<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marco-fraser-2024-subword">
    <titleInfo>
        <title>Subword Segmentation in LLMs: Looking at Inflection and Consistency</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Marion</namePart>
        <namePart type="given">Di</namePart>
        <namePart type="family">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>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The role of subword segmentation in relation to capturing morphological patterns in LLMs is currently not well explored. Ideally, one would train models like GPT using various segmentations and evaluate how well word meanings are captured. Since this is not computationally feasible, we group words according to their segmentation properties and compare how well a model can solve a linguistic task for these groups. We study two criteria: (i) adherence to morpheme boundaries and (ii) the segmentation consistency of the different inflected forms of a lemma. We select word forms with high and low values for these criteria and carry out experiments on GPT-4o’s ability to capture verbal inflection for 10 languages. Our results indicate that in particular the criterion of segmentation consistency can help to predict the model’s ability to recognize and generate the lemma from an inflected form, providing evidence that subword segmentation is relevant.</abstract>
    <identifier type="citekey">marco-fraser-2024-subword</identifier>
    <identifier type="doi">10.18653/v1/2024.emnlp-main.672</identifier>
    <location>
        <url>https://aclanthology.org/2024.emnlp-main.672</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>12050</start>
            <end>12060</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Subword Segmentation in LLMs: Looking at Inflection and Consistency
%A Marco, Marion Di
%A Fraser, Alexander
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F marco-fraser-2024-subword
%X The role of subword segmentation in relation to capturing morphological patterns in LLMs is currently not well explored. Ideally, one would train models like GPT using various segmentations and evaluate how well word meanings are captured. Since this is not computationally feasible, we group words according to their segmentation properties and compare how well a model can solve a linguistic task for these groups. We study two criteria: (i) adherence to morpheme boundaries and (ii) the segmentation consistency of the different inflected forms of a lemma. We select word forms with high and low values for these criteria and carry out experiments on GPT-4o’s ability to capture verbal inflection for 10 languages. Our results indicate that in particular the criterion of segmentation consistency can help to predict the model’s ability to recognize and generate the lemma from an inflected form, providing evidence that subword segmentation is relevant.
%R 10.18653/v1/2024.emnlp-main.672
%U https://aclanthology.org/2024.emnlp-main.672
%U https://doi.org/10.18653/v1/2024.emnlp-main.672
%P 12050-12060

Markdown (Informal)

[Subword Segmentation in LLMs: Looking at Inflection and Consistency](https://aclanthology.org/2024.emnlp-main.672) (Marco & Fraser, EMNLP 2024)

• Subword Segmentation in LLMs: Looking at Inflection and Consistency (Marco & Fraser, EMNLP 2024)

ACL

• Marion Di Marco and Alexander Fraser. 2024. Subword Segmentation in LLMs: Looking at Inflection and Consistency. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 12050–12060, Miami, Florida, USA. Association for Computational Linguistics.