ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2410.22499
40
0

Anticipating Future with Large Language Model for Simultaneous Machine Translation

29 October 2024
Siqi Ouyang
Oleksii Hrinchuk
Zhehuai Chen
Vitaly Lavrukhin
Jagadeesh Balam
Lei Li
Boris Ginsburg
ArXivPDFHTML
Abstract

Simultaneous machine translation (SMT) takes streaming input utterances and incrementally produces target text. Existing SMT methods only use the partial utterance that has already arrived at the input and the generated hypothesis. Motivated by human interpreters' technique to forecast future words before hearing them, we propose T\textbf{T}Translation by A\textbf{A}Anticipating F\textbf{F}Future (TAF), a method to improve translation quality while retraining low latency. Its core idea is to use a large language model (LLM) to predict future source words and opportunistically translate without introducing too much risk. We evaluate our TAF and multiple baselines of SMT on four language directions. Experiments show that TAF achieves the best translation quality-latency trade-off and outperforms the baselines by up to 5 BLEU points at the same latency (three words).

View on arXiv
Comments on this paper