Neural Borrowing Detection with Monolingual Lexical Models

John E. Miller, Emanuel Pariasca, César A. Beltrán Castañón

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Identification of lexical borrowings, transfer of words between languages, is an essential practice of historical linguistics and a vital tool in analysis of language contact and cultural events in general. We seek to improve tools for automatic detection of lexical borrowings, focusing here on detecting borrowed words from monolingual wordlists. Starting with a recurrent neural network lexical model and competing entropies approach, we incorporate a more current Transformer based lexical model. From there we experiment with several different models and approaches including a lexical donor model with augmented wordlist. The Transformer model reduces execution time and minimally improves borrowing detection, and the augmented donor model shows some promise. A substantive change in approach or model seems necessary for significant gains in detection of lexical borrowings.

Original languageEnglish
Title of host publicationProceedings of the 1stWorkshop on Multimodal Machine Translation for Low Resource Languages, MMTLRL 2021 in conjunction with International Conference on Recent Advances in Natural Language Processing, RANLP 2021
EditorsReinhard Rapp, Thoudam Doren Singh, Cristina Espana i Bonet, Reinhard Rapp, Sivaji Bandyopadhyay, Serge Sharoff, Josef Van Genabith, Pierre Zweigenbaum
PublisherIncoma Ltd
Pages109-117
Number of pages9
ISBN (Electronic)9789544520731, 9789544520762
DOIs
StatePublished - 2021
Event2021 Student Research Workshop, SRW 2021 associated with the International Conference on Recent Advances in Natural Language Processing, RANLP 2021 - Virtual, Online
Duration: 1 Sep 20213 Sep 2021

Publication series

NameInternational Conference Recent Advances in Natural Language Processing, RANLP
Volume2021-September
ISSN (Print)1313-8502

Conference

Conference2021 Student Research Workshop, SRW 2021 associated with the International Conference on Recent Advances in Natural Language Processing, RANLP 2021
CityVirtual, Online
Period1/09/213/09/21

Fingerprint

Dive into the research topics of 'Neural Borrowing Detection with Monolingual Lexical Models'. Together they form a unique fingerprint.

Cite this