Semisupervised Neural Proto-Language Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Liang, Xie, Peirong, Mortensen, David R.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914908380069888
author Lu, Liang
Xie, Peirong
Mortensen, David R.
author_facet Lu, Liang
Xie, Peirong
Mortensen, David R.
contents Existing work implementing comparative reconstruction of ancestral languages (proto-languages) has usually required full supervision. However, historical reconstruction models are only of practical value if they can be trained with a limited amount of labeled data. We propose a semisupervised historical reconstruction task in which the model is trained on only a small amount of labeled data (cognate sets with proto-forms) and a large amount of unlabeled data (cognate sets without proto-forms). We propose a neural architecture for comparative reconstruction (DPD-BiReconstructor) incorporating an essential insight from linguists' comparative method: that reconstructed words should not only be reconstructable from their daughter words, but also deterministically transformable back into their daughter words. We show that this architecture is able to leverage unlabeled cognate sets to outperform strong semisupervised baselines on this novel task.
format Preprint
id arxiv_https___arxiv_org_abs_2406_05930
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Semisupervised Neural Proto-Language Reconstruction
Lu, Liang
Xie, Peirong
Mortensen, David R.
Computation and Language
Existing work implementing comparative reconstruction of ancestral languages (proto-languages) has usually required full supervision. However, historical reconstruction models are only of practical value if they can be trained with a limited amount of labeled data. We propose a semisupervised historical reconstruction task in which the model is trained on only a small amount of labeled data (cognate sets with proto-forms) and a large amount of unlabeled data (cognate sets without proto-forms). We propose a neural architecture for comparative reconstruction (DPD-BiReconstructor) incorporating an essential insight from linguists' comparative method: that reconstructed words should not only be reconstructable from their daughter words, but also deterministically transformable back into their daughter words. We show that this architecture is able to leverage unlabeled cognate sets to outperform strong semisupervised baselines on this novel task.
title Semisupervised Neural Proto-Language Reconstruction
topic Computation and Language
url https://arxiv.org/abs/2406.05930