BROWSE
Detail
Conference Paper
Harnessing Linguistic Dissimilarity for Language Generalization on Unseen Low-Resource Varieties
- Authors
- Jinju Kim, Haeji Jung, Youjeong Roh, Jong Hwan Ko, David R. Mortensen
- Issue Date
- 2026-07
- Citation
- Conference on Computational Natural Language Learning (CoNLL) 2026, pp.284-300
- Publisher
- Association for Computational Linguistics
- Language
- English
- Type
- Conference Paper
- Abstract
- Low-resource language varieties used by specific groups remain neglected in the development of Multilingual Language Models. A great deal of cross-lingual research focuses on inter-lingual language transfer which strives to align allied varieties and minimize differences between them. However, for low-resource varieties, linguistic dissimilarity is also an important cue allowing generalization to unseen varieties. Unlike prior approaches, we propose a two-stage Language Generalization framework that focuses on capturing variety-specific cues while also exploiting rich overlap offered by high-resource source variety. First, we propose TOPPing, a source-selection method specifically designed for low-resource varieties. Second, we suggest a lightweight VAÇAÍ-Bowl architecture that learns variety-specific attributes with one branch while a parallel branch captures variety-invariant attributes using adversarial training. We evaluate our framework on structural prediction tasks, which are among the few tasks available, as proxy for performance on other downstream tasks. Using VAÇAÍ-Bowl with TOPPing yields an average 54.62% improvement in the dependency parsing task, which serves as a proxy for performance on other downstream tasks across 10 low-resource varieties.
- KSP Keywords
- Adversarial Training, Dependency Parsing, Multilingual language models, Selection method, Structural prediction, Two-Stage, cross-lingual, low-resource language
This work is distributed under the term of Creative Commons License (CCL)
(CC BY)
(CC BY)
