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://aclanthology.org/S19-2220
- DOI:
- 10.18653/v1/S19-2220
- Cite (ACL):
- Cheoneum Park, Juae Kim, Hyeon-gu Lee, Reinald Kim Amplayo, Harksoo Kim, Jungyun Seo, and Changki Lee. 2019. ThisIsCompetition at SemEval-2019 Task 9: BERT is unstable for out-of-domain samples. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 1254–1261, Minneapolis, Minnesota, USA. Association for Computational Linguistics.
- Cite (Informal):
- ThisIsCompetition at SemEval-2019 Task 9: BERT is unstable for out-of-domain samples (Park et al., SemEval 2019)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/S19-2220.pdf