Sampling Matters! An Empirical Study of Negative Sampling Strategies for Learning of Matching Models in Retrieval-based Dialogue Systems

Jia Li, Chongyang Tao, Wei Wu, Yansong Feng, Dongyan Zhao, Rui Yan


Abstract
We study how to sample negative examples to automatically construct a training set for effective model learning in retrieval-based dialogue systems. Following an idea of dynamically adapting negative examples to matching models in learning, we consider four strategies including minimum sampling, maximum sampling, semi-hard sampling, and decay-hard sampling. Empirical studies on two benchmarks with three matching models indicate that compared with the widely used random sampling strategy, although the first two strategies lead to performance drop, the latter two ones can bring consistent improvement to the performance of all the models on both benchmarks.
Anthology ID:
D19-1128
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1291–1296
Language:
URL:
https://www.aclweb.org/anthology/D19-1128
DOI:
10.18653/v1/D19-1128
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D19-1128.pdf