Does the Order of Training Samples Matter? Improving Neural Data-to-Text Generation with Curriculum Learning

Ernie Chang, Hui-Syuan Yeh, Vera Demberg


Abstract
Recent advancements in data-to-text generation largely take on the form of neural end-to-end systems. Efforts have been dedicated to improving text generation systems by changing the order of training samples in a process known as curriculum learning. Past research on sequence-to-sequence learning showed that curriculum learning helps to improve both the performance and convergence speed. In this work, we delve into the same idea surrounding the training samples consisting of structured data and text pairs, where at each update, the curriculum framework selects training samples based on the model’s competence. Specifically, we experiment with various difficulty metrics and put forward a soft edit distance metric for ranking training samples. On our benchmarks, it shows faster convergence speed where training time is reduced by 38.7% and performance is boosted by 4.84 BLEU.
Anthology ID:
2021.eacl-main.61
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
727–733
Language:
URL:
https://aclanthology.org/2021.eacl-main.61
DOI:
10.18653/v1/2021.eacl-main.61
Bibkey:
Cite (ACL):
Ernie Chang, Hui-Syuan Yeh, and Vera Demberg. 2021. Does the Order of Training Samples Matter? Improving Neural Data-to-Text Generation with Curriculum Learning. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 727–733, Online. Association for Computational Linguistics.
Cite (Informal):
Does the Order of Training Samples Matter? Improving Neural Data-to-Text Generation with Curriculum Learning (Chang et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.61.pdf