Zero-Shot Cross-Lingual NER Using Phonemic Representations for Low-Resource Languages
- URL: http://arxiv.org/abs/2406.16030v1
- Date: Sun, 23 Jun 2024 06:38:56 GMT
- Title: Zero-Shot Cross-Lingual NER Using Phonemic Representations for Low-Resource Languages
- Authors: Jimin Sohn, Haeji Jung, Alex Cheng, Jooeon Kang, Yilin Du, David R. Mortensen,
- Abstract summary: Existing zero-shot cross-lingual NER approaches require substantial prior knowledge of the target language.
We propose a novel approach to NER using phonemic representation based on the International Phonetic Alphabet (IPA) to bridge the gap between representations of different languages.
- Score: 5.580028223598989
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Existing zero-shot cross-lingual NER approaches require substantial prior knowledge of the target language, which is impractical for low-resource languages. In this paper, we propose a novel approach to NER using phonemic representation based on the International Phonetic Alphabet (IPA) to bridge the gap between representations of different languages. Our experiments show that our method significantly outperforms baseline models in extremely low-resource languages, with the highest average F-1 score (46.38%) and lowest standard deviation (12.67), particularly demonstrating its robustness with non-Latin scripts.
Related papers
- Low-Resource Named Entity Recognition with Cross-Lingual, Character-Level Neural Conditional Random Fields [68.17213992395041]
Low-resource named entity recognition is still an open problem in NLP.
We present a transfer learning scheme, whereby we train character-level neural CRFs to predict named entities for both high-resource languages and low resource languages jointly.
arXiv Detail & Related papers (2024-04-14T23:44:49Z) - Multilingual Word Embeddings for Low-Resource Languages using Anchors
and a Chain of Related Languages [54.832599498774464]
We propose to build multilingual word embeddings (MWEs) via a novel language chain-based approach.
We build MWEs one language at a time by starting from the resource rich source and sequentially adding each language in the chain till we reach the target.
We evaluate our method on bilingual lexicon induction for 4 language families, involving 4 very low-resource (5M tokens) and 4 moderately low-resource (50M) target languages.
arXiv Detail & Related papers (2023-11-21T09:59:29Z) - Efficient Spoken Language Recognition via Multilabel Classification [53.662747523872305]
We show that our models obtain competitive results while being orders of magnitude smaller and faster than current state-of-the-art methods.
Our multilabel strategy is more robust to unseen non-target languages compared to multiclass classification.
arXiv Detail & Related papers (2023-06-02T23:04:19Z) - Language-universal phonetic encoder for low-resource speech recognition [28.21805271848413]
We leverage International Phonetic Alphabet (IPA) based language-universal phonetic model to improve low-resource ASR performances.
Our approach and adaptation are effective on extremely low-resource languages, even within domain- and language-mismatched scenarios.
arXiv Detail & Related papers (2023-05-19T10:24:30Z) - Language-Universal Phonetic Representation in Multilingual Speech
Pretraining for Low-Resource Speech Recognition [28.21805271848413]
We leverage an International Phonetic Alphabet (IPA) multilingual model to create frame-level pseudo labels for unlabeled speech.
We use these pseudo labels to guide hidden-unit BERT (HuBERT) based speech pretraining in a phonetically-informed manner.
Our approach outperforms most of the state of the arts, with much less pretraining data in terms of hours and language diversity.
arXiv Detail & Related papers (2023-05-19T10:15:11Z) - Can Character-based Language Models Improve Downstream Task Performance
in Low-Resource and Noisy Language Scenarios? [0.0]
We focus on North-African colloquial dialectal Arabic written using an extension of the Latin script, called NArabizi.
We show that a character-based model trained on only 99k sentences of NArabizi and fined-tuned on a small treebank leads to performance close to those obtained with the same architecture pre-trained on large multilingual and monolingual models.
arXiv Detail & Related papers (2021-10-26T14:59:16Z) - Automatically Identifying Language Family from Acoustic Examples in Low
Resource Scenarios [48.57072884674938]
We propose a method to analyze language similarity using deep learning.
Namely, we train a model on the Wilderness dataset and investigate how its latent space compares with classical language family findings.
arXiv Detail & Related papers (2020-12-01T22:44:42Z) - Building Low-Resource NER Models Using Non-Speaker Annotation [58.78968578460793]
Cross-lingual methods have had notable success in addressing these concerns.
We propose a complementary approach to building low-resource Named Entity Recognition (NER) models using non-speaker'' (NS) annotations.
We show that use of NS annotators produces results that are consistently on par or better than cross-lingual methods built on modern contextual representations.
arXiv Detail & Related papers (2020-06-17T03:24:38Z) - That Sounds Familiar: an Analysis of Phonetic Representations Transfer
Across Languages [72.9927937955371]
We use the resources existing in other languages to train a multilingual automatic speech recognition model.
We observe significant improvements across all languages in the multilingual setting, and stark degradation in the crosslingual setting.
Our analysis uncovered that even the phones that are unique to a single language can benefit greatly from adding training data from other languages.
arXiv Detail & Related papers (2020-05-16T22:28:09Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.