no code implementations • WNUT (ACL) 2021 • Léo Jacqmin, Gabriel Marzinotto, Justyna Gromada, Ewelina Szczekocka, Robert Kołodyński, Géraldine Damnati
Following the increasing performance of neural machine translation systems, the paradigm of using automatically translated data for cross-lingual adaptation is now studied in several applicative domains.
no code implementations • JEPTALNRECITAL 2020 • Gabriel Marzinotto, Delphine Charlet, G{\'e}raldine Damnati, Fr{\'e}d{\'e}ric B{\'e}chet
Dans le cadre de la compr{\'e}hension automatique de documents, cet article propose une {\'e}valuation intrins{\`e}que et extrins{\`e}que d{'}un mod{\`e}le d{'}analyse automatique en cadres s{\'e}mantiques (Frames).
no code implementations • JEPTALNRECITAL 2020 • Gabriel Marzinotto, G{\'e}raldine Damnati, Fr{\'e}d{\'e}ric B{\'e}chet, Beno{\^\i}t Favre
Nous pr{\'e}sentons des r{\'e}sum{\'e}s en fran{\c{c}}ais et en anglais de l{'}article (Marzinotto et al., 2019) pr{\'e}sent{\'e} {\`a} la conf{\'e}rence North American Chapter of the Association for Computational Linguistics : Human Language Technologies en 2019.
no code implementations • LREC 2020 • Gabriel Marzinotto
This paper presents an approach to project FrameNet annotations into other languages using attention-based neural machine translation (NMT) models.
no code implementations • LREC 2020 • Delphine Charlet, Geraldine Damnati, Frederic Bechet, Gabriel Marzinotto, Johannes Heinecke
Machine Reading received recently a lot of attention thanks to both the availability of very large corpora such as SQuAD or MS MARCO containing triplets (document, question, answer), and the introduction of Transformer Language Models such as BERT which obtain excellent results, even matching human performance according to the SQuAD leaderboard.
no code implementations • 7 Oct 2019 • Gabriel Marzinotto, Geraldine Damnati, Frédéric Béchet
We show that adversarial learning increases all models generalization capabilities both on manual and automatic speech transcription as well as on encyclopedic data.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +6
no code implementations • SEMEVAL 2019 • Gabriel Marzinotto, Johannes Heinecke, Geraldine Damnati
Parsing is done recursively, we perform a first inference on the sentence to extract the main scenes and links and then we recursively apply our model on the sentence using a masking feature that reflects the decisions made in previous steps.
no code implementations • NAACL 2019 • Gabriel Marzinotto, Geraldine Damnati, Frédéric Béchet, Benoit Favre
This paper addresses the issue of generalization for Semantic Parsing in an adversarial framework.
no code implementations • 21 Dec 2018 • Gabriel Marzinotto, Frédéric Béchet, Géraldine Damnati, Alexis Nasr
This paper describes a Semantic Frame parsing System based on sequence labeling methods, precisely BiLSTM models with highway connections, for performing information extraction on a corpus of French encyclopedic history texts annotated according to the Berkeley FrameNet formalism.
no code implementations • LREC 2018 • Gabriel Marzinotto, Jeremy Auguste, Frederic Bechet, Géraldine Damnati, Alexis Nasr
This paper presents a publicly available corpus of French encyclopedic history texts annotated according to the Berkeley FrameNet formalism.
no code implementations • 19 Dec 2018 • Gabriel Marzinotto, Géraldine Damnati, Frederic Bechet
This article presents an automatic frame analysis system evaluated on a corpus of French encyclopedic history texts annotated according to the FrameNet formalism.
no code implementations • JEPTALNRECITAL 2017 • Gabriel Marzinotto, G{\'e}raldine Damnati, Fr{\'e}d{\'e}ric B{\'e}chet
Cet article pr{\'e}sente un syst{\`e}me d{'}analyse automatique en cadres s{\'e}mantiques {\'e}valu{\'e} sur un corpus de textes encyclop{\'e}diques d{'}histoire annot{\'e}s selon le formalisme FrameNet.