Zobrazeno 1 - 10
of 207
pro vyhledávání: '"A. Ailem"'
Benchmarks have emerged as the central approach for evaluating Large Language Models (LLMs). The research community often relies on a model's average performance across the test prompts of a benchmark to evaluate the model's performance. This is cons
Externí odkaz:
http://arxiv.org/abs/2404.16966
This paper describes Lingua Custodia's submission to the WMT21 shared task on machine translation using terminologies. We consider three directions, namely English to French, Russian, and Chinese. We rely on a Transformer-based architecture as a buil
Externí odkaz:
http://arxiv.org/abs/2111.02120
We present a new approach to encourage neural machine translation to satisfy lexical constraints. Our method acts at the training step and thereby avoiding the introduction of any extra computational overhead at inference step. The proposed method co
Externí odkaz:
http://arxiv.org/abs/2106.03730
Publikováno v:
In Bulletin de l'Académie Nationale de Médecine February 2024 208(2):163-170
Autor:
Ikhlef, M., Ailem, A.
Publikováno v:
In Journal Français d'Ophtalmologie December 2023 46(10):1182-1194
Autor:
Yueyun Ding, Tyler Simpson, Rupal Bhatt, Ana Lako, Christine Tauras, Zoe Bleicher, Timothy Consedine, Benjamin Chen, Sangeeth George, David Balli, Sharmila Chamling Rai, Ailem Schrand, Joe DeBettencourt, William J Geese, Noe Ramirez-Alejo
Publikováno v:
Journal for ImmunoTherapy of Cancer, Vol 11, Iss Suppl 1 (2023)
Externí odkaz:
https://doaj.org/article/86e21c0bb54c4ca385f87496e698f69b
Steady progress has been made in abstractive summarization with attention-based sequence-to-sequence learning models. In this paper, we propose a new decoder where the output summary is generated by conditioning on both the input text and the latent
Externí odkaz:
http://arxiv.org/abs/1908.07026
Classical approaches for approximate inference depend on cleverly designed variational distributions and bounds. Modern approaches employ amortized variational inference, which uses a neural network to approximate any posterior without leveraging the
Externí odkaz:
http://arxiv.org/abs/1906.02428
Publikováno v:
In Progress in Nuclear Energy May 2023 159
Publikováno v:
In Neurocomputing 21 July 2022 495:105-117