BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
BEGIN:VEVENT
UID:729@lincs.fr
DTSTART;TZID=Europe/Paris:20221108T150000
DTEND;TZID=Europe/Paris:20221108T180000
DTSTAMP:20221109T100037Z
URL:https://www.lincs.fr/events/phd-thesis-defense-analysis-and-control-of
 -online-interactions-through-neural-natural-language-processing/
SUMMARY:PhD thesis defense "Analysis and Control of Online Interactions
 through Neural Natural Language Processing"
DESCRIPTION:Natural Language Processing is motivated by applications where
 computers should gain a semantic and syntactic understanding of human
 language. Recently\, the field has been impacted by a paradigm shift. Deep
 learning architectures coupled with self-supervised training have become
 the core of state-of-the-art models used in Natural Language Understanding
 and Natural Language Generation. Sometimes considered as foundation
 models\, these systems pave the way for novel use cases. Driven by an
 academic-industrial partnership between the Institut Polytechnique de Paris
 and Google AI Research\, the present research has focused on investigating
 how pretrained neural Natural Language Processing models could be leveraged
 to improve online interactions.\n\nThis thesis first explored how
 self-supervised style transfer could be applied to the toxic-to-civil
 rephrasing of offensive comments found in online conversations. In the
 context of toxic content moderation online\, we proposed to fine-tune a
 pretrained text-to-text model (T5) with a denoising and cyclic auto-encoder
 loss.\n\nThen\, a subsequent work investigated the human labeling and
 automatic detection of toxic spans in online conversations. We released a
 new labeled dataset to train and evaluate systems\, which led to a shared
 task at the 15th International Workshop on Semantic
 Evaluation.\n\nFinally\, we developed a recommender system based on online
 reviews of items\, taking part in the topic of explaining users' tastes
 considered by the predicted recommendations. The method uses textual
 semantic similarity models to represent a user's preferences as a graph of
 textual snippets\, where the edges are defined by semantic
 similarity.\n\n&nbsp\;\nThe jury is composed as follows:\n\n\n 	Mr. Benoît
 Sagot\, Research Director\, INRIA\, France (Examiner\, President)\n 	Ms.
 Serena Villata\, Tenured Researcher\, CNRS\, France (Reviewer)\n 	Mr.
 François Yvon\, Research Director\, CNRS\, France (Reviewer)\n 	Mr. Ion
 Androutsopoulos\, Professor\, Athens University of Economics and Business\,
 Greece (Examiner)\n 	Ms. Marine Carpuat\, Assistant professor\, University
 of Maryland\, United States (Examiner)\n 	Mr. Slav Petrov\, Distinguished
 Scientist\, Google AI Research\, United States (Examiner)\n 	Mr. Thomas
 Bonald\, Professor\, Télécom Paris\, France (Ph.D. supervisor)\n 	Mr.
 Lucas Dixon\, Research scientist\, Google AI Research\, France (Ph.D.
 co-supervisor)\n
CATEGORIES:PhD Defense
LOCATION:Zoom + Amphi 4 chez Télécom-Paris\, 19 Place Marguerite Perey\,
 Palaiseau\,  91120\, France
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=19 Place Marguerite Perey\,
 Palaiseau\,  91120\, France;X-APPLE-RADIUS=100;X-TITLE=Zoom + Amphi 4 chez
 Télécom-Paris:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20221030T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR