Robust Generalization Strategies for Morpheme Glossing in an Endangered Language Documentation Context
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909158610042880 |
|---|---|
| author | Ginn, Michael Palmer, Alexis |
| author_facet | Ginn, Michael Palmer, Alexis |
| contents | Generalization is of particular importance in resource-constrained settings, where the available training data may represent only a small fraction of the distribution of possible texts. We investigate the ability of morpheme labeling models to generalize by evaluating their performance on unseen genres of text, and we experiment with strategies for closing the gap between performance on in-distribution and out-of-distribution data. Specifically, we use weight decay optimization, output denoising, and iterative pseudo-labeling, and achieve a 2% improvement on a test set containing texts from unseen genres. All experiments are performed using texts written in the Mayan language Uspanteko. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_02777 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Robust Generalization Strategies for Morpheme Glossing in an Endangered Language Documentation Context Ginn, Michael Palmer, Alexis Computation and Language Machine Learning Generalization is of particular importance in resource-constrained settings, where the available training data may represent only a small fraction of the distribution of possible texts. We investigate the ability of morpheme labeling models to generalize by evaluating their performance on unseen genres of text, and we experiment with strategies for closing the gap between performance on in-distribution and out-of-distribution data. Specifically, we use weight decay optimization, output denoising, and iterative pseudo-labeling, and achieve a 2% improvement on a test set containing texts from unseen genres. All experiments are performed using texts written in the Mayan language Uspanteko. |
| title | Robust Generalization Strategies for Morpheme Glossing in an Endangered Language Documentation Context |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2311.02777 |