@inproceedings{hoang-etal-2026-incorporating,
title = "Incorporating {A}bstract {M}eaning {R}epresentation and Uniform Meaning Representation into In-Context Learning Strategies for Machine Translation",
author = "Hoang, Thu and
Yang, Ellie and
Lin, Weixin and
Wein, Shira",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.96/",
pages = "2090--2124",
ISBN = "979-8-89176-439-2",
abstract = "While in-context machine translation approaches lead to notable progress for low-resource languages, it is not yet clear what kinds of linguistic information in prompts can consistently and reliably lead to performance gains. We evaluate whether English semantic representations, specifically Abstract Meaning Representation (AMR) and its extension Uniform Meaning Representation (UMR), can improve LLM-based MT via prompting. Across 12 languages, 7 models from 5 families, and multiple prompting strategies, we find that conclusions about their effectiveness are highly sensitive to the setting. We further observe that prompts using UMR tend to outperform those using AMR, particularly in few-shot scenarios and for certain models. These results highlight the need for comprehensive evaluation for in-context learning work."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoang-etal-2026-incorporating">
<titleInfo>
<title>Incorporating Abstract Meaning Representation and Uniform Meaning Representation into In-Context Learning Strategies for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thu</namePart>
<namePart type="family">Hoang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellie</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weixin</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shira</namePart>
<namePart type="family">Wein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>While in-context machine translation approaches lead to notable progress for low-resource languages, it is not yet clear what kinds of linguistic information in prompts can consistently and reliably lead to performance gains. We evaluate whether English semantic representations, specifically Abstract Meaning Representation (AMR) and its extension Uniform Meaning Representation (UMR), can improve LLM-based MT via prompting. Across 12 languages, 7 models from 5 families, and multiple prompting strategies, we find that conclusions about their effectiveness are highly sensitive to the setting. We further observe that prompts using UMR tend to outperform those using AMR, particularly in few-shot scenarios and for certain models. These results highlight the need for comprehensive evaluation for in-context learning work.</abstract>
<identifier type="citekey">hoang-etal-2026-incorporating</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.96/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>2090</start>
<end>2124</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Incorporating Abstract Meaning Representation and Uniform Meaning Representation into In-Context Learning Strategies for Machine Translation
%A Hoang, Thu
%A Yang, Ellie
%A Lin, Weixin
%A Wein, Shira
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F hoang-etal-2026-incorporating
%X While in-context machine translation approaches lead to notable progress for low-resource languages, it is not yet clear what kinds of linguistic information in prompts can consistently and reliably lead to performance gains. We evaluate whether English semantic representations, specifically Abstract Meaning Representation (AMR) and its extension Uniform Meaning Representation (UMR), can improve LLM-based MT via prompting. Across 12 languages, 7 models from 5 families, and multiple prompting strategies, we find that conclusions about their effectiveness are highly sensitive to the setting. We further observe that prompts using UMR tend to outperform those using AMR, particularly in few-shot scenarios and for certain models. These results highlight the need for comprehensive evaluation for in-context learning work.
%U https://aclanthology.org/2026.aacl-long.96/
%P 2090-2124
Markdown (Informal)
[Incorporating Abstract Meaning Representation and Uniform Meaning Representation into In-Context Learning Strategies for Machine Translation](https://aclanthology.org/2026.aacl-long.96/) (Hoang et al., AACL-IJCNLP 2026)
ACL