BLCU-NLP at COIN-Shared Task1: Stagewise Fine-tuning BERT for Commonsense Inference in Everyday Narrations

Chunhua Liu, Dong Yu


Abstract
This paper describes our system for COIN Shared Task 1: Commonsense Inference in Everyday Narrations. To inject more external knowledge to better reason over the narrative passage, question and answer, the system adopts a stagewise fine-tuning method based on pre-trained BERT model. More specifically, the first stage is to fine-tune on addi- tional machine reading comprehension dataset to learn more commonsense knowledge. The second stage is to fine-tune on target-task (MCScript2.0) with MCScript (2018) dataset assisted. Experimental results show that our system achieves significant improvements over the baseline systems with 84.2% accuracy on the official test dataset.
Anthology ID:
D19-6012
Volume:
Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Simon Ostermann, Sheng Zhang, Michael Roth, Peter Clark
Venue:
WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
99–103
Language:
URL:
https://aclanthology.org/D19-6012
DOI:
10.18653/v1/D19-6012
Bibkey:
Cite (ACL):
Chunhua Liu and Dong Yu. 2019. BLCU-NLP at COIN-Shared Task1: Stagewise Fine-tuning BERT for Commonsense Inference in Everyday Narrations. In Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing, pages 99–103, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
BLCU-NLP at COIN-Shared Task1: Stagewise Fine-tuning BERT for Commonsense Inference in Everyday Narrations (Liu & Yu, 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/D19-6012.pdf