AIConfPaper
← Search

Telmo Pires

4 accepted papers

2024

SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain

Pierre Colombo, Telmo Pires, Malik Boudiaf, Rui Filipe Coimbra Pereira de Melo, Gabriel Hautreux, Etienne Malaboeuf +3
NeurIPS 2024poster

In this paper, we introduce SaulLM-medium and SaulLM-large, two large language models (LLMs) families tailored for the legal sector. These models, which feature architectures of 54 billion and 140 billion parameters, respectively, are based on the Mixtral architecture. The development of SaulLM-54B…

Cited by 8Source ↗PDF ↗Scholar ↗
2023

Learning Language-Specific Layers for Multilingual Machine Translation

Telmo Pires, Robin Schmidt, Yi-Hsiu Liao, Stephan Peitz
ACL 2023long

Multilingual Machine Translation promises to improve translation quality between non-English languages. This is advantageous for several reasons, namely lower latency (no need to translate twice), and reduced error cascades (e.g., avoiding losing gender and formality information when translating thr…

Cited by 15Source ↗PDF ↗code ↗Scholar ↗
2022

End-to-End Speech Translation for Code Switched Speech

Orion Weller, Matthias Sperber, Telmo Pires, Hendra Setiawan, Christian Gollan, Dominic Telaar +1
ACL 2022findings

Code switching (CS) refers to the phenomenon of interchangeably using words and phrases from different languages. CS can pose significant accuracy challenges to NLP, due to the often monolingual nature of the underlying systems. In this work, we focus on CS in the context of English/Spanish conversa…

Cited by 28Source ↗PDF ↗code ↗Scholar ↗
2022

Non-Autoregressive Neural Machine Translation: A Call for Clarity

Robin Schmidt, Telmo Pires, Stephan Peitz, Jonas Lööf
EMNLP 2022main

Non-autoregressive approaches aim to improve the inference speed of translation models by only requiring a single forward pass to generate the output sequence instead of iteratively producing each predicted token. Consequently, their translation quality still tends to be inferior to their autoregres…

Cited by 9Source ↗PDF ↗code ↗Scholar ↗