{"id":25592,"date":"2022-04-26T13:55:36","date_gmt":"2022-04-26T11:55:36","guid":{"rendered":"https:\/\/lium.univ-lemans.fr\/?p=25592"},"modified":"2022-04-26T13:54:54","modified_gmt":"2022-04-26T11:54:54","slug":"des-arbres-des-chevaliers-et-des-marionnettes%e2%80%af-apprentissages-par-transferts-pour-le-traitement-des-langues-historiques","status":"publish","type":"post","link":"https:\/\/lium.univ-lemans.fr\/en\/des-arbres-des-chevaliers-et-des-marionnettes%e2%80%af-apprentissages-par-transferts-pour-le-traitement-des-langues-historiques\/","title":{"rendered":"Des arbres, des chevaliers et des marionnettes\u202f: apprentissages par transferts pour le traitement des langues historiques"},"content":{"rendered":"

Seminar from Lo\u00efc Grobol, Assistant Professor at Universit\u00e9 Paris Nanterre<\/h2>\n

 <\/p>\n

Date:<\/strong> 29\/04\/2022
\nTime:<\/strong> 11h00
\nLocalization:<\/strong> IC2 Boardroom, online<\/a>
\nSpeaker:<\/strong> Lo\u00efc Grobol
\n <\/p>\n

Trees, knights and puppets: transfer learning for processing of historical languages <\/strong><\/p>\n

 <\/p>\n

In recent years, automatic natural language processing (NLP) has evolved extremely rapidly, with NLP systems achieving record performance for many tasks and domains. These developments are largely due to the contributions of deep learning techniques, of which the most recent and impactful are based on the use of semi-supervised pre-training on large amounts of unannotated data complemented by targeted learning (fine-tuning<\/strong>) for target tasks (Peters et al., 2018 ; Howard et Ruder, 2018 ; Devlin et al., 2019). The main advantage of these techniques is that they allow the exploitation of massive data resulting from the omnipresent digitalization of language in all its forms. However, for many applications, the existence of such data is far from self-evident – whether in poorly endowed languages (Hedderic et al., 2021) or in poorly documented domains (Ramponi et Plank, 2021).<\/p>\n

Historical languages, and in particular those representing ancient states of still existing and well-documented languages, are a particularly interesting case of this problem. Indeed, while the available data are often scarce, highly heterogeneous, and necessarily finite, their proximity to much better endowed languages makes it tempting to apply so-called transfer learning<\/strong> techniques to them: use resources (data and systems) developed for their well-endowed descendants, and use the data available for the former state to adapt<\/strong> those resources to it.<\/p>\n

In this talk, I will present work done and still in progress in the framework of the PROFITEROLE project (PRocessing Old French Instrumented TExts for the Representation Of Language Evolution), which focuses on the use of heterogeneous resources for the syntactic analysis of medieval French. Our experiments show that it is possible to exploit resources for contemporary French (and in particular contextual representations of words) to significantly improve the processing of old French states using transfer learning techniques.<\/p>\n

 
\nReferences<\/strong><\/p>\n