/gfast.png)
+
+# Dependency parsing
+
+## Example (UD)
+![](img/ud.svg)
+
+\small
+```
+1	the	_	DET	_	_	3	det	_	_
+2	black	_	ADJ	_	_	3	amod	_	_
+3	cat	_	NOUN	_	_	4	nsubj	_	_
+4	sees	_	VERB	_	_	0	root	_	_
+5	us	_	PRON	_	_	4	obj	_	_
+6	now	_	ADV	_	_	4	advmod	_	_
+```
+
+## Two paradigms
+- __graph-based algorithms__: find the optimal tree from the set of all possible candidate solutions (or a subset of it)
+- __transition-based algorithms__: incrementally build a tree by solving a sequence of classification problems
+
+## Graph-based approaches
+$$\hat{t} = \underset{t \in T(s)}{argmax}\, score(s,t)$$
+
+- $t$: candidate tree
+- $\hat{t}$: predicted tree
+- $s$: input sentence
+- $T(s)$: set of candidate trees for $s$ 
+
+## Complexity
+Depends on:
+
+- choice of $T$ (upper bound: $n^{n-1}$, where $n$ is the number of words in $s$)
+- scoring function (in the __arc-factor model__, the score of a tree is the sum of the score of each edge, scored individually by a NN)
+
+
+In practice: $O(n^3)$ complexity
+
+## Transition-based approaches
+- trees are built through a sequence of steps, called _transitions_
+- training requires:
+  - a gold-standard treebank (as for graph-based approaches)
+  - an _oracle_ i.e. an algorithm that converts each tree into a a gold-standard sequence of transitions
+- much more efficient: $O(n)$
+
+## Evaluation
+2 main metrics:
+
+- __UAS__ (Unlabelled Attachment Score): what's the fraction of nodes are attached to the correct dependency head?
+- __LAS__ (Labelled Attachment Score): what's the fraction of nodes are attached to the correct dependency head _with an arc labelled with the correct relation type_[^1]?
+
+[^1]: in UD: the `DEPREL` column
+
+# Specifics of UD parsing
+
+## Not just parsing per se
+UD "parsers" typically do a lot more than dependency parsing:
+
+- sentence segmentation
+- tokenization
+- lemmatization (`LEMMA` column)
+- POS tagging (`UPOS` + `XPOS`)
+- morphological tagging (`FEATS`)
+- ...
+
+Sometimes, some of these tasks are performed __jointly__ to achieve better performance.
+
+## Evaluation (UD-specific)
+Some more specific metrics:
+
+- __CLAS__ (Content-word LAS): LAS limited to content words
+- __MLAS__ (Morphology-Aware LAS): CLAS that also uses the `FEATS` column
+- __BLEX__ (Bi-Lexical dependency score): CLAS that also uses the `LEMMA` column
+
+## Evaluation script output
+\small
+```
+Metric     | Precision |    Recall |  F1 Score | AligndAcc
+-----------+-----------+-----------+-----------+-----------
+Tokens     |    100.00 |    100.00 |    100.00 |
+Sentences  |    100.00 |    100.00 |    100.00 |
+Words      |    100.00 |    100.00 |    100.00 |
+UPOS       |     98.36 |     98.36 |     98.36 |     98.36
+XPOS       |    100.00 |    100.00 |    100.00 |    100.00
+UFeats     |    100.00 |    100.00 |    100.00 |    100.00
+AllTags    |     98.36 |     98.36 |     98.36 |     98.36
+Lemmas     |    100.00 |    100.00 |    100.00 |    100.00
+UAS        |     92.73 |     92.73 |     92.73 |     92.73
+LAS        |     90.30 |     90.30 |     90.30 |     90.30
+CLAS       |     88.50 |     88.34 |     88.42 |     88.34
+MLAS       |     86.72 |     86.56 |     86.64 |     86.56
+BLEX       |     88.50 |     88.34 |     88.42 |     88.34
+```
+
+## Three generations of parsers
+(all transition-based)
+
+1. __MaltParser__ (Nivre et al. 2006): "classic" transition-based parser, data-driven but not NN-based
+2. __UDPipe__: neural parser, personal favorite
+   - v1 (Straka et al. 2016): fast, solid software, easy to install and available anywhere
+   - v2 (Straka et al. 2018): much better results but slower and only available through an API/via the web GUI
+3. __MaChAmp__ (van der Goot et al. 2021): transformer-based toolkit for multi-task learning, works on all CoNNL-like data, close to the SOTA, relatively easy to install and train
+
+## MaChAmp config example
+```json
+{"compsyn": {
+    "train_data_path": "PATH-TO-YOUR-TRAIN-SPLIT",
+    "dev_data_path": "PATH-TO-YOUR-DEV-SPLIT",
+    "word_idx": 1,
+    "tasks": {
+        "upos": {
+            "task_type": "seq",
+            "column_idx": 3
+        },
+        "dependency": {
+            "task_type": "dependency",
+            "column_idx": 6}}}}
+```
+
+## Your task (lab 3)
+![](img/machamp.png)
+
+1. annotate a small treebank for your language of choice (started yesterday)
+2. __train a parser-tagger on a reference UD treebank__ (tomorrow, or maybe even today: installation)
+3. evaluate it on your treebank
+
+# To learn more
+
+## Main sources
+- chapters 18-19 of the January 2024 draft of _Speech and Language Processing_ (Jurafsky & Martin) (full text available [__here__](https://web.stanford.edu/~jurafsky/slp3/))
+- unit 3-2 of Johansson & Kuhlmann's course "Deep Learning for Natural Language Processing" ([__slides and videos__](https://liu-nlp.ai/dl4nlp/modules/module3/))
+- section 10.9.2 on parser evaluation from Aarne's course notes (on Canvas)
+
+## Papers describing the parsers
+- _MaltParser: A Data-Driven Parser-Generator for Dependency Parsing_ (Nivre et al. 2006) ([__PDF__](http://lrec-conf.org/proceedings/lrec2006/pdf/162_pdf.pdf))
+- _UDPipe: Trainable Pipeline for Processing CoNLL-U Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing_ (Straka et al. 2016) ([__PDF__](https://aclanthology.org/L16-1680.pdf))
+- _UDPipe 2.0 Prototype at CoNLL 2018 UD Shared Task_ (Straka et al. 2018) ([__PDF__](https://aclanthology.org/K18-2020.pdf))
+- _Massive Choice, Ample Tasks (MACHAMP): A Toolkit for Multi-task Learning in NLP_ (van der Goot et al., 2021) ([__PDF__](https://arxiv.org/pdf/2005.14672))
+
+## CSE courses you may like
+1. [DIT231](https://www.gu.se/en/study-gothenburg/programming-language-technology-dit231) Programming language technology
+   - build a complete compiler
+2. [DIT301](https://www.gu.se/en/study-gothenburg/compiler-construction-dit301) Compiler construction 
+   - the hardcore version of 1.
+   - build another compiler _and optimize it_
+3. DIT247 Machine learning for NLP (?)
+   - has a module on dependency parsing similar to the one in "Deep Learning for Natural Language Processing"
--- a/lectures/2025/lecture-n-1/slides.pdf
+++ b/lectures/2025/lecture-n-1/slides.pdf