Search Results for author:
Found 51 papers, 24 papers with code
Weakly Supervised Word Segmentation for Computational Language Documentation
Word and morpheme segmentation are fundamental steps of language documentation as they allow to discover lexical units in a language for which the lexicon is unknown.
Biais de genre dans un système de traduction automatiqueneuronale : une étude préliminaire (Gender Bias in Neural Translation : a preliminary study )
Cet article présente les premiers résultats d’une étude en cours sur les biais de genre dans les corpus d’entraînements et dans les systèmes de traduction neuronale.
Vers la production automatique de sous-titres adaptés à l’affichage (Towards automatic adapted monolingual captioning)
Une façon de réaliser un sous-titrage automatique monolingue est d’associer un système de reconnaissance de parole avec un modèle de traduction de la transcription vers les sous-titres.
Priming Neural Machine Translation
Priming is a well known and studied psychology phenomenon based on the prior presentation of one stimulus (cue) to influence the processing of a response.
A Study of Residual Adapters for Multi-Domain Neural Machine Translation
Domain adaptation is an old and vexing problem for machine translation systems.
LIMSI @ WMT 2020
This paper describes LIMSI’s submissions to the translation shared tasks at WMT’20.
Multi-Domain Adaptation in Neural Machine Translation with Dynamic Sampling Strategies
In this paper, we study dynamic data selection strategies that are able to automatically re-evaluate the usefulness of data samples and to evolve a data selection policy in the course of training.
Flux d’informations dans les systèmes encodeur-décodeur. Application à l’explication des biais de genre dans les systèmes de traduction automatique. (Information flow in encoder-decoder systems applied to the explanation of gender bias in machine translation systems)
Ce travail présente deux séries d’expériences visant à identifier les flux d’information dans les systèmes de traduction neuronaux.
Latent Group Dropout for Multilingual and Multidomain Machine Translation
Multidomain and multilingual machine translation often rely on parameter sharing strategies, where large portions of the network are meant to capture the commonalities of the tasks at hand, while smaller parts are reserved to model the peculiarities of a language or a domain.
Optimizing Word Alignments with Better Subword Tokenization
Word alignment identify translational correspondences between words in a parallel sentence pair and are used and for example and to train statistical machine translation and learn bilingual dictionaries or to perform quality estimation.
Modèle-s bayés-ien-s pour la segment-ation à deux niveau-x faible-ment super-vis-é-e (Bayesian models for weakly supervised two-level segmentation )
La segmentation automatique en mots et en morphèmes est une étape cruciale dans le processus de documentation des langues.
Ré-ordonnancement via programmation dynamique pour l’adaptation cross-lingue d’un analyseur en dépendances (Sentence reordering via dynamic programming for cross-lingual dependency parsing )
Cet article s’intéresse au transfert cross-lingue d’analyseurs en dépendances et étudie des méthodes pour limiter l’effet potentiellement néfaste pour le transfert de divergences entre l’ordre des mots dans les langues source et cible.
Generic and Specialized Word Embeddings for Multi-Domain Machine Translation
Supervised machine translation works well when the train and test data are sampled from the same distribution.
Two-Step MT: Predicting Target Morphology
This paper describes a two-step machine translation system that addresses the issue of translating into a morphologically rich language (English to Czech), by performing separately the translation and the generation of target morphology.
Investigating Length Issues in Document-level Machine Translation
Transformer architectures are increasingly effective at processing and generating very long chunks of texts, opening new perspectives for document-level machine translation (MT).
GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages
The need for large text corpora has increased with the advent of pretrained language models and, in particular, the discovery of scaling laws for these models.
MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment
This suggests that MEXA is a reliable method for estimating the multilingual capabilities of English-centric LLMs, providing a clearer understanding of their multilingual potential and the inner workings of LLMs.
How Transliterations Improve Crosslingual Alignment
However, we also show that better alignment does not always yield better downstream performance, suggesting that further research is needed to clarify the connection between alignment and performance.
Zero-Shot Machine-Generated Text Detection Using Mixture of Large Language Models
The dissemination of Large Language Models (LLMs), trained at scale, and endowed with powerful text-generating abilities has vastly increased the threats posed by generative AI technologies by reducing the cost of producing harmful, toxic, faked or forged content.
MaskLID: Code-Switching Language Identification through Iterative Masking
This method uses the LID itself to identify the features that require masking and does not rely on any external resource.
Optimizing example selection for retrieval-augmented machine translation with translation memories
Retrieval-augmented machine translation leverages examples from a translation memory by retrieving similar instances.
Lessons from the Trenches on Reproducible Evaluation of Language Models
Third, we present the Language Model Evaluation Harness (lm-eval): an open source library for independent, reproducible, and extensible evaluation of language models that seeks to address these issues.
CroissantLLM: A Truly Bilingual French-English Language Model
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 open-sourced bilingual model that runs swiftly on consumer-grade local hardware.
GlotLID: Language Identification for Low-Resource Languages
Several recent papers have published good solutions for language identification (LID) for about 300 high-resource and medium-resource languages.
Ranked #1 on
Language Identification
on GlotLID-C
Structural generalization in COGS: Supertagging is (almost) all you need
In many Natural Language Processing applications, neural networks have been found to fail to generalize on out-of-distribution examples.
Towards Example-Based NMT with Multi-Levenshtein Transformers
Retrieval-Augmented Machine Translation (RAMT) is attracting growing attention.
GlotScript: A Resource and Tool for Low Resource Writing System Identification
We present GlotScript, an open resource and tool for low resource writing system identification.
BiSync: A Bilingual Editor for Synchronized Monolingual Texts
In our globalized world, a growing number of situations arise where people are required to communicate in one or several foreign languages.
Assessing Word Importance Using Models Trained for Semantic Tasks
Many NLP tasks require to automatically identify the most significant words in a text.
Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages
The NLP community has mainly focused on scaling Large Language Models (LLMs) vertically, i. e., making them better for about 100 languages.
Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM
The NLP community recently saw the release of a new large open-access multilingual language model, BLOOM (BigScience et al., 2022) covering 46 languages.
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions.
Bilingual Synchronization: Restoring Translational Relationships with Editing Operations
Machine Translation (MT) is usually viewed as a one-shot process that generates the target language equivalent of some source text from scratch.
Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging
An established method for training a POS tagger in such a scenario is to create a labeled training set by transferring from high-resource languages.
Integrating Translation Memories into Non-Autoregressive Machine Translation
Non-autoregressive machine translation (NAT) has recently made great progress.
Evaluating Subtitle Segmentation for End-to-end Generation Systems
Subtitle segmentation can be evaluated with sequence segmentation metrics against a human reference.
Joint Generation of Captions and Subtitles with Dual Decoding
As the amount of audio-visual content increases, the need to develop automatic captioning and subtitling solutions to match the expectations of a growing international audience appears as the only viable way to boost throughput and lower the related post-production costs.
Graph Neural Networks for Multiparallel Word Alignment
First, we create a multiparallel word alignment graph, joining all bilingual word alignment pairs in one graph.
Screening Gender Transfer in Neural Machine Translation
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 English.
One Source, Two Targets: Challenges and Rewards of Dual Decoding
Machine translation is generally understood as generating one target text from an input source document.
Graph Algorithms for Multiparallel Word Alignment
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 more recently.
Can You Traducir This? Machine Translation for Code-Switched Input
Code-Switching (CSW) is a common phenomenon that occurs in multilingual geographic or social contexts, which raises challenging problems for natural language processing tools.
Generative latent neural models for automatic word alignment
Word alignments identify translational correspondences between words in a parallel sentence pair and are used, for instance, to learn bilingual dictionaries, to train statistical machine translation systems or to perform quality estimation.
Neural Baselines for Word Alignment
Word alignments identify translational correspondences between words in a parallel sentence pair and is used, for instance, to learn bilingual dictionaries, to train statistical machine translation systems , or to perform quality estimation.
SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings
We find that alignments created from embeddings are superior for four and comparable for two language pairs compared to those produced by traditional statistical aligners, even with abundant parallel data; e. g., contextualized embeddings achieve a word alignment F1 for English-German that is 5 percentage points higher than eflomal, a high-quality statistical aligner, trained on 100k parallel sentences.
The European Language Technology Landscape in 2020: Language-Centric and Human-Centric AI for Cross-Cultural Communication in Multilingual Europe
Multilingualism is a cultural cornerstone of Europe and firmly anchored in the European treaties including full language equality.
Using Monolingual Data in Neural Machine Translation: a Systematic Study
Our findings confirm that back-translation is very effective and give new explanations as to why this is the case.
Unsupervised Word Segmentation from Speech with Attention
We present a first attempt to perform attentional word segmentation directly from the speech signal, with the final goal to automatically identify lexical units in a low-resource, unwritten language (UL).
Bayesian Models for Unit Discovery on a Very Low Resource Language
Developing speech technologies for low-resource languages has become a very active research field over the last decade.
