LLM-based Translation Inference with Iterative Bilingual Understanding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Andong, Chen, Kehai, Xiang, Yang, Bai, Xuefeng, Yang, Muyun, Feng, Yang, Zhao, Tiejun, zhang, Min
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909443096051712
author Chen, Andong
Chen, Kehai
Xiang, Yang
Bai, Xuefeng
Yang, Muyun
Feng, Yang
Zhao, Tiejun
zhang, Min
author_facet Chen, Andong
Chen, Kehai
Xiang, Yang
Bai, Xuefeng
Yang, Muyun
Feng, Yang
Zhao, Tiejun
zhang, Min
contents The remarkable understanding and generation capabilities of large language models (LLMs) have greatly improved translation performance. However, incorrect understanding of the sentence to be translated can degrade translation quality. To address this issue, we proposed a novel Iterative Bilingual Understanding Translation (IBUT) method based on the cross-lingual capabilities of LLMs and the dual characteristics of translation tasks. The cross-lingual capability of LLMs enables the generation of contextual understanding for both the source and target languages separately. Furthermore, the dual characteristics allow IBUT to generate effective cross-lingual feedback, iteratively refining contextual understanding, thereby reducing errors and improving translation performance. Experimental results showed that the proposed IBUT outperforms several strong comparison methods, especially being generalized to multiple domains (e.g., news, commonsense, and cultural translation benchmarks).
format Preprint
id arxiv_https___arxiv_org_abs_2410_12543
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LLM-based Translation Inference with Iterative Bilingual Understanding
Chen, Andong
Chen, Kehai
Xiang, Yang
Bai, Xuefeng
Yang, Muyun
Feng, Yang
Zhao, Tiejun
zhang, Min
Computation and Language
Artificial Intelligence
The remarkable understanding and generation capabilities of large language models (LLMs) have greatly improved translation performance. However, incorrect understanding of the sentence to be translated can degrade translation quality. To address this issue, we proposed a novel Iterative Bilingual Understanding Translation (IBUT) method based on the cross-lingual capabilities of LLMs and the dual characteristics of translation tasks. The cross-lingual capability of LLMs enables the generation of contextual understanding for both the source and target languages separately. Furthermore, the dual characteristics allow IBUT to generate effective cross-lingual feedback, iteratively refining contextual understanding, thereby reducing errors and improving translation performance. Experimental results showed that the proposed IBUT outperforms several strong comparison methods, especially being generalized to multiple domains (e.g., news, commonsense, and cultural translation benchmarks).
title LLM-based Translation Inference with Iterative Bilingual Understanding
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.12543