{"id":4263,"date":"2026-01-28T13:26:29","date_gmt":"2026-01-28T12:26:29","guid":{"rendered":"https:\/\/u-paris.fr\/linguistique\/?page_id=4263"},"modified":"2026-07-03T16:06:15","modified_gmt":"2026-07-03T14:06:15","slug":"m1s1-machine-learning-for-nlp","status":"publish","type":"page","link":"https:\/\/u-paris.fr\/linguistique\/en\/m1s1-machine-learning-for-nlp\/","title":{"rendered":"Machine Learning for NLP: the Fundamentals (Master S1 CLass)"},"content":{"rendered":"<p>[et_pb_section fb_built=\u00a0\u00bb1&Prime; _builder_version=\u00a0\u00bb3.22.1&Prime;][et_pb_row _builder_version=\u00a0\u00bb3.22.1&Prime;][et_pb_column type=\u00a0\u00bb4_4&Prime; _builder_version=\u00a0\u00bb3.22.1&Prime;][et_pb_post_title meta=\u00a0\u00bboff\u00a0\u00bb _builder_version=\u00a0\u00bb3.22.1&Prime;][\/et_pb_post_title][et_pb_text _builder_version=\u00a0\u00bb3.22.1&Prime;]<\/p>\n<h4>Basic information<\/h4>\n<ul>\n<li>Credits: 6<\/li>\n<li>Format: 4 hours weekly<\/li>\n<li>2026-2027 instructors: <a href=\"http:\/\/www.llf.cnrs.fr\/fr\/Gens\/Candito\" target=\"_blank\" rel=\"noopener noreferrer\">Marie Candito<\/a><\/li>\n<li>2026-2027 schedule: Tuesdays 09:00-11:00 and 11:15-13:15, room 234C (Halle aux farines)<\/li>\n<li><a href=\"https:\/\/moodle.u-pariscite.fr\/course\/view.php?id=7666\" target=\"_blank\" rel=\"noopener noreferrer\">Moodle page<\/a><\/li>\n<\/ul>\n<h4>Description<\/h4>\n<p>The course provides the fundamental concepts of supervised classification via deep learning methods, with typical examples in NLP. It will cover:<\/p>\n<ul>\n<li>linear and log-linear models, linear separability and kernel methods<\/li>\n<li>multi-layer perceptrons, non-linearities, universal approximation theorem<\/li>\n<li>learning as loss minimization, stochastic gradient descent and variants, backpropagation algorithm<\/li>\n<li>word embeddings as dense features, word embeddings&rsquo; learning<\/li>\n<li>overview of metrics and methodology in supervised machine learning<br \/>Depending on progress, we will touch upon how these concepts are used within large language models, thanks to self-supervised learning and the language modeling training objective.<\/li>\n<\/ul>\n<h4>Prerequisites<\/h4>\n<p>Programming skills in python. Basic linear algebra (dot product, matrix product), basic probability theory (chain rule of probability).<\/p>\n<h4>Learning outcomes<\/h4>\n<p>On successful completion of this course, students should be able to:<\/p>\n<ul>\n<li>master the fundamental concepts of machine learning;<\/li>\n<li>understand and design supervised classifiers of various types;<\/li>\n<li>master operations on tensors;<\/li>\n<li>get basic proficiency in some of the most vastly used python machine learning libraries (sklearn and pytorch);<\/li>\n<li>get a first broad picture of how supervised learning is applied within (large) language models, thanks to the notion of self-supervision and the language modeling training objective.<\/li>\n<\/ul>\n<p>[\/et_pb_text][\/et_pb_column][\/et_pb_row][\/et_pb_section]<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Basic information Credits: 6 Format: 4 hours weekly 2026-2027 instructors: Marie Candito 2026-2027 schedule: Tuesdays 09:00-11:00 and 11:15-13:15, room 234C (Halle aux farines) Moodle page Description The course provides the fundamental concepts of supervised classification via deep learning methods, with typical examples in NLP. It will cover: linear and log-linear models, linear separability and kernel&hellip; <a class=\"continue\" href=\"https:\/\/u-paris.fr\/linguistique\/en\/m1s1-machine-learning-for-nlp\/\">Lire la suite<span> Machine Learning for NLP: the Fundamentals (Master S1 CLass)<\/span><\/a><\/p>\n","protected":false},"author":609,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_et_pb_use_builder":"on","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"coauthors":[114],"class_list":["post-4263","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/u-paris.fr\/linguistique\/wp-json\/wp\/v2\/pages\/4263","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/u-paris.fr\/linguistique\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/u-paris.fr\/linguistique\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/u-paris.fr\/linguistique\/wp-json\/wp\/v2\/users\/609"}],"replies":[{"embeddable":true,"href":"https:\/\/u-paris.fr\/linguistique\/wp-json\/wp\/v2\/comments?post=4263"}],"version-history":[{"count":4,"href":"https:\/\/u-paris.fr\/linguistique\/wp-json\/wp\/v2\/pages\/4263\/revisions"}],"predecessor-version":[{"id":6870,"href":"https:\/\/u-paris.fr\/linguistique\/wp-json\/wp\/v2\/pages\/4263\/revisions\/6870"}],"wp:attachment":[{"href":"https:\/\/u-paris.fr\/linguistique\/wp-json\/wp\/v2\/media?parent=4263"}],"wp:term":[{"taxonomy":"author","embeddable":true,"href":"https:\/\/u-paris.fr\/linguistique\/wp-json\/wp\/v2\/coauthors?post=4263"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}