Data Augmentation for Hypernymy Detection

Thomas Kober, Julie Weeds, Lorenzo Bertolini, David Weir


Abstract
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.
Anthology ID:
2021.eacl-main.89
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1034–1048
Language:
URL:
https://aclanthology.org/2021.eacl-main.89
DOI:
10.18653/v1/2021.eacl-main.89
Bibkey:
Cite (ACL):
Thomas Kober, Julie Weeds, Lorenzo Bertolini, and David Weir. 2021. Data Augmentation for Hypernymy Detection. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1034–1048, Online. Association for Computational Linguistics.
Cite (Informal):
Data Augmentation for Hypernymy Detection (Kober et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.89.pdf
Software:
 2021.eacl-main.89.Software.zip
Dataset:
 2021.eacl-main.89.Dataset.txt
Code
 tttthomasssss/le-augmentation