@inproceedings{haley-etal-2023-language,
title = "Language-Agnostic Measures Discriminate Inflection and Derivation",
author = "Haley, Coleman and
Ponti, Edoardo M. and
Goldwater, Sharon",
editor = "Beinborn, Lisa and
Goswami, Koustava and
Murado{\u{g}}lu, Saliha and
Sorokin, Alexey and
Kumar, Ritesh and
Shcherbakov, Andreas and
Ponti, Edoardo M. and
Cotterell, Ryan and
Vylomova, Ekaterina",
booktitle = "Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.sigtyp-1.18",
doi = "10.18653/v1/2023.sigtyp-1.18",
pages = "150--152",
abstract = "In morphology, a distinction is commonly drawn between inflection and derivation. However, a precise definition of this distinction which captures the way the terms are used across languages remains elusive within linguistic theory, typically being based on subjective tests. In this study, we present 4 quantitative measures which use the statistics of a raw text corpus in a language to estimate how much and how variably a morphological construction changes aspects of the lexical entry, specifically, the word{'}s form and the word{'}s semantic and syntactic properties (as operationalised by distributional word embeddings). Based on a sample of 26 languages, we find that we can reconstruct 90{\%} of the classification of constructions into inflection and derivation in Unimorph using our 4 measures, providing large-scale cross-linguistic evidence that the concepts of inflection and derivation are associated with measurable signatures in terms of form and distribution signatures that behave consistently across a variety of languages. Critically, our measures and models are entirely language-agnostic, yet perform well across all languages studied. We find that while there is a high degree of consistency in the use of the terms inflection and derivation in terms of our measures, there are still many constructions near the model{'}s decision boundary between the two categories, indicating a gradient, rather than categorical, distinction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="haley-etal-2023-language">
<titleInfo>
<title>Language-Agnostic Measures Discriminate Inflection and Derivation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Coleman</namePart>
<namePart type="family">Haley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edoardo</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Ponti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharon</namePart>
<namePart type="family">Goldwater</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Beinborn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koustava</namePart>
<namePart type="family">Goswami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saliha</namePart>
<namePart type="family">Muradoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexey</namePart>
<namePart type="family">Sorokin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Shcherbakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edoardo</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Ponti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In morphology, a distinction is commonly drawn between inflection and derivation. However, a precise definition of this distinction which captures the way the terms are used across languages remains elusive within linguistic theory, typically being based on subjective tests. In this study, we present 4 quantitative measures which use the statistics of a raw text corpus in a language to estimate how much and how variably a morphological construction changes aspects of the lexical entry, specifically, the word’s form and the word’s semantic and syntactic properties (as operationalised by distributional word embeddings). Based on a sample of 26 languages, we find that we can reconstruct 90% of the classification of constructions into inflection and derivation in Unimorph using our 4 measures, providing large-scale cross-linguistic evidence that the concepts of inflection and derivation are associated with measurable signatures in terms of form and distribution signatures that behave consistently across a variety of languages. Critically, our measures and models are entirely language-agnostic, yet perform well across all languages studied. We find that while there is a high degree of consistency in the use of the terms inflection and derivation in terms of our measures, there are still many constructions near the model’s decision boundary between the two categories, indicating a gradient, rather than categorical, distinction.</abstract>
<identifier type="citekey">haley-etal-2023-language</identifier>
<identifier type="doi">10.18653/v1/2023.sigtyp-1.18</identifier>
<location>
<url>https://aclanthology.org/2023.sigtyp-1.18</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>150</start>
<end>152</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language-Agnostic Measures Discriminate Inflection and Derivation
%A Haley, Coleman
%A Ponti, Edoardo M.
%A Goldwater, Sharon
%Y Beinborn, Lisa
%Y Goswami, Koustava
%Y Muradoğlu, Saliha
%Y Sorokin, Alexey
%Y Kumar, Ritesh
%Y Shcherbakov, Andreas
%Y Ponti, Edoardo M.
%Y Cotterell, Ryan
%Y Vylomova, Ekaterina
%S Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F haley-etal-2023-language
%X In morphology, a distinction is commonly drawn between inflection and derivation. However, a precise definition of this distinction which captures the way the terms are used across languages remains elusive within linguistic theory, typically being based on subjective tests. In this study, we present 4 quantitative measures which use the statistics of a raw text corpus in a language to estimate how much and how variably a morphological construction changes aspects of the lexical entry, specifically, the word’s form and the word’s semantic and syntactic properties (as operationalised by distributional word embeddings). Based on a sample of 26 languages, we find that we can reconstruct 90% of the classification of constructions into inflection and derivation in Unimorph using our 4 measures, providing large-scale cross-linguistic evidence that the concepts of inflection and derivation are associated with measurable signatures in terms of form and distribution signatures that behave consistently across a variety of languages. Critically, our measures and models are entirely language-agnostic, yet perform well across all languages studied. We find that while there is a high degree of consistency in the use of the terms inflection and derivation in terms of our measures, there are still many constructions near the model’s decision boundary between the two categories, indicating a gradient, rather than categorical, distinction.
%R 10.18653/v1/2023.sigtyp-1.18
%U https://aclanthology.org/2023.sigtyp-1.18
%U https://doi.org/10.18653/v1/2023.sigtyp-1.18
%P 150-152
Markdown (Informal)
[Language-Agnostic Measures Discriminate Inflection and Derivation](https://aclanthology.org/2023.sigtyp-1.18) (Haley et al., SIGTYP 2023)
ACL