bibtex to appear
Appearing in: 47th European Conference on Information Retrieval (ECIR 2025)
Abstract:
Globalisation and colonisation have led the vast majority of the world to use only a fraction of languages, such as English and French, to communicate, excluding many others. This has severely affected the survivability of many now-deemed vulnerable or endangered languages, such as Occitan and Sicilian. These languages often share some characteristics, such as elements of their grammar and lexicon, with other high-resource languages, e.g. French or Italian. They can be clustered into groups of language varieties with various degrees of mutual intelligibility. Current search systems are not usually trained on many of these low-resource varieties, leading search users to express their needs in a high-resource one instead. This problem is further complicated when most information content is expressed in a high-resource language, inhibiting even more retrieval in low-resource languages. We show that current search systems are not robust across language varieties, severely affecting retrieval effectiveness. Therefore, it would be desirable for these systems to leverage the capabilities of neural models to bridge the differences between these varieties. This can allow users to express their needs in their low-resource variety and retrieve the most relevant documents in a high-resource one. To address this, we propose fine-tuning neural rankers on pairs of language varieties, thereby exposing them to their linguistic similarities. We find that this approach improves the performance of the varieties upon which the models were directly trained, thereby regularising these models to generalise and perform better even on unseen language variety pairs. We additionally explore whether this approach can transfer across language families, where we observe mixed results, which opens doors for future research.
BibTeX @inproceedings{chari:ecir2025-lowresource, author = {Chari, Andreas and MacAvaney, Sean and Ounis, Iadh}, title = {Improving Low-Resource Retrieval Effectiveness using Zero-Shot Linguistic Similarity Transfer}, booktitle = {47th European Conference on Information Retrieval}, year = {2025} }