Abstract
We propose a new character-based text classification framework for non-alphabetic languages, such as Chinese and Japanese. Our framework consists of a variational character encoder (VCE) and character-level text classifier. The VCE is composed of a β-variational auto-encoder (β -VAE) that learns the proposed glyph-aware disentangled character embedding (GDCE). Since our GDCE provides zero-mean unit-variance character embeddings that are dimensionally independent, it is applicable for our interpretable data augmentation, namely, semantic sub-character augmentation (SSA). In this paper, we evaluated our framework using Japanese text classification tasks at the document- and sentence-level. We confirmed that our GDCE and SSA not only provided embedding interpretability but also improved the classification performance. Our proposal achieved a competitive result to the state-of-the-art model while also providing model interpretability.- Anthology ID:
- 2020.aacl-srw.1
- Volume:
- Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop
- Month:
- December
- Year:
- 2020
- Address:
- Suzhou, China
- Venue:
- AACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1–7
- Language:
- URL:
- https://aclanthology.org/2020.aacl-srw.1
- DOI:
- Cite (ACL):
- Takumi Aoki, Shunsuke Kitada, and Hitoshi Iyatomi. 2020. Text Classification through Glyph-aware Disentangled Character Embedding and Semantic Sub-character Augmentation. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop, pages 1–7, Suzhou, China. Association for Computational Linguistics.
- Cite (Informal):
- Text Classification through Glyph-aware Disentangled Character Embedding and Semantic Sub-character Augmentation (Aoki et al., AACL 2020)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2020.aacl-srw.1.pdf
- Code
- IyatomiLab/GDCE-SSA