[prev in list] [next in list] [prev in thread] [next in thread]
List: haskell-cafe
Subject: [Haskell-cafe] Haskell language model
From: Jorrit Willaert <jorrit.willaert () student ! kuleuven ! be>
Date: 2022-10-19 15:08:42
Message-ID: HE1PR0801MB189826B1A5D5CDAFD3A440B3A12B9 () HE1PR0801MB1898 ! eurprd08 ! prod ! outlook ! com
[Download RAW message or body]
[Attachment #2 (multipart/alternative)]
Dear all,
For my thesis, I will try to offer Haskell coding assignments for a course =
in a more dynamic way, where the next assignment is based on the knowledge =
gap of the learner. For this, I will use a neural network, which will have =
to process a submission of a learner. Therefore, I want to use a language m=
odel that extracts features from the submission.
I was planning to use BERT in a first phase, since this model creates embed=
dings from a document. However, this model is not trained on any programmin=
g language, so this may turn out to be insufficient. Moreover, models such =
as CodeBERT are trained on source code, but only on very well known program=
ming languages.
I was wondering if someone had an idea if there already exists a language m=
odel that can create meaningful representations for Haskell. More general m=
odels such as Codex (paying API) or GPT-Code-Clippy (free and opensource) c=
ould also be tried out, but if there exists a model that has been trained o=
n Haskell specific data, that would of course be the most beneficial option=
.
If you want to read more about my thesis, you can read more about it in the=
attachment.
Thanks in advance!
Kind regards,
Jorrit Willaert
https://www.linkedin.com/in/jorrit-willaert-166a64198/
https://github.com/JorritWillaert
[Attachment #5 (text/html)]
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} \
</style> </head>
<body dir="ltr">
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; \
color: rgb(0, 0, 0);" class="elementToProof"> <br>
</div>
<span class="x_elementToProof" \
style="font-size:12pt;margin:0px;background-color:rgb(255, 255, 255)"><span \
class="x_x_elementToProof x_ContentPasted0 ContentPasted0" \
style="margin:0px;background-color:rgb(255, 255, 255)">Dear all,</span></span> <div \
class="x_elementToProof" style="font-size:12pt;margin:0px;background-color:rgb(255, \
255, 255)"> <div class="x_x_elementToProof" \
style="margin:0px;background-color:rgb(255, 255, 255)"> <br class="x_ContentPasted0 \
ContentPasted0"> </div>
<div class="x_x_elementToProof x_ContentPasted0 ContentPasted0" \
style="margin:0px;background-color:rgb(255, 255, 255)"> For my thesis, I will try to \
offer Haskell coding assignments for a course in a more dynamic way, where the \
next assignment is based on the knowledge gap of the learner. For this, I will use a \
neural network, which will have to process a submission of a learner. Therefore, I \
want to use a language model that extracts features from the submission. </div> \
<div class="x_x_elementToProof x_ContentPasted0 ContentPasted0" \
style="margin:0px;background-color:rgb(255, 255, 255)"> I was planning to use BERT in \
a first phase, since this model creates embeddings from a document. However, this \
model is not trained on any programming language, so this may turn out to be \
insufficient. Moreover, models such as CodeBERT are trained on source code, but only \
on very well known programming languages.</div> <div class="x_x_elementToProof" \
style="margin:0px;background-color:rgb(255, 255, 255)"> <br class="x_ContentPasted0 \
ContentPasted0"> </div>
<div class="x_x_elementToProof x_ContentPasted0 ContentPasted0" \
style="margin:0px;background-color:rgb(255, 255, 255)"> I was wondering if someone \
had an idea if there already exists a language model that can create meaningful \
representations for Haskell. More general models such as Codex (paying API) or \
GPT-Code-Clippy (free and opensource) could also be tried out, but if there exists a \
model that has been trained on Haskell specific data, that would of course be the \
most beneficial option.</div> <div class="x_x_elementToProof" \
style="margin:0px;background-color:rgb(255, 255, 255)"> <span style="margin:0px"><br \
class="x_ContentPasted0 ContentPasted0"> </span></div>
<div class="x_x_elementToProof" style="margin:0px;background-color:rgb(255, 255, \
255)"> <span class="x_ContentPasted0 ContentPasted0" style="margin:0px">If you want \
to read more about my thesis, you can read more about it in the attachment.</span><br \
class="x_ContentPasted0 ContentPasted0"> </div>
<div class="x_x_elementToProof" style="margin:0px;background-color:rgb(255, 255, \
255)"> <span style="margin:0px"><br class="x_ContentPasted0 ContentPasted0">
</span></div>
<div class="x_x_elementToProof" style="margin:0px;background-color:rgb(255, 255, \
255)"> <span class="x_ContentPasted0 ContentPasted0" style="margin:0px">Thanks \
in advance!</span></div> <div class="x_x_elementToProof" \
style="margin:0px;background-color:rgb(255, 255, 255)"> <br class="x_ContentPasted0 \
ContentPasted0"> </div>
<div class="x_x_elementToProof x_ContentPasted0 ContentPasted0" \
style="margin:0px;background-color:rgb(255, 255, 255)"> Kind regards,</div>
<div class="x_x_elementToProof x_ContentPasted0 ContentPasted0" \
style="margin:0px;background-color:rgb(255, 255, 255)"> Jorrit Willaert<br \
class="x_ContentPasted0 ContentPasted0"> </div>
<div class="x_x_elementToProof x_x_ContentPasted0" \
style="margin:0px;background-color:rgb(255, 255, 255)"> <a \
href="https://www.linkedin.com/in/jorrit-willaert-166a64198/" target="_blank" \
rel="noopener noreferrer" data-auth="NotApplicable" data-safelink="true" \
data-linkindex="0" class="x_ContentPasted0 ContentPasted0" \
style="margin:0px">https://www.linkedin.com/in/jorrit-willaert-166a64198/</a><br \
class="x_ContentPasted0 ContentPasted0"> </div>
</div>
<span class="x_elementToProof" \
style="font-size:12pt;margin:0px;background-color:rgb(255, 255, 255)"><span \
class="x_x_elementToProof x_x_ContentPasted0 x_x_ContentPasted1" \
style="margin:0px;background-color:rgb(255, 255, 255)"><a \
href="https://github.com/JorritWillaert" target="_blank" rel="noopener noreferrer" \
data-auth="NotApplicable" data-safelink="true" data-linkindex="1" \
class="x_ContentPasted0 ContentPasted0" \
style="margin:0px">https://github.com/JorritWillaert</a></span></span> <div \
class="elementToProof"> <div id="Signature">
<div>
<div name="divtagdefaultwrapper" \
style="font-family:Calibri,Arial,Helvetica,sans-serif; font-size:; margin:0"> \
<div></div> </div>
</div>
</div>
</div>
</body>
</html>
["masterproef.pdf" (application/pdf)]
[Attachment #7 (text/plain)]
_______________________________________________
Haskell-Cafe mailing list
To (un)subscribe, modify options or view archives go to:
http://mail.haskell.org/cgi-bin/mailman/listinfo/haskell-cafe
Only members subscribed via the mailman list are allowed to post.
[prev in list] [next in list] [prev in thread] [next in thread]
Configure |
About |
News |
Add a list |
Sponsored by KoreLogic