DeepAI AI Chat
Log In Sign Up

Data Augmentation for Hypernymy Detection

by   Thomas Kober, et al.
University of Sussex

The automatic detection of hypernymy relationships represents a challenging problem in NLP. The successful application of state-of-the-art supervised approaches using distributed representations has generally been impeded by the limited availability of high quality training data. We have developed two novel data augmentation techniques which generate new training examples from existing ones. First, we combine the linguistic principles of hypernym transitivity and intersective modifier-noun composition to generate additional pairs of vectors, such as "small dog - dog" or "small dog - animal", for which a hypernymy relationship can be assumed. Second, we use generative adversarial networks (GANs) to generate pairs of vectors for which the hypernymy relation can also be assumed. We furthermore present two complementary strategies for extending an existing dataset by leveraging linguistic resources such as WordNet. Using an evaluation across 3 different datasets for hypernymy detection and 2 different vector spaces, we demonstrate that both of the proposed automatic data augmentation and dataset extension strategies substantially improve classifier performance.


page 7

page 13


Data Augmentation of Room Classifiers using Generative Adversarial Networks

The classification of acoustic environments allows for machines to bette...

A Survey on Face Data Augmentation

The quality and size of training set have great impact on the results of...

Hypernyms under Siege: Linguistically-motivated Artillery for Hypernymy Detection

The fundamental role of hypernymy in NLP has motivated the development o...

Dialog State Tracking with Reinforced Data Augmentation

Neural dialog state trackers are generally limited due to the lack of qu...

Training Strategies and Data Augmentations in CNN-based DeepFake Video Detection

The fast and continuous growth in number and quality of deepfake videos ...