Abstract
This paper proposes a neural based system to solve the essential interpretability problem existing in text classification, especially in charge prediction task. First, we use a deep reinforcement learning method to extract rationales which mean short, readable and decisive snippets from input text. Then a rationale augmented classification model is proposed to elevate the prediction accuracy. Naturally, the extracted rationales serve as the introspection explanation for the prediction result of the model, enhancing the transparency of the model. Experimental results demonstrate that our system is able to extract readable rationales in a high consistency with manual annotation and is comparable with the attention model in prediction accuracy.- Anthology ID:
- C18-2032
- Volume:
- Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations
- Month:
- August
- Year:
- 2018
- Address:
- Santa Fe, New Mexico
- Editor:
- Dongyan Zhao
- Venue:
- COLING
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 146–151
- Language:
- URL:
- https://aclanthology.org/C18-2032
- DOI:
- Cite (ACL):
- Xin Jiang, Hai Ye, Zhunchen Luo, WenHan Chao, and Wenjia Ma. 2018. Interpretable Rationale Augmented Charge Prediction System. In Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations, pages 146–151, Santa Fe, New Mexico. Association for Computational Linguistics.
- Cite (Informal):
- Interpretable Rationale Augmented Charge Prediction System (Jiang et al., COLING 2018)
- PDF:
- https://preview.aclanthology.org/fix-dup-bibkey/C18-2032.pdf