Work

Knowledge-Aware Meta-learning for Low-Resource Text Classification

Year: 2021

Type: conference-paper

Abstract: Meta-learning has achieved great success in leveraging the historical learned knowledge to facilitate the learning process of the new task.However, merely learning the knowledge from the historical tasks, adopted by current meta-learning algorithms, may not generalize well to testing tasks when they are not well-supported by training tasks.This paper studies a low-resource text classification problem and bridges the gap between meta-training and meta-testing tasks by leveraging the external knowledge bases.Specifically, we propose KGML to introduce additional representation for each sentence learned from the extracted sentence-specific knowledge graph.The extensive experiments on three datasets demonstrate the effectiveness of KGML under both supervised adaptation and unsupervised adaptation settings.

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.18653/v1/2021.emnlp-main.136

Authors: Huaxiu Yao, Ying-xin Wu, Maruan Al-Shedivat, Eric Xing

Institutions: Stanford University, University of Science and Technology of China, Carnegie Mellon University, Mohamed bin Zayed University of Artificial Intelligence

Language: English

Topic: Domain Adaptation and Few-Shot Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Science Foundation

Awards: III: Small: A New Approach to Latent Space Learning with Diversity-Inducing Regularization and Applications to Healthcare Data Analytics, CNS Core: Small: Toward Globally-Optimal Resource Distribution and Computation Acceleration in Multi-Tenant and Heterogeneous Machine Learning Systems, Collaborative Research: RI: Medium: A Rigorous, General Framework for Tractable Learning of Large-Scale DAGs from Data