@inproceedings{wang-etal-2026-towards-low,
title = "Towards Low-Resource {M}anchu Text Generation: Corpus Construction and Multi-Granularity Augmentation",
author = "Wang, Meiqi and
Xu, Zhiyong and
Sun, Xiaoxin and
Yu, Ruixin and
Guo, Zhiyong and
Wang, Zifan and
You, Shuqi and
Liu, Siyu and
Qin, Xiayu and
Wang, Suhua",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.29/",
pages = "546--559",
ISBN = "979-8-89176-444-6",
abstract = "Manchu is a typical low-resource agglutinative language, for which existing digital resources are largely limited to character recognition and basic annotation, while sentence-level generation remains underexplored. In this paper, we study constrained sentence-level Manchu continuation. We construct the first context-target corpus for this continuation task, consisting of 3214 examples collected from Manchu Stories in Translation, Common Manchu Dialogues, and other sources, covering both narrative and conversational genres. To improve robustness to rich suffixation, relatively flexible word order, and frequent OCR or transcription noise in Manchu, we propose a Multi-Granularity Data Augmentation (MGDA) strategy that expands training data through character-level noise injection, phrase rearrangement, and suffix perturbation, without relying on external dictionaries or translation models. Experiments on ByT5-small and Qwen2-1.5B show that MGDA substantially improves Manchu text generation performance: BLEU-4/ROUGE-L increases from 2.03/2.59 to 17.60/42.70 for ByT5, and from 1.98/6.42 to 14.12/41.49 for Qwen. Further ablation studies demonstrate the complementarity of the three augmentation granularities and suggest potential benefits of byte-level modeling in this experimental setting."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-towards-low">
<titleInfo>
<title>Towards Low-Resource Manchu Text Generation: Corpus Construction and Multi-Granularity Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Meiqi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyong</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoxin</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruixin</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyong</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zifan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuqi</namePart>
<namePart type="family">You</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siyu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiayu</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suhua</namePart>
<namePart type="family">Wang</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>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</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">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Manchu is a typical low-resource agglutinative language, for which existing digital resources are largely limited to character recognition and basic annotation, while sentence-level generation remains underexplored. In this paper, we study constrained sentence-level Manchu continuation. We construct the first context-target corpus for this continuation task, consisting of 3214 examples collected from Manchu Stories in Translation, Common Manchu Dialogues, and other sources, covering both narrative and conversational genres. To improve robustness to rich suffixation, relatively flexible word order, and frequent OCR or transcription noise in Manchu, we propose a Multi-Granularity Data Augmentation (MGDA) strategy that expands training data through character-level noise injection, phrase rearrangement, and suffix perturbation, without relying on external dictionaries or translation models. Experiments on ByT5-small and Qwen2-1.5B show that MGDA substantially improves Manchu text generation performance: BLEU-4/ROUGE-L increases from 2.03/2.59 to 17.60/42.70 for ByT5, and from 1.98/6.42 to 14.12/41.49 for Qwen. Further ablation studies demonstrate the complementarity of the three augmentation granularities and suggest potential benefits of byte-level modeling in this experimental setting.</abstract>
<identifier type="citekey">wang-etal-2026-towards-low</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.29/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>546</start>
<end>559</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Low-Resource Manchu Text Generation: Corpus Construction and Multi-Granularity Augmentation
%A Wang, Meiqi
%A Xu, Zhiyong
%A Sun, Xiaoxin
%A Yu, Ruixin
%A Guo, Zhiyong
%A Wang, Zifan
%A You, Shuqi
%A Liu, Siyu
%A Qin, Xiayu
%A Wang, Suhua
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F wang-etal-2026-towards-low
%X Manchu is a typical low-resource agglutinative language, for which existing digital resources are largely limited to character recognition and basic annotation, while sentence-level generation remains underexplored. In this paper, we study constrained sentence-level Manchu continuation. We construct the first context-target corpus for this continuation task, consisting of 3214 examples collected from Manchu Stories in Translation, Common Manchu Dialogues, and other sources, covering both narrative and conversational genres. To improve robustness to rich suffixation, relatively flexible word order, and frequent OCR or transcription noise in Manchu, we propose a Multi-Granularity Data Augmentation (MGDA) strategy that expands training data through character-level noise injection, phrase rearrangement, and suffix perturbation, without relying on external dictionaries or translation models. Experiments on ByT5-small and Qwen2-1.5B show that MGDA substantially improves Manchu text generation performance: BLEU-4/ROUGE-L increases from 2.03/2.59 to 17.60/42.70 for ByT5, and from 1.98/6.42 to 14.12/41.49 for Qwen. Further ablation studies demonstrate the complementarity of the three augmentation granularities and suggest potential benefits of byte-level modeling in this experimental setting.
%U https://aclanthology.org/2026.findings-aacl.29/
%P 546-559
Markdown (Informal)
[Towards Low-Resource Manchu Text Generation: Corpus Construction and Multi-Granularity Augmentation](https://aclanthology.org/2026.findings-aacl.29/) (Wang et al., Findings 2026)
ACL
- Meiqi Wang, Zhiyong Xu, Xiaoxin Sun, Ruixin Yu, Zhiyong Guo, Zifan Wang, Shuqi You, Siyu Liu, Xiayu Qin, and Suhua Wang. 2026. Towards Low-Resource Manchu Text Generation: Corpus Construction and Multi-Granularity Augmentation. In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026, pages 546–559, Hengqin, China. Association for Computational Linguistics.