@inproceedings{chen-etal-2026-bridging,
title = "Bridging the Consistency Gap: A Noun Bank Augmented Framework for Low-Cost Long Text Translation",
author = "Chen, Tao and
Zheng, Mao and
Li, Zheng and
Zheng, Zhang and
Lv, Bo",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.521/",
pages = "11960--11977",
ISBN = "979-8-89176-459-0",
abstract = "Large Language Models (LLMs) have advanced machine translation, yet long-text translation still faces a practical tension between document-level lexical consistency and inference cost. Recent document-level methods improve coherence by expanding context, maintaining multi-level memories, or injecting multi-granularity knowledge, but such broad context mechanisms often introduce substantial prompt redundancy and limit parallel inference. We propose $\textbf{NoBAT}$ ($\textbf{No}$un $\textbf{B}$ank $\textbf{A}$ugmented $\textbf{T}$ranslation), a lightweight framework that distills document-level lexical constraints into a compact global Noun Bank. NoBAT first constructs and disambiguates the Noun Bank serially, and then retrieves only relevant noun constraints for local, parallel translation. Experiments on IWSLT2017 and Novels-XL with multiple LLM backbones show that NoBAT consistently improves lexical translation consistency while maintaining competitive COMET scores. Compared with DELTA, NoBAT further reduces total token consumption by $\textbf{6.3$\times$}$, demonstrating a cost-effective trade-off among consistency, translation quality, and efficiency."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-bridging">
<titleInfo>
<title>Bridging the Consistency Gap: A Noun Bank Augmented Framework for Low-Cost Long Text Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mao</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhang</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Lv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) have advanced machine translation, yet long-text translation still faces a practical tension between document-level lexical consistency and inference cost. Recent document-level methods improve coherence by expanding context, maintaining multi-level memories, or injecting multi-granularity knowledge, but such broad context mechanisms often introduce substantial prompt redundancy and limit parallel inference. We propose NoBAT (Noun Bank Augmented Translation), a lightweight framework that distills document-level lexical constraints into a compact global Noun Bank. NoBAT first constructs and disambiguates the Noun Bank serially, and then retrieves only relevant noun constraints for local, parallel translation. Experiments on IWSLT2017 and Novels-XL with multiple LLM backbones show that NoBAT consistently improves lexical translation consistency while maintaining competitive COMET scores. Compared with DELTA, NoBAT further reduces total token consumption by 6.3\times, demonstrating a cost-effective trade-off among consistency, translation quality, and efficiency.</abstract>
<identifier type="citekey">chen-etal-2026-bridging</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.521/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>11960</start>
<end>11977</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bridging the Consistency Gap: A Noun Bank Augmented Framework for Low-Cost Long Text Translation
%A Chen, Tao
%A Zheng, Mao
%A Li, Zheng
%A Zheng, Zhang
%A Lv, Bo
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F chen-etal-2026-bridging
%X Large Language Models (LLMs) have advanced machine translation, yet long-text translation still faces a practical tension between document-level lexical consistency and inference cost. Recent document-level methods improve coherence by expanding context, maintaining multi-level memories, or injecting multi-granularity knowledge, but such broad context mechanisms often introduce substantial prompt redundancy and limit parallel inference. We propose NoBAT (Noun Bank Augmented Translation), a lightweight framework that distills document-level lexical constraints into a compact global Noun Bank. NoBAT first constructs and disambiguates the Noun Bank serially, and then retrieves only relevant noun constraints for local, parallel translation. Experiments on IWSLT2017 and Novels-XL with multiple LLM backbones show that NoBAT consistently improves lexical translation consistency while maintaining competitive COMET scores. Compared with DELTA, NoBAT further reduces total token consumption by 6.3\times, demonstrating a cost-effective trade-off among consistency, translation quality, and efficiency.
%U https://aclanthology.org/2026.emnlp-main.521/
%P 11960-11977
Markdown (Informal)
[Bridging the Consistency Gap: A Noun Bank Augmented Framework for Low-Cost Long Text Translation](https://aclanthology.org/2026.emnlp-main.521/) (Chen et al., EMNLP 2026)
ACL