ThisIsCompetition at SemEval-2019 Task 9: BERT is unstable for out-of-domain samples

Cheoneum Park, Juae Kim, Hyeon-gu Lee, Reinald Kim Amplayo, Harksoo Kim, Jungyun Seo, Changki Lee


Abstract
This paper describes our system, Joint Encoders for Stable Suggestion Inference (JESSI), for the SemEval 2019 Task 9: Suggestion Mining from Online Reviews and Forums. JESSI is a combination of two sentence encoders: (a) one using multiple pre-trained word embeddings learned from log-bilinear regression (GloVe) and translation (CoVe) models, and (b) one on top of word encodings from a pre-trained deep bidirectional transformer (BERT). We include a domain adversarial training module when training for out-of-domain samples. Our experiments show that while BERT performs exceptionally well for in-domain samples, several runs of the model show that it is unstable for out-of-domain samples. The problem is mitigated tremendously by (1) combining BERT with a non-BERT encoder, and (2) using an RNN-based classifier on top of BERT. Our final models obtained second place with 77.78% F-Score on Subtask A (i.e. in-domain) and achieved an F-Score of 79.59% on Subtask B (i.e. out-of-domain), even without using any additional external data.
Anthology ID:
S19-2220
Volume:
Proceedings of the 13th International Workshop on Semantic Evaluation
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota, USA
Venue:
*SEMEVAL
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
1254–1261
Language:
URL:
https://www.aclweb.org/anthology/S19-2220
DOI:
10.18653/v1/S19-2220
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/S19-2220.pdf