@inproceedings{ouyang-etal-2025-anticipating,
title = "Anticipating Future with Large Language Model for Simultaneous Machine Translation",
author = "Ouyang, Siqi and
Hrinchuk, Oleksii and
Chen, Zhehuai and
Lavrukhin, Vitaly and
Balam, Jagadeesh and
Li, Lei and
Ginsburg, Boris",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.286/",
doi = "10.18653/v1/2025.naacl-long.286",
pages = "5547--5557",
ISBN = "979-8-89176-189-6",
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 Translation by Anticipating Future (TAF), a method to improve translation quality while retaining 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)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ouyang-etal-2025-anticipating">
<titleInfo>
<title>Anticipating Future with Large Language Model for Simultaneous Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Ouyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oleksii</namePart>
<namePart type="family">Hrinchuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhehuai</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vitaly</namePart>
<namePart type="family">Lavrukhin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jagadeesh</namePart>
<namePart type="family">Balam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boris</namePart>
<namePart type="family">Ginsburg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<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 Translation by Anticipating Future (TAF), a method to improve translation quality while retaining 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).</abstract>
<identifier type="citekey">ouyang-etal-2025-anticipating</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.286</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.286/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>5547</start>
<end>5557</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Anticipating Future with Large Language Model for Simultaneous Machine Translation
%A Ouyang, Siqi
%A Hrinchuk, Oleksii
%A Chen, Zhehuai
%A Lavrukhin, Vitaly
%A Balam, Jagadeesh
%A Li, Lei
%A Ginsburg, Boris
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F ouyang-etal-2025-anticipating
%X 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 Translation by Anticipating Future (TAF), a method to improve translation quality while retaining 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).
%R 10.18653/v1/2025.naacl-long.286
%U https://aclanthology.org/2025.naacl-long.286/
%U https://doi.org/10.18653/v1/2025.naacl-long.286
%P 5547-5557
Markdown (Informal)
[Anticipating Future with Large Language Model for Simultaneous Machine Translation](https://aclanthology.org/2025.naacl-long.286/) (Ouyang et al., NAACL 2025)
ACL
- Siqi Ouyang, Oleksii Hrinchuk, Zhehuai Chen, Vitaly Lavrukhin, Jagadeesh Balam, Lei Li, and Boris Ginsburg. 2025. Anticipating Future with Large Language Model for Simultaneous Machine Translation. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 5547–5557, Albuquerque, New Mexico. Association for Computational Linguistics.