no code implementations • ACL (WebNLG, INLG) 2020 • Yuanmin Leng, François Portet, Cyril Labbé, Raheel Qader
In this paper, we study different strategies of control in triple-totext generation systems particularly from the aspects of text structure and text length.
no code implementations • WMT (EMNLP) 2021 • Melissa Ailem, Jingshu Liu, Raheel Qader
This paper describes Lingua Custodia’s submission to the WMT21 shared task on machine translation using terminologies.
no code implementations • JEP/TALN/RECITAL 2022 • Melissa Ailem, Jingshu Liu, Raheel Qader
Empirical results show that our method improves upon related baselines in terms of both BLEU score and the percentage of generated constraint terms.
no code implementations • 26 Jan 2024 • Pau Rodriguez Inserte, Mariam Nakhlé, Raheel Qader, Gaetan Caillaut, Jingshu Liu
We show that through careful fine-tuning on both financial documents and instructions, these foundation models can be adapted to the target domain.
no code implementations • 3 Nov 2021 • Melissa Ailem, Jinghsu Liu, Raheel Qader
This paper describes Lingua Custodia's submission to the WMT21 shared task on machine translation using terminologies.
no code implementations • 19 Oct 2021 • Ali Can Kocabiyikoglu, François Portet, Raheel Qader, Jean-Marc Babouchkine
This is why the medication extraction task has emerged.
no code implementations • Findings (ACL) 2021 • Melissa Ailem, Jinghsu Liu, Raheel Qader
Intuitively, this encourages the model to learn a copy behavior when it encounters constraint terms.
no code implementations • LREC 2020 • Raheel Qader, Fran{\c{c}}ois Portet, Cyril Labbe
We present Seq2SeqPy a lightweight toolkit for sequence-to-sequence modeling that prioritizes simplicity and ability to customize the standard architectures easily.
no code implementations • WS 2019 • Kritika Mehta, Raheel Qader, Cyril Labbe, Fran{\c{c}}ois Portet
The results demonstrate that the position identifiers do constraint the neural model to respect the intended output structure which can be useful in a variety of domains that require the generated text to be in a certain structure.
no code implementations • WS 2019 • Raheel Qader, François Portet, Cyril Labbé
These findings open the way to the exploitation of non-annotated datasets which is the current bottleneck for the E2E NLG system development to new applications.
no code implementations • WS 2018 • Raheel Qader, Khoder Jneid, Fran{\c{c}}ois Portet, Cyril Labb{\'e}
In this paper we study the performance of several state-of-the-art sequence-to-sequence models applied to generation of short company descriptions.
no code implementations • JEPTALNRECITAL 2017 • Raheel Qader, Gw{\'e}nol{\'e} Lecorv{\'e}, Damien Lolive, Pascale S{\'e}billot
Cet article pr{\'e}sente un travail exploratoire sur l{'}ajout automatique de disfluences, c{'}est-{\`a}-dire de pauses, de r{\'e}p{\'e}titions et de r{\'e}visions, dans les {\'e}nonc{\'e}s en entr{\'e}e d{'}un syst{\`e}me de synth{\`e}se de la parole.
no code implementations • JEPTALNRECITAL 2016 • Raheel Qader, Gw{\'e}nol{\'e} Lecorv{\'e}, Damien Lolive, Pascale S{\'e}billot
Cet article pr{\'e}sente une nouvelle m{\'e}thode d{'}adaptation de la prononciation dont le but est de reproduire le style spontan{\'e}.