@inproceedings{sheng-etal-2026-context,
title = "In-Context Learning for {U}pper {S}orbian to {G}erman Translation: Comparing Lexical and Morpho-Syntactic Information",
author = "Sheng, Qimin and
Di Marco, Marion and
Fraser, Alexander",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Eleventh Conference on Machine Translation",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wmt-main.39/",
pages = "698--710",
ISBN = "979-8-89176-474-3",
abstract = "LLM-based translation remains challenging for low-resource languages, as LLMs often lack linguistic knowledge due to their limited representation in pre-training data. This is particularly problematic for morphologically rich languages where a large vocabulary can lead to further data sparsity.\par Previous work has shown that providing external guidance on the source sentence in the form of language-specific information can help LLMs with tasks such as machine translation. In this study, we investigate zero-shot context augmentation for Upper Sorbian-to-German translation by enriching prompts with different types of contextual information: translation candidates in the form of bilingual dictionary entries, and morpho-syntactic analysis provided through morphological tagging. We first compare the effectiveness of these types of information in a zero-shot setting and then evaluate whether they generalize across additional experimental settings. We find that context-augmented prompting can improve Upper Sorbian-to-German translation. Contexts only containing translation candidates perform overall best, whereas morpho-syntactic analysis offers limited benefits, both on its own and in combination with lexical cues."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sheng-etal-2026-context">
<titleInfo>
<title>In-Context Learning for Upper Sorbian to German Translation: Comparing Lexical and Morpho-Syntactic Information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qimin</namePart>
<namePart type="family">Sheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marion</namePart>
<namePart type="family">Di Marco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Fraser</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 Eleventh Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</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">979-8-89176-474-3</identifier>
</relatedItem>
<abstract>LLM-based translation remains challenging for low-resource languages, as LLMs often lack linguistic knowledge due to their limited representation in pre-training data. This is particularly problematic for morphologically rich languages where a large vocabulary can lead to further data sparsity.\par Previous work has shown that providing external guidance on the source sentence in the form of language-specific information can help LLMs with tasks such as machine translation. In this study, we investigate zero-shot context augmentation for Upper Sorbian-to-German translation by enriching prompts with different types of contextual information: translation candidates in the form of bilingual dictionary entries, and morpho-syntactic analysis provided through morphological tagging. We first compare the effectiveness of these types of information in a zero-shot setting and then evaluate whether they generalize across additional experimental settings. We find that context-augmented prompting can improve Upper Sorbian-to-German translation. Contexts only containing translation candidates perform overall best, whereas morpho-syntactic analysis offers limited benefits, both on its own and in combination with lexical cues.</abstract>
<identifier type="citekey">sheng-etal-2026-context</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.39/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>698</start>
<end>710</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T In-Context Learning for Upper Sorbian to German Translation: Comparing Lexical and Morpho-Syntactic Information
%A Sheng, Qimin
%A Di Marco, Marion
%A Fraser, Alexander
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Eleventh Conference on Machine Translation
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-474-3
%F sheng-etal-2026-context
%X LLM-based translation remains challenging for low-resource languages, as LLMs often lack linguistic knowledge due to their limited representation in pre-training data. This is particularly problematic for morphologically rich languages where a large vocabulary can lead to further data sparsity.\par Previous work has shown that providing external guidance on the source sentence in the form of language-specific information can help LLMs with tasks such as machine translation. In this study, we investigate zero-shot context augmentation for Upper Sorbian-to-German translation by enriching prompts with different types of contextual information: translation candidates in the form of bilingual dictionary entries, and morpho-syntactic analysis provided through morphological tagging. We first compare the effectiveness of these types of information in a zero-shot setting and then evaluate whether they generalize across additional experimental settings. We find that context-augmented prompting can improve Upper Sorbian-to-German translation. Contexts only containing translation candidates perform overall best, whereas morpho-syntactic analysis offers limited benefits, both on its own and in combination with lexical cues.
%U https://aclanthology.org/2026.wmt-main.39/
%P 698-710
Markdown (Informal)
[In-Context Learning for Upper Sorbian to German Translation: Comparing Lexical and Morpho-Syntactic Information](https://aclanthology.org/2026.wmt-main.39/) (Sheng et al., WMT 2026)
ACL