TrInk: Ink Generation with Transformer Network

ACL ARR 2025 May Submission621 Authors

Abstract: In this paper, we propose TrInk, a Transformer-based model for ink generation, enabling parallel training and better capturing global dependencies. To better facilitate the alignment between the input text and generated stroke points, we introduce scaled positional embeddings and a Gaussian memory mask in the cross-attention module. Additionally, we design both subjective and objective evaluation pipelines to comprehensively assess the legibility and style consistency of the generated handwriting. Experiments demonstrate that our Transformer-based model achieves a 35.56\% reduction in character error rate (CER) and an 29.66\% reduction in word error rate (WER) on the IAM-OnDB dataset compared to previous methods. We provide an online demo page with handwriting samples from TrInk and baseline models at: https://akahello-a11y.github.io/trink-demo/

Paper Type: Short

Research Area: Human-Centered NLP

Research Area Keywords: Ink Generation, Transformer, Sequence to Sequence

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Publicly available software and/or pre-trained models

Languages Studied: English

Keywords: Ink generation, Transformer, Generative model

Submission Number: 621