SenWiCh: Sense-Annotation of Low-Resource Languages for WiC using Hybrid Methods

This paper addresses the critical need for high-quality evaluation datasets in low-resource languages to advance cross-lingual transfer. While cross-lingual transfer offers a key strategy for leveraging multilingual pretraining to expand language technologies to understudied and typologically diverse languages, its effectiveness is dependent on quality and suitable benchmarks. We release new sense-annotated datasets of sentences containing polysemous words, spanning nine low-resource languages across diverse language families and scripts. To facilitate dataset creation, the paper presents a demonstrably beneficial semi-automatic annotation method. The utility of the datasets is demonstrated through Word-in-Context (WiC) formatted experiments that evaluate transfer on these low-resource languages. Results highlight the importance of targeted dataset creation and evaluation for effective polysemy disambiguation in low-resource settings and transfer studies. The released datasets and code aim to support further research into fair, robust, and truly multilingual NLP.

@article{goworek2025_2505.23714,
  title={ SenWiCh: Sense-Annotation of Low-Resource Languages for WiC using Hybrid Methods },
  author={ Roksana Goworek and Harpal Karlcut and Muhammad Shezad and Nijaguna Darshana and Abhishek Mane and Syam Bondada and Raghav Sikka and Ulvi Mammadov and Rauf Allahverdiyev and Sriram Purighella and Paridhi Gupta and Muhinyia Ndegwa and Haim Dubossarsky },
  journal={arXiv preprint arXiv:2505.23714},
  year={ 2025 }
}