Cross-Lingual IPA Contrastive Learning for Zero-Shot NER
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 26 of its 30 references that are in the map. First posted on arXiv 10 Mar 2025.
Builds on
26 of 30 references.
References · 26
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,588
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,009
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,712
- 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,215
- 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,397
- 2019A Theoretical Analysis of Contrastive Unsupervised Representation Learningcited by 530
- 2020Understanding the Behaviour of Contrastive Losscited by 397
- 2021Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Losscited by 312
- 2021CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representationcited by 231
- 2020Predicting What You Already Know Helps: Provable Self-Supervised Learningcited by 152
- 2020Contrastive learning, multi-view redundancy, and linear modelscited by 146
14 more
- 2021Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learningcited by 119
- 2022Understanding Contrastive Learning Requires Incorporating Inductive Biasescited by 96
- 2022How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learningcited by 65
- 2020Understanding Self-supervised Learning with Dual Deep Networkscited by 62
- 2022ByT5 model for massively multilingual grapheme-to-phoneme conversioncited by 49
- 2018Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representationscited by 18
- 2023XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speechcited by 16
- 2023mCL-NER: Cross-Lingual Named Entity Recognition via Multi-view Contrastive Learningcited by 14
- 2023ZGUL: Zero-shot Generalization to Unseen Languages using Multi-source Ensembling of Language Adapterscited by 10
- 2024On the Comparison between Multi-modal and Single-modal Contrastive Learningcited by 10
- 2025Temperature-Free Loss Function for Contrastive Learningcited by 7
- 2023PWESuite: Phonetic Word Embeddings and Tasks They Facilitatecited by 6
- 2024Phoneme-Level Contrastive Learning for User-Defined Keyword Spotting with Flexible Enrollmentcited by 5
- 2023IPA-CLIP: Integrating Phonetic Priors into Vision and Language Pretrainingcited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.