<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="boesenberg-evang-2026-trainable">
    <titleInfo>
        <title>Trainable, Multiword-aware Linguistic Tokenization Using Modern Neural Networks</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Clara</namePart>
        <namePart type="family">Boesenberg</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kilian</namePart>
        <namePart type="family">Evang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Selene</namePart>
            <namePart type="family">Baez Santamaria</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sai</namePart>
            <namePart type="given">Ashish</namePart>
            <namePart type="family">Somayajula</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Atsuki</namePart>
            <namePart type="family">Yamaguchi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-383-8</identifier>
    </relatedItem>
    <abstract>We revisit MWE-aware linguistic tokenization as a character-level and token-level sequence labeling problem and present a systematic evaluation on English, German, Italian, and Dutch data. We compare a standard tokenizer trained without MWE-awareness as a baseline (UDPipe), a character-level SRN+CRF model (Elephant), and transformer-based MaChAmp models trained either directly on gold character labels or as token-level postprocessors on top of UDPipe. Our results show that the two-stage pipeline – UDPipe pretokenization followed by MaChAmp postprocessing – consistently yields the best accuracy. Our analysis of error patterns highlights how different architectures trade off over- and undersegmentation. These findings provide practical guidance for building MWE-aware tokenizers and suggest that postprocessing pipelines with transformers are a strong and general strategy for non-standard tokenization.</abstract>
    <identifier type="citekey">boesenberg-evang-2026-trainable</identifier>
    <location>
        <url>https://aclanthology.org/2026.eacl-srw.19/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>266</start>
            <end>276</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Trainable, Multiword-aware Linguistic Tokenization Using Modern Neural Networks
%A Boesenberg, Clara
%A Evang, Kilian
%Y Baez Santamaria, Selene
%Y Somayajula, Sai Ashish
%Y Yamaguchi, Atsuki
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-383-8
%F boesenberg-evang-2026-trainable
%X We revisit MWE-aware linguistic tokenization as a character-level and token-level sequence labeling problem and present a systematic evaluation on English, German, Italian, and Dutch data. We compare a standard tokenizer trained without MWE-awareness as a baseline (UDPipe), a character-level SRN+CRF model (Elephant), and transformer-based MaChAmp models trained either directly on gold character labels or as token-level postprocessors on top of UDPipe. Our results show that the two-stage pipeline – UDPipe pretokenization followed by MaChAmp postprocessing – consistently yields the best accuracy. Our analysis of error patterns highlights how different architectures trade off over- and undersegmentation. These findings provide practical guidance for building MWE-aware tokenizers and suggest that postprocessing pipelines with transformers are a strong and general strategy for non-standard tokenization.
%U https://aclanthology.org/2026.eacl-srw.19/
%P 266-276

Markdown (Informal)

[Trainable, Multiword-aware Linguistic Tokenization Using Modern Neural Networks](https://aclanthology.org/2026.eacl-srw.19/) (Boesenberg & Evang, EACL 2026)

• Trainable, Multiword-aware Linguistic Tokenization Using Modern Neural Networks (Boesenberg & Evang, EACL 2026)

ACL

• Clara Boesenberg and Kilian Evang. 2026. Trainable, Multiword-aware Linguistic Tokenization Using Modern Neural Networks. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 266–276, Rabat, Morocco. Association for Computational Linguistics.