Back to Search Start Over

Simul-LLM: A Framework for Exploring High-Quality Simultaneous Translation with Large Language Models

Authors :
Agostinelli, Victor
Wild, Max
Raffel, Matthew
Fuad, Kazi Ahmed Asif
Chen, Lizhong
Publication Year :
2023

Abstract

Large language models (LLMs) with billions of parameters and pretrained on massive amounts of data are now capable of near or better than state-of-the-art performance in a variety of downstream natural language processing tasks. Neural machine translation (NMT) is one such task that LLMs have been applied to with great success. However, little research has focused on applying LLMs to the more difficult subset of NMT called simultaneous translation (SimulMT), where translation begins before the entire source context is available to the model. In this paper, we address key challenges facing LLMs fine-tuned for SimulMT, validate classical SimulMT concepts and practices in the context of LLMs, explore adapting LLMs that are fine-tuned for NMT to the task of SimulMT, and introduce Simul-LLM, the first open-source fine-tuning and evaluation pipeline development framework for LLMs focused on SimulMT.<br />Comment: ACL 2024

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2312.04691
Document Type :
Working Paper