LLMs Are Zero-Shot Context-Aware Simultaneous Translators

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Koshkin, Roman, Sudoh, Katsuhito, Nakamura, Satoshi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929398431612928
author Koshkin, Roman
Sudoh, Katsuhito
Nakamura, Satoshi
author_facet Koshkin, Roman
Sudoh, Katsuhito
Nakamura, Satoshi
contents The advent of transformers has fueled progress in machine translation. More recently large language models (LLMs) have come to the spotlight thanks to their generality and strong performance in a wide range of language tasks, including translation. Here we show that open-source LLMs perform on par with or better than some state-of-the-art baselines in simultaneous machine translation (SiMT) tasks, zero-shot. We also demonstrate that injection of minimal background information, which is easy with an LLM, brings further performance gains, especially on challenging technical subject-matter. This highlights LLMs' potential for building next generation of massively multilingual, context-aware and terminologically accurate SiMT systems that require no resource-intensive training or fine-tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2406_13476
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LLMs Are Zero-Shot Context-Aware Simultaneous Translators
Koshkin, Roman
Sudoh, Katsuhito
Nakamura, Satoshi
Computation and Language
The advent of transformers has fueled progress in machine translation. More recently large language models (LLMs) have come to the spotlight thanks to their generality and strong performance in a wide range of language tasks, including translation. Here we show that open-source LLMs perform on par with or better than some state-of-the-art baselines in simultaneous machine translation (SiMT) tasks, zero-shot. We also demonstrate that injection of minimal background information, which is easy with an LLM, brings further performance gains, especially on challenging technical subject-matter. This highlights LLMs' potential for building next generation of massively multilingual, context-aware and terminologically accurate SiMT systems that require no resource-intensive training or fine-tuning.
title LLMs Are Zero-Shot Context-Aware Simultaneous Translators
topic Computation and Language
url https://arxiv.org/abs/2406.13476