RetroGAN: A Cyclic Post-Specialization System for Improving Out-of-Knowledge and Rare Word Representations
Abstract
Retrofitting is a technique used to move word vectors closer together or further apart in their space to reflect their relationships in a Knowledge Base (KB). However, retrofitting only works on concepts that are present in that KB. RetroGAN uses a pair of Generative Adversarial Networks (GANs) to learn a one-to-one mapping between concepts and their retrofitted counterparts. It applies that mapping (post-specializes) to handle concepts that do not appear in the original KB in a manner similar to how some natural language systems handle out-of-vocabulary entries. We test our system on three word-similarity benchmarks and a downstream sentence simplification task and achieve the state of the art (CARD-660). Altogether, our results demonstrate our system's effectiveness for out-of-knowledge and rare word generalization.
Keywords
Cite
@article{arxiv.2108.12941,
title = {RetroGAN: A Cyclic Post-Specialization System for Improving Out-of-Knowledge and Rare Word Representations},
author = {Pedro Colon-Hernandez and Yida Xin and Henry Lieberman and Catherine Havasi and Cynthia Breazeal and Peter Chin},
journal= {arXiv preprint arXiv:2108.12941},
year = {2021}
}