Entity Aware Syntax Tree Based Data Augmentation for Natural Language Understanding

TL;DR

This paper introduces Entity Aware Data Augmentation (EADA), a novel method using syntax trees focused on entities to generate extensive training data for natural language understanding tasks, improving accuracy and generalization.

Contribution

The paper presents a new data augmentation technique that leverages entity-aware syntax trees to enhance NLU model training with limited annotated data.

Findings

EADA outperforms existing augmentation methods in accuracy.

EADA improves model generalization on multiple datasets.

The method effectively generates large training sets from small annotated samples.

Abstract

Understanding the intention of the users and recognizing the semantic entities from their sentences, aka natural language understanding (NLU), is the upstream task of many natural language processing tasks. One of the main challenges is to collect a sufficient amount of annotated data to train a model. Existing research about text augmentation does not abundantly consider entity and thus performs badly for NLU tasks. To solve this problem, we propose a novel NLP data augmentation technique, Entity Aware Data Augmentation (EADA), which applies a tree structure, Entity Aware Syntax Tree (EAST), to represent sentences combined with attention on the entity. Our EADA technique automatically constructs an EAST from a small amount of annotated data, and then generates a large number of training instances for intent detection and slot filling. Experimental results on four datasets showed that the proposed technique significantly outperforms the existing data augmentation methods in terms of both accuracy and generalization ability.