SemLa: A Visual Analysis System for Fine-Grained Text Classification

Abstract

Fine-grained text classification requires models to distinguish between many fine-grained classes that are hard to tell apart. However, despite the increased risk of models relying on confounding features and predictions being especially difficult to interpret in this context, existing work on the interpretability of fine-grained text classification is severely limited. Therefore, we introduce our visual analysis system, SemLa, which incorporates novel visualization techniques that are tailored to this challenge. Our evaluation based on case studies and expert feedback shows that SemLa can be a powerful tool for identifying model weaknesses, making decisions about data annotation, and understanding the root cause of errors.

Cite

Text

Battogtokh et al. "SemLa: A Visual Analysis System for Fine-Grained Text Classification." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30560

Markdown

[Battogtokh et al. "SemLa: A Visual Analysis System for Fine-Grained Text Classification." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/battogtokh2024aaai-semla/) doi:10.1609/AAAI.V38I21.30560

BibTeX

@inproceedings{battogtokh2024aaai-semla,
  title     = {{SemLa: A Visual Analysis System for Fine-Grained Text Classification}},
  author    = {Battogtokh, Munkhtulga and Davidescu, Cosmin and Luck, Michael and Borgo, Rita},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {23772-23774},
  doi       = {10.1609/AAAI.V38I21.30560},
  url       = {https://mlanthology.org/aaai/2024/battogtokh2024aaai-semla/}
}