<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koshkin-etal-2024-transllama">
    <titleInfo>
        <title>TransLLaMa: LLM-based Simultaneous Translation System</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Roman</namePart>
        <namePart type="family">Koshkin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Katsuhito</namePart>
        <namePart type="family">Sudoh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Satoshi</namePart>
        <namePart type="family">Nakamura</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Decoder-only large language models (LLMs) have recently demonstrated impressive capabilities in text generation and reasoning. Nonetheless, they have limited applications in simultaneous machine translation (SiMT), currently dominated by encoder-decoder transformers. This study demonstrates that, after fine-tuning on a small dataset comprising causally aligned source and target sentence pairs, a pre-trained open-source LLM can control input segmentation directly by generating a special “wait” token. This obviates the need for a separate policy and enables the LLM to perform English-German and English-Russian SiMT tasks with BLEU scores that are comparable to those of specific state-of-the-art baselines. We also evaluated closed-source models such as GPT-4, which displayed encouraging results in performing the SiMT task without prior training (zero-shot), indicating a promising avenue for enhancing future SiMT systems.</abstract>
    <identifier type="citekey">koshkin-etal-2024-transllama</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-emnlp.27</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>461</start>
            <end>476</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TransLLaMa: LLM-based Simultaneous Translation System
%A Koshkin, Roman
%A Sudoh, Katsuhito
%A Nakamura, Satoshi
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F koshkin-etal-2024-transllama
%X Decoder-only large language models (LLMs) have recently demonstrated impressive capabilities in text generation and reasoning. Nonetheless, they have limited applications in simultaneous machine translation (SiMT), currently dominated by encoder-decoder transformers. This study demonstrates that, after fine-tuning on a small dataset comprising causally aligned source and target sentence pairs, a pre-trained open-source LLM can control input segmentation directly by generating a special “wait” token. This obviates the need for a separate policy and enables the LLM to perform English-German and English-Russian SiMT tasks with BLEU scores that are comparable to those of specific state-of-the-art baselines. We also evaluated closed-source models such as GPT-4, which displayed encouraging results in performing the SiMT task without prior training (zero-shot), indicating a promising avenue for enhancing future SiMT systems.
%U https://aclanthology.org/2024.findings-emnlp.27
%P 461-476

Markdown (Informal)

[TransLLaMa: LLM-based Simultaneous Translation System](https://aclanthology.org/2024.findings-emnlp.27) (Koshkin et al., Findings 2024)

• TransLLaMa: LLM-based Simultaneous Translation System (Koshkin et al., Findings 2024)

ACL

• Roman Koshkin, Katsuhito Sudoh, and Satoshi Nakamura. 2024. TransLLaMa: LLM-based Simultaneous Translation System. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 461–476, Miami, Florida, USA. Association for Computational Linguistics.