paper-with-me

Papers

MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning

2021-04-16 · NAACL 2021 4 · Mengzhou Xia, Guoqing Zheng, Subhabrata Mukherjee, Milad Shokouhi, Graham Neubig, Ahmed Hassan Awadallah

The combination of multilingual pre-trained representations and cross-lingual transfer learning is one of the most effective methods for building functional NLP systems for low-resource languages. However, for extremely low-resource languages without large-scale monolingual corpora for pre-training or sufficient annotated data for fine-tuning, transfer learning remains an under-studied and challenging task. Moreover, recent work shows that multilingual representations are surprisingly disjoint across languages, bringing additional challenges for transfer onto extremely low-resource languages. In this paper, we propose MetaXL, a meta-learning based framework that learns to transform representations judiciously from auxiliary languages to a target one and brings their representation spaces closer for effective transfer. Extensive experiments on real-world low-resource languages - without access to large-scale monolingual corpora or large amounts of labeled data - for tasks like cross-lingual sentiment analysis and named entity recognition show the effectiveness of our approach. Code for MetaXL is publicly available at github.com/microsoft/MetaXL.

📄 PDF Abstract BibTeX arXiv:2104.07908

Code (2)

microsoft/MetaXL 공식 구현 pytorch
liatb282/metaxlr pytorch

Tasks

Cross-Lingual TransferMeta-Learningnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Sentiment AnalysisTransfer Learning

Similar Papers 제목 키워드 기반

MetaXLR -- Mixed Language Meta Representation Transformation for Low-resource Cross-lingual Learning based on Multi-Armed Bandit

2023-05-31 · Liat Bezalel, Eyal Orgad

Transfer learning for extremely low resource languages is a challenging task as there is no large scale monolingual corpora for pre training or sufficient annotated data for fine tuning. We follow the work of MetaXL whic…

Meta-LearningNERTransfer Learning

EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimization

2021-06-19 · NeurIPS 2021 12 · Ondrej Bohdal, Yongxin Yang, Timothy Hospedales

Gradient-based meta-learning and hyperparameter optimization have seen significant progress recently, enabling practical end-to-end training of neural networks together with many hyperparameters. Nevertheless, existing a…

Cross-Domain Few-Shotcross-domain few-shot learningFew-Shot LearningHyperparameter Optimization+1

A Common Semantic Space for Monolingual and Cross-Lingual Meta-Embeddings

2020-01-17 · Iker García-Ferrero, Rodrigo Agerri, German Rigau

This paper presents a new technique for creating monolingual and cross-lingual meta-embeddings. Our method integrates multiple word embeddings created from complementary techniques, textual sources, knowledge bases and l…

Cross-Lingual TransferPOSPOS TaggingSemantic Textual Similarity+3

MetaEnzyme: Meta Pan-Enzyme Learning for Task-Adaptive Redesign

2024-08-05 · Jiangbin Zheng, Han Zhang, Qianqing Xu, An-Ping Zeng 외

Enzyme design plays a crucial role in both industrial production and biology. However, this field faces challenges due to the lack of comprehensive benchmarks and the complexity of enzyme design tasks, leading to a deart…

FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers

2019-12-29 · Haohang Xu, Hongkai Xiong, Guo-Jun Qi

One of the most significant challenges facing a few-shot learning task is the generalizability of the (meta-)model from the base to the novel categories. Most of existing few-shot learning models attempt to address this …

Data AugmentationFew-Shot LearningNovel Concepts