Automated Cognate Detection as a Supervised Link Prediction Task with Cognate Transformer
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910319438200832 |
|---|---|
| author | Akavarapu, V. S. D. S. Mahesh Bhattacharya, Arnab |
| author_facet | Akavarapu, V. S. D. S. Mahesh Bhattacharya, Arnab |
| contents | Identification of cognates across related languages is one of the primary problems in historical linguistics. Automated cognate identification is helpful for several downstream tasks including identifying sound correspondences, proto-language reconstruction, phylogenetic classification, etc. Previous state-of-the-art methods for cognate identification are mostly based on distributions of phonemes computed across multilingual wordlists and make little use of the cognacy labels that define links among cognate clusters. In this paper, we present a transformer-based architecture inspired by computational biology for the task of automated cognate detection. Beyond a certain amount of supervision, this method performs better than the existing methods, and shows steady improvement with further increase in supervision, thereby proving the efficacy of utilizing the labeled information. We also demonstrate that accepting multiple sequence alignments as input and having an end-to-end architecture with link prediction head saves much computation time while simultaneously yielding superior performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_02926 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Automated Cognate Detection as a Supervised Link Prediction Task with Cognate Transformer Akavarapu, V. S. D. S. Mahesh Bhattacharya, Arnab Computation and Language Machine Learning Social and Information Networks I.2.7 Identification of cognates across related languages is one of the primary problems in historical linguistics. Automated cognate identification is helpful for several downstream tasks including identifying sound correspondences, proto-language reconstruction, phylogenetic classification, etc. Previous state-of-the-art methods for cognate identification are mostly based on distributions of phonemes computed across multilingual wordlists and make little use of the cognacy labels that define links among cognate clusters. In this paper, we present a transformer-based architecture inspired by computational biology for the task of automated cognate detection. Beyond a certain amount of supervision, this method performs better than the existing methods, and shows steady improvement with further increase in supervision, thereby proving the efficacy of utilizing the labeled information. We also demonstrate that accepting multiple sequence alignments as input and having an end-to-end architecture with link prediction head saves much computation time while simultaneously yielding superior performance. |
| title | Automated Cognate Detection as a Supervised Link Prediction Task with Cognate Transformer |
| topic | Computation and Language Machine Learning Social and Information Networks I.2.7 |
| url | https://arxiv.org/abs/2402.02926 |