Number theory meets linguistics: modelling noun pluralisation across 1497 languages using 2-adic metrics

Gregory Baker; Diego Molla-Aliod

doi:10.18653/v1/2022.aacl-short.4

Number theory meets linguistics: modelling noun pluralisation across 1497 languages using 2-adic metrics

Gregory Baker, Diego Molla-Aliod

School of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

Abstract

A simple machine learning model of pluralisation as a linear regression problem minimising a p-adic metric substantially outperforms even the most robust of Euclidean-space regressors on languages in the Indo-European, Austronesian, Trans New-Guinea, Sino-Tibetan, Nilo-Saharan, Oto-Meanguean and Atlantic-Congo language families. There is insufficient evidence to support modelling distinct noun declensions as a p-adic neighbourhood even in Indo-European languages.

Original language	English
Title of host publication	Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (volume 2: short papers)
Place of Publication	Stroudsburg
Publisher	Association for Computational Linguistics (ACL)
Pages	24-32
Number of pages	9
ISBN (Electronic)	9781955917643
DOIs	https://doi.org/10.18653/v1/2022.aacl-short.4
Publication status	Published - 2022
Event	The 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing - Online Duration: 20 Nov 2022 → 23 Nov 2022

Conference

Conference	The 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing
Abbreviated title	AACL-IJCNLP 2022
City	Online
Period	20/11/22 → 23/11/22

Access to Document

10.18653/v1/2022.aacl-short.4Licence: Unspecified

Cite this

Baker, G., & Molla-Aliod, D. (2022). Number theory meets linguistics: modelling noun pluralisation across 1497 languages using 2-adic metrics. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (volume 2: short papers) (pp. 24-32). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2022.aacl-short.4

Baker, Gregory ; Molla-Aliod, Diego. / Number theory meets linguistics : modelling noun pluralisation across 1497 languages using 2-adic metrics. Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (volume 2: short papers). Stroudsburg : Association for Computational Linguistics (ACL), 2022. pp. 24-32

@inproceedings{7901fe265c2946af859cee0ec6ba5db3,

title = "Number theory meets linguistics: modelling noun pluralisation across 1497 languages using 2-adic metrics",

abstract = "A simple machine learning model of pluralisation as a linear regression problem minimising a p-adic metric substantially outperforms even the most robust of Euclidean-space regressors on languages in the Indo-European, Austronesian, Trans New-Guinea, Sino-Tibetan, Nilo-Saharan, Oto-Meanguean and Atlantic-Congo language families. There is insufficient evidence to support modelling distinct noun declensions as a p-adic neighbourhood even in Indo-European languages.",

author = "Gregory Baker and Diego Molla-Aliod",

year = "2022",

doi = "10.18653/v1/2022.aacl-short.4",

language = "English",

pages = "24--32",

booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (volume 2: short papers)",

publisher = "Association for Computational Linguistics (ACL)",

note = "The 2nd Conference of the Asia-Pacific Chapter of the Association for<br/>Computational Linguistics and the 12th International Joint Conference on Natural Language Processing, AACL-IJCNLP 2022 ; Conference date: 20-11-2022 Through 23-11-2022",

}

Baker, G & Molla-Aliod, D 2022, Number theory meets linguistics: modelling noun pluralisation across 1497 languages using 2-adic metrics. in Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (volume 2: short papers). Association for Computational Linguistics (ACL), Stroudsburg, pp. 24-32, The 2nd Conference of the Asia-Pacific Chapter of the Association for
Computational Linguistics and the 12th International Joint Conference on Natural Language Processing, Online, 20/11/22. https://doi.org/10.18653/v1/2022.aacl-short.4

Number theory meets linguistics: modelling noun pluralisation across 1497 languages using 2-adic metrics. / Baker, Gregory ; Molla-Aliod, Diego.
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (volume 2: short papers). Stroudsburg: Association for Computational Linguistics (ACL), 2022. p. 24-32.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - Number theory meets linguistics

T2 - The 2nd Conference of the Asia-Pacific Chapter of the Association for<br/>Computational Linguistics and the 12th International Joint Conference on Natural Language Processing

AU - Baker, Gregory

AU - Molla-Aliod, Diego

PY - 2022

Y1 - 2022

N2 - A simple machine learning model of pluralisation as a linear regression problem minimising a p-adic metric substantially outperforms even the most robust of Euclidean-space regressors on languages in the Indo-European, Austronesian, Trans New-Guinea, Sino-Tibetan, Nilo-Saharan, Oto-Meanguean and Atlantic-Congo language families. There is insufficient evidence to support modelling distinct noun declensions as a p-adic neighbourhood even in Indo-European languages.

AB - A simple machine learning model of pluralisation as a linear regression problem minimising a p-adic metric substantially outperforms even the most robust of Euclidean-space regressors on languages in the Indo-European, Austronesian, Trans New-Guinea, Sino-Tibetan, Nilo-Saharan, Oto-Meanguean and Atlantic-Congo language families. There is insufficient evidence to support modelling distinct noun declensions as a p-adic neighbourhood even in Indo-European languages.

UR - https://www.scopus.com/pages/publications/105027095494

U2 - 10.18653/v1/2022.aacl-short.4

DO - 10.18653/v1/2022.aacl-short.4

M3 - Conference proceeding contribution

SP - 24

EP - 32

BT - Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (volume 2: short papers)

PB - Association for Computational Linguistics (ACL)

CY - Stroudsburg

Y2 - 20 November 2022 through 23 November 2022

ER -

Baker G , Molla-Aliod D. Number theory meets linguistics: modelling noun pluralisation across 1497 languages using 2-adic metrics. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (volume 2: short papers). Stroudsburg: Association for Computational Linguistics (ACL). 2022. p. 24-32 doi: 10.18653/v1/2022.aacl-short.4

Number theory meets linguistics: modelling noun pluralisation across 1497 languages using 2-adic metrics

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this