C2C-GenDA: Cluster-to-Cluster Generation for Data Augmentation of Slot Filling

Authors

  • Yutai Hou Harbin Institute of Technology
  • Sanyuan Chen Harbin Institute of Technology
  • Wanxiang Che Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology
  • Cheng Chen Harbin Institute of Technology
  • Ting Liu Harbin Institute of Technology

Keywords:

Conversational AI/Dialog Systems

Abstract

Slot filling, a fundamental module of spoken language understanding, often suffers from insufficient quantity and diversity of training data. To remedy this, we propose a novel Cluster-to-Cluster generation framework for Data Augmentation (DA), named C2C-GenDA. It enlarges the training set by reconstructing existing utterances into alternative expressions while keeping semantic. Different from previous DA works that reconstruct utterances one by one independently, C2C-GenDA jointly encodes multiple existing utterances of the same semantics and simultaneously decodes multiple unseen expressions. Jointly generating multiple new utterances allows to consider the relations between generated instances and encourages diversity. Besides, encoding multiple existing utterances endows C2C with a wider view of existing expressions, helping to reduce generation that duplicates existing data. Experiments on ATIS and Snips datasets show that instances augmented by C2C-GenDA improve slot filling by 7.99 (11.9%↑) and 5.76 (13.6%↑) F-scores respectively, when there are only hundreds of training utterances. Code: https://github.com/Sanyuan-Chen/C2C-DA.

Downloads

Published

2021-05-18

How to Cite

Hou, Y., Chen, S., Che, W., Chen, C., & Liu, T. (2021). C2C-GenDA: Cluster-to-Cluster Generation for Data Augmentation of Slot Filling. Proceedings of the AAAI Conference on Artificial Intelligence, 35(14), 13027-13035. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17540

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing I