Comparing Attention-Based Convolutional and Recurrent Neural Networks: Success and Limitations in Machine Reading Comprehension
Matthias Blohm, Glorianna Jagfeld, Ekta Sood, Xiang Yu, Ngoc Thang Vu
Abstract
We propose a machine reading comprehension model based on the compare-aggregate framework with two-staged attention that achieves state-of-the-art results on the MovieQA question answering dataset. To investigate the limitations of our model as well as the behavioral difference between convolutional and recurrent neural networks, we generate adversarial examples to confuse the model and compare to human performance. Furthermore, we assess the generalizability of our model by analyzing its differences to human inference, drawing upon insights from cognitive science.- Anthology ID:
- K18-1011
- Volume:
- Proceedings of the 22nd Conference on Computational Natural Language Learning
- Month:
- October
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Anna Korhonen, Ivan Titov
- Venue:
- CoNLL
- SIG:
- SIGNLL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 108–118
- Language:
- URL:
- https://aclanthology.org/K18-1011
- DOI:
- 10.18653/v1/K18-1011
- Cite (ACL):
- Matthias Blohm, Glorianna Jagfeld, Ekta Sood, Xiang Yu, and Ngoc Thang Vu. 2018. Comparing Attention-Based Convolutional and Recurrent Neural Networks: Success and Limitations in Machine Reading Comprehension. In Proceedings of the 22nd Conference on Computational Natural Language Learning, pages 108–118, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Comparing Attention-Based Convolutional and Recurrent Neural Networks: Success and Limitations in Machine Reading Comprehension (Blohm et al., CoNLL 2018)
- PDF:
- https://preview.aclanthology.org/teach-a-man-to-fish/K18-1011.pdf
- Code
- DigitalPhonetics/reading-comprehension
- Data
- MovieQA, SQuAD