Papers with historical linguistics
Automated Cognate Detection as a Supervised Link Prediction Task with Cognate Transformer (2024.eacl-long)
Copied to clipboard
| Challenge: | Existing methods for cognate identification are based on distributions of phonemes and make little use of cognacy labels. |
| Approach: | They propose a transformer-based architecture inspired by computational biology for automated cognate detection. |
| Outcome: | The proposed architecture performs better than existing methods with increased supervision. |
Combining Information-Weighted Sequence Alignment and Sound Correspondence Models for Improved Cognate Detection (C18-1)
Copied to clipboard
| Challenge: | a new approach to cognate detection is proposed to capture the remaining similarities between cognate word forms after thousands of years of divergence. |
| Approach: | They propose a method which uses information weighting and sound correspondence modeling to improve cognate detection. |
| Outcome: | The proposed approach improves on the measure of form similarity and distance-based cognate clustering. |
Cognate Transformer for Automated Phonological Reconstruction and Cognate Reflex Prediction (2023.emnlp-main)
Copied to clipboard
| Challenge: | Phonological reconstruction is one of the central problems in historical linguistics where a proto-word of an ancestral language is determined from the observed cognate words of daughter languages. |
| Approach: | They propose to use a protein language model to train on multiple sequence alignments to train a model on phonological reconstruction. |
| Outcome: | The proposed model outperforms existing models on cognate reflex prediction task. |
Querying a Dozen Corpora and a Thousand Years with Fintan (2022.lrec-1)
Copied to clipboard
| Challenge: | Large-scale quantitative diachronic corpus studies are difficult if multiple corpus are to be consulted . multi-layer corpus technology can solve the problem, but it requires the user to run queries manually. |
| Approach: | They propose a platform for studying word order in German using syntactically annotated corpora . fintan is a flexible integrated transformation and annotation platform . |
| Outcome: | The proposed platform can be used to study word order in German . it hints at two major phases in the development of scrambling in modern german . |
Pater Incertus? There Is a Solution: Automatic Discrimination between Cognates and Borrowings for Romance Languages (2024.lrec-main)
Copied to clipboard
Liviu P. Dinu, Ana Sabina Uban, Ioan-Bogdan Iordache, Alina Maria Cristea, Simona Georgescu, Laurentiu Zoicas
| Challenge: | Existing methods for discriminating between cognates and borrowings are difficult, but they provide a deeper insight into the history of a language and allow for a better characterization of language relatedness. |
| Approach: | They propose a computational approach for discriminating between cognates and borrowings based on a comprehensive database of Romance cognates. |
| Outcome: | The proposed approach is the most comprehensive in terms of covered languages. |