Working Towards Digital Documentation of Uralic Languages With Open-Source Tools and Modern NLP Methods

Mika Hämäläinen; Jack Rueter; Khalid Alnajjar; Niko Partanen

Working Towards Digital Documentation of Uralic Languages With Open-Source Tools and Modern NLP Methods

Mika Hämäläinen, Jack Rueter, Khalid Alnajjar, Niko Partanen

Department of Digital Humanities

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

Abstract

We present our work towards building an infrastructure for documenting endangered languages with the focus on Uralic languages in particular. Our infrastructure consists of tools to write dictionaries so that entries are structured in XML format. These dictionaries are the foundation for rule-based NLP tools such as FSTs. We also work actively towards enhancing these dictionaries and tools by using the latest state-of-the-art neural models by generating training data through rules and lexica.

Original language	English
Title of host publication	Proceedings of the Big Picture Workshop
Editors	Yanai Elazar, Allyson Ettinger, Norea Kassner, Sebastian Ruder, Noah A. Smith
Number of pages	10
Place of Publication	Stroudsburg
Publisher	The Association for Computational Linguistics
Publication date	2023
Pages	18-27
ISBN (Electronic)	979-8-89176-051-6
Publication status	Published - 2023
MoE publication type	A4 Article in conference proceedings
Event	The Big Picture Workshop - , Singapore Duration: 7 Dec 2023 → 7 Dec 2023

Fields of Science

6121 Languages
113 Computer and information sciences

Access to Document

2023.bigpicture-1.2Final published version, 1.58 MBLicence: CC BY

https://aclanthology.org/2023.bigpicture-1.2/Licence: CC BY

1 Consultancy

Language facilitator
Trosterud, T. (Consultant), Moshagen, S. (Consultant), Rueter, J. (Consultant), Antonsen, L. (Consultant), Uibo, H. (Consultant), Gerstenberger, C. (Consultant), Fedina, M. (Consultant), Kaalep, H.-J. (Consultant) & Ernstreits, V. (Consultant)
Aug 2004 → …
Activity: Consultancy types › Consultancy

Cite this

Hämäläinen, M., Rueter, J., Alnajjar, K., & Partanen, N. (2023). Working Towards Digital Documentation of Uralic Languages With Open-Source Tools and Modern NLP Methods. In Y. Elazar, A. Ettinger, N. Kassner, S. Ruder, & N. A. Smith (Eds.), Proceedings of the Big Picture Workshop (pp. 18-27). The Association for Computational Linguistics. https://aclanthology.org/2023.bigpicture-1.2/

Hämäläinen, Mika ; Rueter, Jack ; Alnajjar, Khalid et al. / Working Towards Digital Documentation of Uralic Languages With Open-Source Tools and Modern NLP Methods. Proceedings of the Big Picture Workshop. editor / Yanai Elazar ; Allyson Ettinger ; Norea Kassner ; Sebastian Ruder ; Noah A. Smith. Stroudsburg : The Association for Computational Linguistics, 2023. pp. 18-27

@inproceedings{a287ad80fe9b47bea4ebf12218ca89bd,

title = "Working Towards Digital Documentation of Uralic Languages With Open-Source Tools and Modern NLP Methods",

abstract = "We present our work towards building an infrastructure for documenting endangered languages with the focus on Uralic languages in particular. Our infrastructure consists of tools to write dictionaries so that entries are structured in XML format. These dictionaries are the foundation for rule-based NLP tools such as FSTs. We also work actively towards enhancing these dictionaries and tools by using the latest state-of-the-art neural models by generating training data through rules and lexica.",

keywords = "6121 Languages, 113 Computer and information sciences",

author = "Mika H{\"a}m{\"a}l{\"a}inen and Jack Rueter and Khalid Alnajjar and Niko Partanen",

year = "2023",

language = "English",

pages = "18--27",

editor = "Yanai Elazar and Ettinger, {Allyson } and Norea Kassner and Ruder, {Sebastian } and Smith, {Noah A. }",

booktitle = "Proceedings of the Big Picture Workshop",

publisher = "The Association for Computational Linguistics",

address = "United States",

note = "The Big Picture Workshop<br/> ; Conference date: 07-12-2023 Through 07-12-2023",

}

Hämäläinen, M, Rueter, J, Alnajjar, K & Partanen, N 2023, Working Towards Digital Documentation of Uralic Languages With Open-Source Tools and Modern NLP Methods. in Y Elazar, A Ettinger, N Kassner, S Ruder & NA Smith (eds), Proceedings of the Big Picture Workshop. The Association for Computational Linguistics, Stroudsburg, pp. 18-27, The Big Picture Workshop
, Singapore, 07/12/2023. <https://aclanthology.org/2023.bigpicture-1.2/>

Working Towards Digital Documentation of Uralic Languages With Open-Source Tools and Modern NLP Methods. / Hämäläinen, Mika; Rueter, Jack; Alnajjar, Khalid et al.
Proceedings of the Big Picture Workshop. ed. / Yanai Elazar; Allyson Ettinger; Norea Kassner; Sebastian Ruder; Noah A. Smith. Stroudsburg: The Association for Computational Linguistics, 2023. p. 18-27.

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

TY - GEN

T1 - Working Towards Digital Documentation of Uralic Languages With Open-Source Tools and Modern NLP Methods

AU - Hämäläinen, Mika

AU - Rueter, Jack

AU - Alnajjar, Khalid

AU - Partanen, Niko

PY - 2023

Y1 - 2023

N2 - We present our work towards building an infrastructure for documenting endangered languages with the focus on Uralic languages in particular. Our infrastructure consists of tools to write dictionaries so that entries are structured in XML format. These dictionaries are the foundation for rule-based NLP tools such as FSTs. We also work actively towards enhancing these dictionaries and tools by using the latest state-of-the-art neural models by generating training data through rules and lexica.

AB - We present our work towards building an infrastructure for documenting endangered languages with the focus on Uralic languages in particular. Our infrastructure consists of tools to write dictionaries so that entries are structured in XML format. These dictionaries are the foundation for rule-based NLP tools such as FSTs. We also work actively towards enhancing these dictionaries and tools by using the latest state-of-the-art neural models by generating training data through rules and lexica.

KW - 6121 Languages

KW - 113 Computer and information sciences

M3 - Conference contribution

SP - 18

EP - 27

BT - Proceedings of the Big Picture Workshop

A2 - Elazar, Yanai

A2 - Ettinger, Allyson

A2 - Kassner, Norea

A2 - Ruder, Sebastian

A2 - Smith, Noah A.

PB - The Association for Computational Linguistics

CY - Stroudsburg

T2 - The Big Picture Workshop<br/>

Y2 - 7 December 2023 through 7 December 2023

ER -

Working Towards Digital Documentation of Uralic Languages With Open-Source Tools and Modern NLP Methods

Abstract

Fields of Science

Access to Document

Activities

Language facilitator

Cite this