no code implementations • EACL (AdaptNLP) 2021 • Sara Meftah, Nasredine Semmar, Youssef Tamaazousti, Hassane Essafi, Fatiha Sadat
Transfer Learning has been shown to be a powerful tool for Natural Language Processing (NLP) and has outperformed the standard supervised learning paradigm, as it takes benefit from the pre-learned knowledge.
no code implementations • NAACL (GeBNLP) 2022 • Oussama Hansal, Ngoc Tan Le, Fatiha Sadat
One of the most common flaws is bias.
no code implementations • JEP/TALN/RECITAL 2021 • Tan Le Ngoc, Fatiha Sadat
Nous présentons des résumés en français et en anglais de l’article (Tan Le & Sadat, 2020) présenté à la 28ème conférence internationale sur les linguistiques computationnelles (the 28th International Conference on Computational Linguistics) en 2020.
no code implementations • ComputEL (ACL) 2022 • Antoine Cadotte, Tan Le Ngoc, Mathieu Boivin, Fatiha Sadat
Innu-Aimun is an Algonquian language spoken in Eastern Canada.
no code implementations • NAACL (AmericasNLP) 2021 • Ngoc Tan Le, Fatiha Sadat
Low-resource polysynthetic languages pose many challenges in NLP tasks, such as morphological analysis and Machine Translation, due to available resources and tools, and the morphologically complex languages.
no code implementations • 6 Nov 2023 • Julien Guité-Vinet, Alexandre Blondin Massé, Fatiha Sadat
In the last years, several variants of transformers have emerged.
no code implementations • 22 May 2023 • Thierno Ibrahima Cissé, Fatiha Sadat
This paper presents a spell checker and correction tool specifically designed for Wolof, an under-represented spoken language in Africa.
no code implementations • 9 Jun 2021 • Sara Meftah, Nasredine Semmar, Youssef Tamaazousti, Hassane Essafi, Fatiha Sadat
In the standard fine-tuning scheme of TL, a model is initially pre-trained on a source domain and subsequently fine-tuned on a target domain and, therefore, source and target domains are trained using the same architecture.
no code implementations • COLING 2020 • Tan Ngoc Le, Fatiha Sadat
Indigenous languages have been very challenging when dealing with NLP tasks and applications because of multiple reasons.
no code implementations • WS 2020 • Sara Meftah, Nasredine Semmar, Mohamed-Ayoub Tahiri, Youssef Tamaazousti, Hassane Essafi, Fatiha Sadat
Two prevalent transfer learning approaches are used in recent works to improve neural networks performance for domains with small amounts of annotated data: Multi-task learning which involves training the task of interest with related auxiliary tasks to exploit their underlying similarities, and Mono-task fine-tuning, where the weights of the model are initialized with the pretrained weights of a large-scale labeled source domain and then fine-tuned with labeled data of the target domain (domain of interest).
no code implementations • LREC 2020 • Billal Belainine, Fatiha Sadat, Mounir Boukadoum, Hakim Lounis
In sentiment analysis, several researchers have used emoji and hashtags as specific forms of training and supervision.
no code implementations • LREC 2020 • Pulkit Madaan, Fatiha Sadat
The technique helps achieve a jump of more than 15 points in BLEU score from the multilingual NMT model.
no code implementations • WS 2019 • Gaith Dekhili, Tan Ngoc Le, Fatiha Sadat
Commonsense can be vital in some applications like Natural Language Understanding (NLU), where it is often required to resolve ambiguity arising from implicit knowledge and underspecification.
no code implementations • JEPTALNRECITAL 2019 • Sara Meftah, Nasredine Semmar, Youssef Tamaazousti, Hassane Essafi, Fatiha Sadat
L{'}apprentissage par transfert repr{\'e}sente la capacit{\'e} qu{'}un mod{\`e}le neuronal entra{\^\i}n{\'e} sur une t{\^a}che {\`a} g{\'e}n{\'e}raliser suffisamment et correctement pour produire des r{\'e}sultats pertinents sur une autre t{\^a}che proche mais diff{\'e}rente.
no code implementations • NAACL 2019 • Sara Meftah, Youssef Tamaazousti, Nasredine Semmar, Hassane Essafi, Fatiha Sadat
Fine-tuning neural networks is widely used to transfer valuable knowledge from high-resource to low-resource domains.
Ranked #1 on Part-Of-Speech Tagging on Social media
no code implementations • 25 Dec 2018 • Salah Zaiem, Fatiha Sadat
Using sequence to sequence algorithms for query expansion has not been explored yet in Information Retrieval literature nor in Question-Answering's.
no code implementations • COLING 2018 • Sara Meftah, Nasredine Semmar, Fatiha Sadat, Stephan Raaijmakers
In this paper, we describe a morpho-syntactic tagger of tweets, an important component of the CEA List DeepLIMA tool which is a multilingual text analysis platform based on deep learning.
no code implementations • WS 2018 • Ngoc Tan Le, Fatiha Sadat
Grapheme-to-phoneme models are key components in automatic speech recognition and text-to-speech systems.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • JEPTALNRECITAL 2017 • Ngoc Tan Le, Fatiha Sadat, Lucie M{\'e}nard
Dans ce travail de recherche, nous pr{\'e}sentons une d{\'e}monstration de conversion de graph{\`e}me en phon{\`e}me pour pallier au probl{\`e}me de translitt{\'e}ration pour une paire de langues peu dot{\'e}e, avec une application sur fran{\c{c}}ais-vietnamien.
no code implementations • WS 2016 • Billal Belainine, Alexs Fonseca, ro, Fatiha Sadat
We evaluate and compare several automatic classification systems using part or all of the items described in our contributions and found that filtering by part of speech and named entity recognition dramatically increase the classification precision to 77. 3 {\%}.
no code implementations • WS 2016 • Ngoc Tan Le, Fatma Mallek, Fatiha Sadat
This paper describes our system used in the 2nd Workshop on Noisy User-generated Text (WNUT) shared task for Named Entity Recognition (NER) in Twitter, in conjunction with Coling 2016.
no code implementations • WS 2016 • Alexs Fonseca, ro, Fatiha Sadat, Fran{\c{c}}ois Lareau
For example, the antonymy is a type of relation that is represented by the lexical function Anti: Anti(big) = small.
no code implementations • JEPTALNRECITAL 2015 • Ngoc Tan Le, Fatiha Sadat
This paper focuses on an automatic construction of named entity annotated corpora for Vietnamese-French, a less-resourced pair of languages.
no code implementations • JEPTALNRECITAL 2013 • Fatiha Sadat, Emad Mohamed