Natural Language Processing

Attention Meets Perturbations: Robust and Interpretable Attention with Adversarial Training

IEEE Access (**Impact Factor: 3.745**; [3rd place in Engineering & Computer Science (general) at Google Scholar Metrics](https://scholar.google.com/citations?view_op=top_venues&hl=en&vq=eng_enggeneral))

Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training for Semi-Supervised Text Classification

We propose a new general training technique for attention mechanisms based on virtual adversarial training (VAT). VAT can compute adversarial perturbations from unlabeled data in a semi-supervised setting for the attention mechanisms that have been …

Text Classification through Glyph-aware Disentangled Character Embedding and Semantic Sub-character Augmentation

Proc. 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

AraDIC: Arabic Document Classification using Image-Based Character Embeddings and Class-Balanced Loss

Proc. of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop

文字単位の解釈可能な潜在表現のdata augmentation

言語処理学会第 26 回年次大会, 2020.

Image-based Character Embedding for Arabic Document Classification

言語処理学会第 26 回年次大会, 2020.

Script-aware embedding を用いた文字表現の獲得

言語処理学会第 26 回年次大会, 2020.

解釈性向上のための注意機構と損失勾配に対する関連損失の導入

NLP 若手の会 (YANS) 第 14 回シンポジウム, 2019. **奨励賞** 受賞

Image Based Character Embeddings for Arabic Document Classification

NLP 若手の会 (YANS) 第 14 回シンポジウム, 2019.

日本語の文字体系を考慮した文書分類モデルの提案

NLP 若手の会 (YANS) 第 14 回シンポジウム, 2019.