Enriching the NArabizi Treebank: A Multifaceted Approach to Supporting an Under-Resourced Language

Autor: Arij, Riabi, Menel, Mahamdi, Djamé, Seddah

In this paper we address the scarcity of annotated data for NArabizi, a Romanized form of North African Arabic used mostly on social media, which poses challenges for Natural Language Processing (NLP). We introduce an enriched version of NArabizi Tre

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e860d21cc640045521a5f7299957bf66
http://arxiv.org/abs/2306.14866

Understanding the Impact of UGC Specificities on Translation Quality

Autor: José Carlos Rosales Núñez, Djamé Seddah, Guillaume Wisniewski

Publikováno v: Proceedings of the Seventh W-NUT workshop (colocated with EMNLP 2021)
W-NUT 2021-Seventh Workshop on Noisy User-generated Text (colocated with EMNLP 2021)
W-NUT 2021-Seventh Workshop on Noisy User-generated Text (colocated with EMNLP 2021), association for computational linguistics, Nov 2021, Punta Cana, Dominican Republic

International audience; This work takes a critical look at the evaluation of user-generated content automatic translation, the well-known specificities of which raise many challenges for MT. Our analyses show that measuring the average-case performan

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b3e286058ac3cfc7ca11ffdbe1fbd807
http://arxiv.org/abs/2110.12551

First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT

Autor: Benoît Sagot, Benjamin Muller, Djamé Seddah, Yanai Elazar

Publikováno v: EACL

Multilingual pretrained language models have demonstrated remarkable zero-shot cross-lingual transfer capabilities. Such transfer emerges by fine-tuning on a task of interest in one language and evaluating on a distinct language, not seen during the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::67ab347b687d350416d3c2e9e8aee254
https://doi.org/10.18653/v1/2021.eacl-main.189

When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual Language Models

Autor: Antonios Anastasopoulos, Djamé Seddah, Benjamin Muller, Benoît Sagot

Publikováno v: NAACL-HLT
NAACL-HLT 2021-2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
NAACL-HLT 2021-2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jun 2021, Mexico City, Mexico
Actes de la 29e Conférence sur le Traitement Automatique des Langues Naturelles. Volume 1 : conférence principale
TALN 2022-29° conférence sur le Traitement Automatique des Langues Naturelles
TALN 2022-29° conférence sur le Traitement Automatique des Langues Naturelles, Jun 2022, Avignon, France. pp.450-451

Transfer learning based on pretraining language models on a large amount of raw data has become a new norm to reach state-of-the-art performance in NLP. Still, it remains unclear how this approach should be applied for unseen languages that are not c

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::67d0f5b2fb9a1aea9118a76d68ee4fc4
http://arxiv.org/abs/2010.12858

Overview of the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies

Autor: Daniel Zeman, Gosse Bouma, Djamé Seddah

Publikováno v: STARTPAGE=151;ENDPAGE=161;TITLE=58th Annual Meeting of the Association for Computational Linguistics
University of Groningen
IWPT 2020

This overview introduces the task of parsing into enhanced universal dependencies, describes the datasets used for training and evaluation, and evaluation metrics. We outline various approaches and discuss the results of the shared task.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e80e6198a0d95916b9ea22befb863a40
https://research.rug.nl/en/publications/e958c69a-48c0-4291-80e2-736e81a1fd46