{"id":24479,"date":"2020-09-14T11:14:05","date_gmt":"2020-09-14T09:14:05","guid":{"rendered":"https:\/\/lium.univ-lemans.fr\/?p=24479"},"modified":"2024-02-06T13:48:32","modified_gmt":"2024-02-06T12:48:32","slug":"thibault-prouteau","status":"publish","type":"post","link":"https:\/\/lium.univ-lemans.fr\/en\/thibault-prouteau\/","title":{"rendered":"Thibault Prouteau"},"content":{"rendered":"

Temporal word embeddings: neologisms, gender bias, corpus of French news<\/h2>

Starting: <\/b> 01\/10\/2020PhD Student: <\/b> Thibault Prouteau<\/a>Advisor(s): <\/b> Sylvain MeignierCo-advisor(s): <\/b> Nicolas Dugu\u00e9 Funding: <\/b> Allocation de recherche du minist\u00e8re de l'enseignement sup\u00e9rieur<\/p><\/div><\/div><\/div><\/div>

Contexte de la th\u00e8se :<\/strong><\/p>\n

La t\u00e9l\u00e9vision, la production litt\u00e9raire et internet fournissent des traces de notre utilisation de la langue [6]. Gr\u00e2ce \u00e0 l’Ina, la m\u00e9moire de la t\u00e9l\u00e9vision perdure, et se replonger dans le pass\u00e9 nous montre \u00e0 quel point la langue \u00e9volue [9]. Avec le Web moderne, les utilisateurs ont un rapport \u00e0 l’actualit\u00e9 diff\u00e9rent : il est possible d’y r\u00e9agir en ligne, tr\u00e8s rapidement et avec une plus grande cr\u00e9ativit\u00e9 linguistique (hashtags, acronymes, etc). Internet est donc propice \u00e0 la cr\u00e9ation de nouveaux mots, ou \u00e0 l’\u00e9mergence de nouveaux sens, r\u00e9inventant ainsi chaque jour notre langue [10]. Enfin, \u00e0 travers la num\u00e9risation des contenus papiers, la production litt\u00e9raire est accessible \u00e0 tous, retra\u00e7ant l’\u00e9volution de la langue depuis le dix-neuvi\u00e8me si\u00e8cle [7].
\nAinsi, ces diff\u00e9rents m\u00e9dias permettent de constituer des corpus textuels temporels qui sont autant de ressources pour \u00e9tudier l’\u00e9volution de notre langue et de notre soci\u00e9t\u00e9.\n<\/p>\n

 
\nDescritpion<\/strong><\/p>\n

Les m\u00e9thodes de plongements<\/em> lexicaux (ou word embeddings) offrent de nouvelles possibilit\u00e9s pour l’\u00e9tude des corpus textuels [8], en particulier concernant la s\u00e9mantique du vocabulaire utilis\u00e9 dans ces corpus. \u00e0 la crois\u00e9e de l’intelligence artificielle et des humanit\u00e9s num\u00e9riques, ce projet a pour but de doter la communaut\u00e9 d’outils robustes pour concevoir des plongements lexicaux temporels interpr\u00e9tables [2] et de les appliquer dans des contextes tels que la d\u00e9tection et la caract\u00e9risation de n\u00e9ologismes sur de grands corpus textuels [4], dans le cadre de l’\u00e9volution du langage t\u00e9l\u00e9vis\u00e9 via des corpus Ina transcrits [6] ou encore pour \u00e9valuer l’\u00e9volution des st\u00e9r\u00e9otypes de genre dans le temps [1, 5, 3].<\/p>\n

 
\nBibliographie<\/strong><\/p>\n

[1] Tolga Bolukbasi, Kai-Wei Chang, James Y Zou, Venkatesh Saligrama, and Adam T Kalai. Man is to computer programmer as woman is to home-maker? debiasing word embeddings. In Advances in neural information processing systems, pages 4349-4357, 2016.
\n[2] Nicolas Dugu\u00e9 and Victor Connes. Complex networks based word embeddings. arXiv preprint arXiv:1910.01489, 2019.
\n[3] Hila Gonen and Yoav Goldberg. Lipstick on a pig: Debiasing methods cover up systematic gender biases in word embeddings but do not remove them. arXiv preprint arXiv:1903.03862, 2019.
\n[4] William L. Hamilton, Jure Leskovec, and Dan Jurafsky. Diachronic word embeddings reveal statistical laws of semantic change. arXiv:1605.09096, 2016.
\n[5] Keita Kurita, Nidhi Vyas, Ayush Pareek, Alan W Black, and Yulia Tsvetkov. Measuring bias in contextualized word representations. arXiv preprint arXiv:1906.07337, 2019.
\n[6] Jean Lagane. L’\u00e9volution du langage radiophonique. Communication & Langages, 111(1):39-52, 1997.
\n[7] Zehua Liu. A diachronic study on british and chinese cultural complexity with google books ngrams. Journal of Quantitative Linguistics, 23(4):361-373, 2016.
\n[8] Jeffrey Pennington, Richard Socher, and Christopher Manning. Glove: Global vectors for word representation. In EMNLP, pages 1532-1543, 2014.
\n[9] Jane Stuart-Smith, Gwilym Pryce, Claire Timmins, and Barrie Gunter. Television can also be a factor in language change: Evidence from an urban dialect. Language, 89(3):501-536, 2013.
\n[10] Sali A Tagliamonte et al. So sick or so cool? the language of youth on the internet. Language in Society, 45(1):1-32, 2016.\n<\/p<\/div><\/div><\/div><\/div>

 <\/div>
 <\/div>
 <\/div><\/div><\/div>","protected":false},"excerpt":{"rendered":"

Temporal word embeddings: neologisms, gender bias, corpus of French newsStarting: 01\/10\/2020PhD Student: Thibault ProuteauAdvisor(s): Sylvain MeignierCo-advisor(s): Nicolas Dugu\u00e9 Funding: Allocation de recherche du minist\u00e8re de l’enseignement sup\u00e9rieurContexte de la th\u00e8se : La t\u00e9l\u00e9vision, la production litt\u00e9raire et internet fournissent des traces de notre utilisation de la langue [6]. Gr\u00e2ce \u00e0 l’Ina, la m\u00e9moire de la […]<\/p>\n

READ MORE<\/span><\/i><\/span><\/a><\/p>\n","protected":false},"author":14,"featured_media":13249,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[52],"tags":[49],"acf":[],"_links":{"self":[{"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/posts\/24479"}],"collection":[{"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/users\/14"}],"replies":[{"embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/comments?post=24479"}],"version-history":[{"count":0,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/posts\/24479\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/media\/13249"}],"wp:attachment":[{"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/media?parent=24479"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/categories?post=24479"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/tags?post=24479"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}