Abstract
In this paper, we describe a machine reading comprehension system that participated in SemEval-2018 Task 11: Machine Comprehension using commonsense knowledge. In this work, we train a series of neural network models such as multi-LSTM, BiLSTM, multi- BiLSTM-CNN and attention-based BiLSTM, etc. On top of some sub models, there are two kinds of word embedding: (a) general word embedding generated from unsupervised neural language model; and (b) position embedding generated from general word embedding. Finally, we make a hard vote on the predictions of these models and achieve relatively good result. The proposed approach achieves 8th place in Task 11 with the accuracy of 0.7213.- Anthology ID:
- S18-1173
- Volume:
- Proceedings of the 12th International Workshop on Semantic Evaluation
- Month:
- June
- Year:
- 2018
- Address:
- New Orleans, Louisiana
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1038–1042
- Language:
- URL:
- https://aclanthology.org/S18-1173
- DOI:
- 10.18653/v1/S18-1173
- Cite (ACL):
- Qingxun Liu, Hongdou Yao, Xaobing Zhou, and Ge Xie. 2018. YNU_AI1799 at SemEval-2018 Task 11: Machine Comprehension using Commonsense Knowledge of Different model ensemble. In Proceedings of the 12th International Workshop on Semantic Evaluation, pages 1038–1042, New Orleans, Louisiana. Association for Computational Linguistics.
- Cite (Informal):
- YNU_AI1799 at SemEval-2018 Task 11: Machine Comprehension using Commonsense Knowledge of Different model ensemble (Liu et al., SemEval 2018)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/S18-1173.pdf