@inproceedings{guerra-etal-2026-document,
title = "Document Summarization for {AI}-based Post-Editing",
author = "Guerra, Vera Senderowicz and
Pavlou, Dimitrios and
Bourgonje, Peter and
Khrapunova, Olesia and
Karageorgos, Konstantinos and
Schliem, Aaron",
editor = "Briakou, Eleftheria and
Gwinnup, Jeremy and
Goel, Shivali",
booktitle = "Proceedings of the 17th Conference of the Association for Machine Translation in the {A}mericas (Volume 1: Research Track)",
month = aug,
year = "2026",
address = "Qu{\'e}bec City, Canada",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2026.amta-research.11/",
pages = "174--185",
abstract = "Post-Editing (PE) is typically performed on isolated segments or small batches, without access to broader document context. In this paper, we investigate whether pre-generated, document-level summaries can improve PE quality. Using a purpose-built summarization prompt evaluated across nine LLMs from OpenAI and Google, we select two models with contrasting summary styles for downstream experiments on 448 documents covering 37 target locales and 13 content domains. Summaries generated by gemini-2.5-flash-lite, which are directive and domain-specific, yield gains in edit distance and modest gains in COMET, whereas those generated by GPT-4o, which tend to be more generic and descriptive, degrade performance across most metrics. The positive effect appears most pronounced in terminologically dense domains and lower-resource locales. A qualitative analysis shows that improvements arise when summaries provide specific, actionable guidance on terminology, domain conventions, and style, and that performance decreases when summaries are underspecified or conflicting. These findings suggest that summary specificity and actionability, rather than the mere addition of context, determine whether document-level information benefits post-editing."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guerra-etal-2026-document">
<titleInfo>
<title>Document Summarization for AI-based Post-Editing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="given">Senderowicz</namePart>
<namePart type="family">Guerra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dimitrios</namePart>
<namePart type="family">Pavlou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Bourgonje</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olesia</namePart>
<namePart type="family">Khrapunova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Konstantinos</namePart>
<namePart type="family">Karageorgos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Schliem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eleftheria</namePart>
<namePart type="family">Briakou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Gwinnup</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shivali</namePart>
<namePart type="family">Goel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Québec City, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Post-Editing (PE) is typically performed on isolated segments or small batches, without access to broader document context. In this paper, we investigate whether pre-generated, document-level summaries can improve PE quality. Using a purpose-built summarization prompt evaluated across nine LLMs from OpenAI and Google, we select two models with contrasting summary styles for downstream experiments on 448 documents covering 37 target locales and 13 content domains. Summaries generated by gemini-2.5-flash-lite, which are directive and domain-specific, yield gains in edit distance and modest gains in COMET, whereas those generated by GPT-4o, which tend to be more generic and descriptive, degrade performance across most metrics. The positive effect appears most pronounced in terminologically dense domains and lower-resource locales. A qualitative analysis shows that improvements arise when summaries provide specific, actionable guidance on terminology, domain conventions, and style, and that performance decreases when summaries are underspecified or conflicting. These findings suggest that summary specificity and actionability, rather than the mere addition of context, determine whether document-level information benefits post-editing.</abstract>
<identifier type="citekey">guerra-etal-2026-document</identifier>
<location>
<url>https://aclanthology.org/2026.amta-research.11/</url>
</location>
<part>
<date>2026-08</date>
<extent unit="page">
<start>174</start>
<end>185</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Document Summarization for AI-based Post-Editing
%A Guerra, Vera Senderowicz
%A Pavlou, Dimitrios
%A Bourgonje, Peter
%A Khrapunova, Olesia
%A Karageorgos, Konstantinos
%A Schliem, Aaron
%Y Briakou, Eleftheria
%Y Gwinnup, Jeremy
%Y Goel, Shivali
%S Proceedings of the 17th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)
%D 2026
%8 August
%I Association for Machine Translation in the Americas
%C Québec City, Canada
%F guerra-etal-2026-document
%X Post-Editing (PE) is typically performed on isolated segments or small batches, without access to broader document context. In this paper, we investigate whether pre-generated, document-level summaries can improve PE quality. Using a purpose-built summarization prompt evaluated across nine LLMs from OpenAI and Google, we select two models with contrasting summary styles for downstream experiments on 448 documents covering 37 target locales and 13 content domains. Summaries generated by gemini-2.5-flash-lite, which are directive and domain-specific, yield gains in edit distance and modest gains in COMET, whereas those generated by GPT-4o, which tend to be more generic and descriptive, degrade performance across most metrics. The positive effect appears most pronounced in terminologically dense domains and lower-resource locales. A qualitative analysis shows that improvements arise when summaries provide specific, actionable guidance on terminology, domain conventions, and style, and that performance decreases when summaries are underspecified or conflicting. These findings suggest that summary specificity and actionability, rather than the mere addition of context, determine whether document-level information benefits post-editing.
%U https://aclanthology.org/2026.amta-research.11/
%P 174-185
Markdown (Informal)
[Document Summarization for AI-based Post-Editing](https://aclanthology.org/2026.amta-research.11/) (Guerra et al., AMTA 2026)
ACL
- Vera Senderowicz Guerra, Dimitrios Pavlou, Peter Bourgonje, Olesia Khrapunova, Konstantinos Karageorgos, and Aaron Schliem. 2026. Document Summarization for AI-based Post-Editing. In Proceedings of the 17th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track), pages 174–185, Québec City, Canada. Association for Machine Translation in the Americas.