Cross-Lingual IPA Contrastive Learning for Zero-Shot NER

ACL ARR 2025 February Submission681 Authors

Abstract:

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.

Paper Type: Long

Research Area: Phonology, Morphology and Word Segmentation

Research Area Keywords: zero-shot, named entity recognition, cross-lingual, IPA, phonology

Contribution Types: Approaches to low-resource settings, Data resources

Languages Studied: Amharic, Assyrian, Quechua, Cebuano, Croatian, English, Esperanto, Ilocano, Javanese, Khmer, Kinyarwanda, Kyrgyz, Malay, Malayalam, Maltese, Maori, Marathi, Punjabi, Sinhala, Somali, Tajik, Telugu, Turkmen, Urdu, Uyghur, Uzbek, Yoruba, Swahili, Indonesian, Hindi, Mandarin, Arabic, Vietnamese, Thai, Tamil, Turkish, Korean

Submission Number: 681