Multi-task learning (MTL) is a common machine learning technique that allows the model to share information across different tasks and improve the accuracy of recommendations for all of them. Many existing MTL implementations suffer from scalability issues as the training and inference performance can degrade with the increasing number of tasks, which can limit production use case scenarios for MTL-based recommender systems. Inspired by the recent advances of large language models, we developed an end-to-end efficient and scalable Generalist Recommender (GRec). GRec takes comprehensive data signals by utilizing NLP heads, parallel Transformers, as well as a wide and deep structure to process multi-modal inputs. These inputs are then combined and fed through a newly proposed task-sentence level routing mechanism to scale the model capabilities on multiple tasks without compromising performance. Offline evaluations and online experiments show that GRec significantly outperforms our previous recommender solutions. GRec has been successfully deployed on one of the largest telecom websites and apps, effectively managing high volumes of online traffic every day.

The article aims at identifying what, from a structural point of view, AI based automatic translators cannot fully capture. It focuses on the machine's mistakes, in order to try to explain its causes. The biblical story of Ca\"in and Abel has been chosen because of its rich interpretive and critical tradition, but also because of its semantic difficulty. The investigation begins with the observation, for the translation of this text, of the language pairs and interfaces offered by the best known machine translation services (Google Translate, DeepL). A typology of the most frequent translation errors is then established. Finally, contemporary translations are compared, in order to underline the unique contribution of each. In conclusion, the article suggests a revision of translation theory and, corArtificial Intelligence, Translation, Limitations, Interpretation, Comparison, Unicityelatively, a reformulation of its technology concerning cultural texts.

In recent years, many NLP studies have focused solely on performance improvement. In this work, we focus on the linguistic and scientific aspects of NLP. We use the task of generating referring expressions in context (REG-in-context) as a case study and start our analysis from GREC, a comprehensive set of shared tasks in English that addressed this topic over a decade ago. We ask what the performance of models would be if we assessed them (1) on more realistic datasets, and (2) using more advanced methods. We test the models using different evaluation metrics and feature selection experiments. We conclude that GREC can no longer be regarded as offering a reliable assessment of models' ability to mimic human reference production, because the results are highly impacted by the choice of corpus and evaluation metrics. Our results also suggest that pre-trained language models are less dependent on the choice of corpus than classic Machine Learning models, and therefore make more robust class predictions.