Meta-X_NLG: A Meta-Learning Approach Based on Language Clustering for Zero-Shot Cross-Lingual Transfer and Generation

03/19/2022
by   Kaushal Kumar Maurya, et al.
0

Recently, the NLP community has witnessed a rapid advancement in multilingual and cross-lingual transfer research where the supervision is transferred from high-resource languages (HRLs) to low-resource languages (LRLs). However, the cross-lingual transfer is not uniform across languages, particularly in the zero-shot setting. Towards this goal, one promising research direction is to learn shareable structures across multiple tasks with limited annotated data. The downstream multilingual applications may benefit from such a learning setup as most of the languages across the globe are low-resource and share some structures with other languages. In this paper, we propose a novel meta-learning framework (called Meta-X_NLG) to learn shareable structures from typologically diverse languages based on meta-learning and language clustering. This is a step towards uniform cross-lingual transfer for unseen languages. We first cluster the languages based on language representations and identify the centroid language of each cluster. Then, a meta-learning algorithm is trained with all centroid languages and evaluated on the other languages in the zero-shot setting. We demonstrate the effectiveness of this modeling on two NLG tasks (Abstractive Text Summarization and Question Generation), 5 popular datasets and 30 typologically diverse languages. Consistent improvements over strong baselines demonstrate the efficacy of the proposed framework. The careful design of the model makes this end-to-end NLG setup less vulnerable to the accidental translation problem, which is a prominent concern in zero-shot cross-lingual NLG tasks.

READ FULL TEXT

page 9

page 16

research
05/24/2023

Meta-Learning For Vision-and-Language Cross-lingual Transfer

Current pre-trained vison-language models (PVLMs) achieve excellent perf...
research
04/10/2021

Meta-learning for fast cross-lingual adaptation in dependency parsing

Meta-learning, or learning to learn, is a technique that can help to ove...
research
06/02/2021

Minimax and Neyman-Pearson Meta-Learning for Outlier Languages

Model-agnostic meta-learning (MAML) has been recently put forth as a str...
research
03/05/2020

Zero-Shot Cross-Lingual Transfer with Meta Learning

Learning what to share between tasks has been a topic of high importance...
research
06/03/2021

ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation

Despite the recent advancement in NLP research, cross-lingual transfer f...
research
01/27/2021

Multilingual and cross-lingual document classification: A meta-learning approach

The great majority of languages in the world are considered under-resour...
research
05/18/2022

Persian Natural Language Inference: A Meta-learning approach

Incorporating information from other languages can improve the results o...

Please sign up or login with your details

Forgot password? Click here to reset