Cross-Lingual IPA Contrastive Learning for Zero-Shot NER
This addresses NER for low-resource languages, offering a domain-specific improvement over existing phonemic methods.
The paper tackles zero-shot Named Entity Recognition for low-resource languages by reducing phonemic representation gaps between languages, proposing a CONLIPA dataset with IPA pairs and an IPAC contrastive learning method that achieves substantial average gains over baselines.
Existing approaches to zero-shot Named Entity Recognition (NER) for low-resource languages have primarily relied on machine translation, whereas more recent methods have shifted focus to phonemic representation. Building upon this, we investigate how reducing the phonemic representation gap in IPA transcription between languages with similar phonetic characteristics enables models trained on high-resource languages to perform effectively on low-resource languages. In this work, we propose CONtrastive Learning with IPA (CONLIPA) dataset containing 10 English and high resource languages IPA pairs from 10 frequently used language families. We also propose a cross-lingual IPA Contrastive learning method (IPAC) using the CONLIPA dataset. Furthermore, our proposed dataset and methodology demonstrate a substantial average gain when compared to the best performing baseline.