DeepAI AI Chat
Log In Sign Up

Continual Learning for Neural Semantic Parsing

by   Vladislav Lialin, et al.

A semantic parsing model is crucial to natural language processing applications such as goal-oriented dialogue systems. Such models can have hundreds of classes with a highly non-uniform distribution. In this work, we show how to efficiently (in terms of computational budget) improve model performance given a new portion of labeled data for a specific low-resource class or a set of classes. We demonstrate that a simple approach with a specific fine-tuning procedure for the old model can reduce the computational costs by  90 performance is on-par with a model trained from scratch on a full dataset. We showcase the efficacy of our approach on two popular semantic parsing datasets, Facebook TOP, and SNIPS.


page 1

page 2

page 3

page 4


The Power of Prompt Tuning for Low-Resource Semantic Parsing

Prompt tuning has recently emerged as an effective method for adapting p...

Unfreeze with Care: Space-Efficient Fine-Tuning of Semantic Parsing Models

Semantic parsing is a key NLP task that maps natural language to structu...

Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers

This paper investigates continual learning for semantic parsing. In this...

CoLLIE: Continual Learning of Language Grounding from Language-Image Embeddings

This paper presents CoLLIE: a simple, yet effective model for continual ...

Training Naturalized Semantic Parsers with Very Little Data

Semantic parsing is an important NLP problem, particularly for voice ass...

Low-Resource Task-Oriented Semantic Parsing via Intrinsic Modeling

Task-oriented semantic parsing models typically have high resource requi...

Semantic Parsing to Manipulate Relational Database For a Management System

Chatbots and AI assistants have claimed their importance in today life. ...