93 citations · 267 across the 26 of their papers we have counts for
31 papers
Complementary Time- and Distance-Based Methods for Cosmogenic Li/He Background Estimation
Cailian Jiang, Qishan Liu, Liangjian Wen +4
Cosmogenic Li and He isotopes constitute an important correlated background in low-energy neutrino experiments because their -delayed neutron decay signatures can mi…
CroissantLLM: A Truly Bilingual French-English Language Model
Manuel Faysse, Patrick Fernandes, Nuno M. Guerreiro +13
We introduce CroissantLLM, a 1.3B language model pretrained on a set of 3T English and French tokens, to bring to the research and industrial community a high-performance, fully op…
Structural generalization in COGS: Supertagging is (almost) all you need
Alban Petit, Caio Corro, François Yvon
In many Natural Language Processing applications, neural networks have been found to fail to generalize on out-of-distribution examples. In particular, several recent semantic pars…
Towards Example-Based NMT with Multi-Levenshtein Transformers
Maxime Bouthors, Josep Crego, François Yvon
Retrieval-Augmented Machine Translation (RAMT) is attracting growing attention. This is because RAMT not only improves translation metrics, but is also assumed to implement some fo…
GlotLID: Language Identification for Low-Resource Languages
Amir Hossein Kargaran, Ayyoob Imani, François Yvon +1
Several recent papers have published good solutions for language identification (LID) for about 300 high-resource and medium-resource languages. However, there is no LID available…
GlotScript: A Resource and Tool for Low Resource Writing System Identification
Amir Hossein Kargaran, François Yvon, Hinrich Schütze
We present GlotScript, an open resource and tool for low resource writing system identification. GlotScript-R is a resource that provides the attested writing systems for more than…
BiSync: A Bilingual Editor for Synchronized Monolingual Texts
Josep Crego, Jitao Xu, François Yvon
In our globalized world, a growing number of situations arise where people are required to communicate in one or several foreign languages. In the case of written communication, us…
Assessing Word Importance Using Models Trained for Semantic Tasks
Dávid Javorský, Ondřej Bojar, François Yvon
Many NLP tasks require to automatically identify the most significant words in a text. In this work, we derive word significance from models trained to solve semantic task: Natural…
Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages
Ayyoob Imani, Peiqin Lin, Amir Hossein Kargaran +8
The NLP community has mainly focused on scaling Large Language Models (LLMs) vertically, i.e., making them better for about 100 languages. We instead scale LLMs horizontally: we cr…
On the analysis of Rayleigh-Bénard convection using Latent Dirichlet Allocation
Bérengère Podvin, Laurent Soucasse, François Yvon
We apply a probabilistic clustering method, Latent Dirichlet Allocation (LDA), to characterize the largescale dynamics of Rayleigh-Bénard convection. The method, introduced in Frih…
Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM
Rachel Bawden, François Yvon
The NLP community recently saw the release of a new large open-access multilingual language model, BLOOM (BigScience et al., 2022) covering 46 languages. We focus on BLOOM's multil…
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
BigScience Workshop, :, Teven Le Scao +391
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to wi…
Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging
Ayyoob Imani, Silvia Severini, Masoud Jalili Sabet +2
Part-of-Speech (POS) tagging is an important component of the NLP pipeline, but many low-resource languages lack labeled data for training. An established method for training a POS…
Bilingual Synchronization: Restoring Translational Relationships with Editing Operations
Jitao Xu, Josep Crego, François Yvon
Machine Translation (MT) is usually viewed as a one-shot process that generates the target language equivalent of some source text from scratch. We consider here a more general set…
Evaluating Subtitle Segmentation for End-to-end Generation Systems
Alina Karakanta, François Buet, Mauro Cettolo +1
Subtitles appear on screen as short pieces of text, segmented based on formal constraints (length) and syntactic/semantic criteria. Subtitle segmentation can be evaluated with sequ…
Graph Neural Networks for Multiparallel Word Alignment
Ayyoob Imani, Lütfi Kerem Şenel, Masoud Jalili Sabet +2
After a period of decrease, interest in word alignments is increasing again for their usefulness in domains such as typological research, cross-lingual annotation projection, and m…
Screening Gender Transfer in Neural Machine Translation
Guillaume Wisniewski, Lichao Zhu, Nicolas Ballier +1
This paper aims at identifying the information flow in state-of-the-art machine translation systems, taking as example the transfer of gender when translating from French into Engl…
One Source, Two Targets: Challenges and Rewards of Dual Decoding
Jitao Xu, François Yvon
Machine translation is generally understood as generating one target text from an input source document. In this paper, we consider a stronger requirement: to jointly generate two…
Graph Algorithms for Multiparallel Word Alignment
Ayyoob Imani, Masoud Jalili Sabet, Lütfi Kerem Şenel +3
With the advent of end-to-end deep learning approaches in machine translation, interest in word alignments initially decreased; however, they have again become a focus of research…
Can You Traducir This? Machine Translation for Code-Switched Input
Jitao Xu, François Yvon
Code-Switching (CSW) is a common phenomenon that occurs in multilingual geographic or social contexts, which raises challenging problems for natural language processing tools. We f…
Generative latent neural models for automatic word alignment
Anh Khoa Ngo Ho, François Yvon
Word alignments identify translational correspondences between words in a parallel sentence pair and are used, for instance, to learn bilingual dictionaries, to train statistical m…
Neural Baselines for Word Alignment
Anh Khoa Ngo Ho, François Yvon
Word alignments identify translational correspondences between words in a parallel sentence pair and is used, for instance, to learn bilingual dictionaries, to train statistical ma…
The European Language Technology Landscape in 2020: Language-Centric and Human-Centric AI for Cross-Cultural Communication in Multilingual Europe
Georg Rehm, Katrin Marheinecke, Stefanie Hegele +44
Multilingualism is a cultural cornerstone of Europe and firmly anchored in the European treaties including full language equality. However, language barriers impacting business, cr…
Controlling Utterance Length in NMT-based Word Segmentation with Attention
Pierre Godard, Laurent Besacier, Francois Yvon
One of the basic tasks of computational language documentation (CLD) is to identify word boundaries in an unsegmented phonemic stream. While several unsupervised monolingual word s…