6 papers · 1 filter
A11y-Compressor: A Framework for Enhancing the Efficiency of GUI Agent Observations through Visual Context Reconstruction and Redundancy Reduction
Michito Takeshita, Takuro Kawada, Takumi Ohashi +2
AI agents that interact with graphical user interfaces (GUIs) require effective observation representations for reliable grounding. The accessibility tree is a commonly used text-b…
Majority or Minority: Data Imbalance Learning Method for Named Entity Recognition
Sota Nemoto, Shunsuke Kitada, Hitoshi Iyatomi
Data imbalance presents a significant challenge in various machine learning (ML) tasks, particularly named entity recognition (NER) within natural language processing (NLP). NER ex…
Text Classification through Glyph-aware Disentangled Character Embedding and Semantic Sub-character Augmentation
Takumi Aoki, Shunsuke Kitada, Hitoshi Iyatomi
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…
AraDIC: Arabic Document Classification using Image-Based Character Embeddings and Class-Balanced Loss
Mahmoud Daif, Shunsuke Kitada, Hitoshi Iyatomi
Classical and some deep learning techniques for Arabic text classification often depend on complex morphological analysis, word segmentation, and hand-crafted feature engineering.…
Conversion Prediction Using Multi-task Conditional Attention Networks to Support the Creation of Effective Ad Creative
Shunsuke Kitada, Hitoshi Iyatomi, Yoshifumi Seki
Accurately predicting conversions in advertisements is generally a challenging task, because such conversions do not occur frequently. In this paper, we propose a new framework to…
End-to-End Text Classification via Image-based Embedding using Character-level Networks
Shunsuke Kitada, Ryunosuke Kotani, Hitoshi Iyatomi
For analysing and/or understanding languages having no word boundaries based on morphological analysis such as Japanese, Chinese, and Thai, it is desirable to perform appropriate w…