@inproceedings{wang-etal-2024-simultaneous,
title = "Simultaneous Machine Translation with Large Language Models",
author = "Wang, Minghan and
Vu, Thuy-Trang and
Zhao, Jinming and
Shiri, Fatemeh and
Shareghi, Ehsan and
Haffari, Gholamreza",
editor = "Baldwin, Tim and
Rodr{\'i}guez M{\'e}ndez, Sergio Jos{\'e} and
Kuo, Nicholas",
booktitle = "Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association",
month = dec,
year = "2024",
address = "Canberra, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.alta-1.7/",
pages = "89--103",
abstract = "Real-world simultaneous machine translation (SimulMT) systems face more challenges than just the quality-latency trade-off. They also need to address issues related to robustness with noisy input, processing long contexts, and flexibility for knowledge injection. These challenges demand models with strong language understanding and generation capabilities which may not often equipped by dedicated MT models. In this paper, we investigate the possibility of applying Large Language Models (LLM) to SimulMT tasks by using existing incremental-decoding methods with a newly proposed RALCP algorithm for latency reduction. We conducted experiments using the Llama2-7b-chat model on nine different languages from the MUST-C dataset. The results show that LLM outperforms dedicated MT models in terms of BLEU and LAAL metrics. Further analysis indicates that LLM has advantages in terms of tuning efficiency and robustness. However, it is important to note that the computational cost of LLM remains a significant obstacle to its application in SimulMT."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-simultaneous">
<titleInfo>
<title>Simultaneous Machine Translation with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thuy-Trang</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinming</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fatemeh</namePart>
<namePart type="family">Shiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Shareghi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergio</namePart>
<namePart type="given">José</namePart>
<namePart type="family">Rodríguez Méndez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Kuo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Canberra, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Real-world simultaneous machine translation (SimulMT) systems face more challenges than just the quality-latency trade-off. They also need to address issues related to robustness with noisy input, processing long contexts, and flexibility for knowledge injection. These challenges demand models with strong language understanding and generation capabilities which may not often equipped by dedicated MT models. In this paper, we investigate the possibility of applying Large Language Models (LLM) to SimulMT tasks by using existing incremental-decoding methods with a newly proposed RALCP algorithm for latency reduction. We conducted experiments using the Llama2-7b-chat model on nine different languages from the MUST-C dataset. The results show that LLM outperforms dedicated MT models in terms of BLEU and LAAL metrics. Further analysis indicates that LLM has advantages in terms of tuning efficiency and robustness. However, it is important to note that the computational cost of LLM remains a significant obstacle to its application in SimulMT.</abstract>
<identifier type="citekey">wang-etal-2024-simultaneous</identifier>
<location>
<url>https://aclanthology.org/2024.alta-1.7/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>89</start>
<end>103</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simultaneous Machine Translation with Large Language Models
%A Wang, Minghan
%A Vu, Thuy-Trang
%A Zhao, Jinming
%A Shiri, Fatemeh
%A Shareghi, Ehsan
%A Haffari, Gholamreza
%Y Baldwin, Tim
%Y Rodríguez Méndez, Sergio José
%Y Kuo, Nicholas
%S Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association
%D 2024
%8 December
%I Association for Computational Linguistics
%C Canberra, Australia
%F wang-etal-2024-simultaneous
%X Real-world simultaneous machine translation (SimulMT) systems face more challenges than just the quality-latency trade-off. They also need to address issues related to robustness with noisy input, processing long contexts, and flexibility for knowledge injection. These challenges demand models with strong language understanding and generation capabilities which may not often equipped by dedicated MT models. In this paper, we investigate the possibility of applying Large Language Models (LLM) to SimulMT tasks by using existing incremental-decoding methods with a newly proposed RALCP algorithm for latency reduction. We conducted experiments using the Llama2-7b-chat model on nine different languages from the MUST-C dataset. The results show that LLM outperforms dedicated MT models in terms of BLEU and LAAL metrics. Further analysis indicates that LLM has advantages in terms of tuning efficiency and robustness. However, it is important to note that the computational cost of LLM remains a significant obstacle to its application in SimulMT.
%U https://aclanthology.org/2024.alta-1.7/
%P 89-103
Markdown (Informal)
[Simultaneous Machine Translation with Large Language Models](https://aclanthology.org/2024.alta-1.7/) (Wang et al., ALTA 2024)
ACL
- Minghan Wang, Thuy-Trang Vu, Jinming Zhao, Fatemeh Shiri, Ehsan Shareghi, and Gholamreza Haffari. 2024. Simultaneous Machine Translation with Large Language Models. In Proceedings of the 22nd Annual Workshop of the Australasian Language Technology Association, pages 89–103, Canberra, Australia. Association for Computational Linguistics.