@inproceedings{dinh-etal-2026-morphology,
title = "When Morphology Hides in Plain Sight: Breaking the Isolation in {V}ietnamese and Beyond",
author = "Dinh, Anh Trac Duc and
Vo, Khang Hoang Nhat and
Ta, Tai Tien and
Doan, Vinh Cong and
Quan, Tho",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.472/",
pages = "10377--10392",
ISBN = "979-8-89176-390-6",
abstract = "In isolating languages such as Vietnamese, core morphological structure is encoded not by inflection but by the composition and ordering of monosyllabic morphemes, yet standard Transformer encoders largely overlook this signal. We introduce HuTieuBERT, a morpheme-aware Transformer that augments a pretrained Vietnamese encoder with two lightweight inductive biases: (i) Adaptive Boundary-Token Fusion, which integrates BMES-based morpheme boundary embeddings into token representations via a learnable gate, and (ii) a Morpheme-Aware Attention Bias, which injects a fixed structural attention matrix into early self-attention layers while minimally perturbing the pretrained attention geometry. Across a suite of Vietnamese POS, NER, and sentence-level classification benchmarks, HuTieuBERT consistently outperforms strong baselines, with the largest gains on syntactic tasks. Hyperparameter ablations show a broad regime in which structural biases improve accuracy without destabilizing representations. Applying the same design to ChineseBERT (Chinese-BERT-wwm) yields MAChineseBERT, which improves $F_{1}$ and produces more balanced tag distributions on Chinese POS and NER, suggesting that explicit morpheme-aware attention is a portable and effective strategy for modeling isolating languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dinh-etal-2026-morphology">
<titleInfo>
<title>When Morphology Hides in Plain Sight: Breaking the Isolation in Vietnamese and Beyond</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anh</namePart>
<namePart type="given">Trac</namePart>
<namePart type="given">Duc</namePart>
<namePart type="family">Dinh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khang</namePart>
<namePart type="given">Hoang</namePart>
<namePart type="given">Nhat</namePart>
<namePart type="family">Vo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tai</namePart>
<namePart type="given">Tien</namePart>
<namePart type="family">Ta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinh</namePart>
<namePart type="given">Cong</namePart>
<namePart type="family">Doan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tho</namePart>
<namePart type="family">Quan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>In isolating languages such as Vietnamese, core morphological structure is encoded not by inflection but by the composition and ordering of monosyllabic morphemes, yet standard Transformer encoders largely overlook this signal. We introduce HuTieuBERT, a morpheme-aware Transformer that augments a pretrained Vietnamese encoder with two lightweight inductive biases: (i) Adaptive Boundary-Token Fusion, which integrates BMES-based morpheme boundary embeddings into token representations via a learnable gate, and (ii) a Morpheme-Aware Attention Bias, which injects a fixed structural attention matrix into early self-attention layers while minimally perturbing the pretrained attention geometry. Across a suite of Vietnamese POS, NER, and sentence-level classification benchmarks, HuTieuBERT consistently outperforms strong baselines, with the largest gains on syntactic tasks. Hyperparameter ablations show a broad regime in which structural biases improve accuracy without destabilizing representations. Applying the same design to ChineseBERT (Chinese-BERT-wwm) yields MAChineseBERT, which improves F₁ and produces more balanced tag distributions on Chinese POS and NER, suggesting that explicit morpheme-aware attention is a portable and effective strategy for modeling isolating languages.</abstract>
<identifier type="citekey">dinh-etal-2026-morphology</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.472/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>10377</start>
<end>10392</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Morphology Hides in Plain Sight: Breaking the Isolation in Vietnamese and Beyond
%A Dinh, Anh Trac Duc
%A Vo, Khang Hoang Nhat
%A Ta, Tai Tien
%A Doan, Vinh Cong
%A Quan, Tho
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F dinh-etal-2026-morphology
%X In isolating languages such as Vietnamese, core morphological structure is encoded not by inflection but by the composition and ordering of monosyllabic morphemes, yet standard Transformer encoders largely overlook this signal. We introduce HuTieuBERT, a morpheme-aware Transformer that augments a pretrained Vietnamese encoder with two lightweight inductive biases: (i) Adaptive Boundary-Token Fusion, which integrates BMES-based morpheme boundary embeddings into token representations via a learnable gate, and (ii) a Morpheme-Aware Attention Bias, which injects a fixed structural attention matrix into early self-attention layers while minimally perturbing the pretrained attention geometry. Across a suite of Vietnamese POS, NER, and sentence-level classification benchmarks, HuTieuBERT consistently outperforms strong baselines, with the largest gains on syntactic tasks. Hyperparameter ablations show a broad regime in which structural biases improve accuracy without destabilizing representations. Applying the same design to ChineseBERT (Chinese-BERT-wwm) yields MAChineseBERT, which improves F₁ and produces more balanced tag distributions on Chinese POS and NER, suggesting that explicit morpheme-aware attention is a portable and effective strategy for modeling isolating languages.
%U https://aclanthology.org/2026.acl-long.472/
%P 10377-10392
Markdown (Informal)
[When Morphology Hides in Plain Sight: Breaking the Isolation in Vietnamese and Beyond](https://aclanthology.org/2026.acl-long.472/) (Dinh et al., ACL 2026)
ACL