Few-Shot NLU with Vector Projection Distance and Abstract Triangular CRF

Abstract

Data sparsity problem is a key challenge of Natural Language Understanding (NLU), especially for a new target domain. By training an NLU model in source domains and applying the model to an arbitrary target domain directly (even without fine-tuning), few-shot NLU becomes crucial to mitigate the data scarcity issue. In this paper, we propose to improve prototypical networks with vector projection distance and abstract triangular Conditional Random Field (CRF) for the few-shot NLU. The vector projection distance exploits projections of contextual word embeddings on label vectors as word-label similarities, which is equivalent to a normalized linear model. The abstract triangular CRF learns domain-agnostic label transitions for joint intent classification and slot filling tasks. Extensive experiments demonstrate that our proposed methods can significantly surpass strong baselines. Specifically, our approach can achieve a new state-of-the-art on two few-shot NLU benchmarks (Few-Joint and SNIPS) in Chinese and English without fine-tuning on target domains.

arXiv commentAccepted by NLPCC 2021

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Matching Networks for One Shot Learning
• Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces
• Few-shot classification in Named Entity Recognition Task
• FewJoint: A Few-shot Learning Benchmark for Joint Language Understanding