Harnessing Test-time Adaptation for NLU tasks Involving Dialects of English
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908603975204864 |
|---|---|
| author | Nguyen, Duke Joshi, Aditya Salim, Flora |
| author_facet | Nguyen, Duke Joshi, Aditya Salim, Flora |
| contents | Test-time domain adaptation (TTDA) is an excellent method which helps generalize models across domains, tasks, and distributions without the use of labeled datasets. Thus, TTDA is very useful in natural language processing (NLP) in the dialectal setting, since oftentimes, models are trained on Standard American English (SAE), evaluated on Indian English (IndE), Singaporean English (SingE), or Nigerian English (NgE), of which distribution differs significantly from the former. This is especially useful since dialectal datasets are scarce. In this paper, we explore one of the most famous TTDA techniques, SHOT, in dialectal NLP. We finetune and evaluate SHOT on different combinations of dialectal GLUE. Our findings show that SHOT is a viable technique when labeled datasets are unavailable. We also theoretically propose the concept of dialectal gap and show that it has a positive correlation with the effectiveness of SHOT. We also find that in many cases, finetuning on SAE yields higher performance than finetuning on dialectal data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12858 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Harnessing Test-time Adaptation for NLU tasks Involving Dialects of English Nguyen, Duke Joshi, Aditya Salim, Flora Computation and Language Machine Learning Test-time domain adaptation (TTDA) is an excellent method which helps generalize models across domains, tasks, and distributions without the use of labeled datasets. Thus, TTDA is very useful in natural language processing (NLP) in the dialectal setting, since oftentimes, models are trained on Standard American English (SAE), evaluated on Indian English (IndE), Singaporean English (SingE), or Nigerian English (NgE), of which distribution differs significantly from the former. This is especially useful since dialectal datasets are scarce. In this paper, we explore one of the most famous TTDA techniques, SHOT, in dialectal NLP. We finetune and evaluate SHOT on different combinations of dialectal GLUE. Our findings show that SHOT is a viable technique when labeled datasets are unavailable. We also theoretically propose the concept of dialectal gap and show that it has a positive correlation with the effectiveness of SHOT. We also find that in many cases, finetuning on SAE yields higher performance than finetuning on dialectal data. |
| title | Harnessing Test-time Adaptation for NLU tasks Involving Dialects of English |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2503.12858 |