Posts by Collection

portfolio

publications

Scientific document processing: challenges for modern learning methods

Published in International Journal on Digital Libraries, 2023

A survey of modern neural network learning methods for scholarly document processing, addressing discourse structure, interconnectivity, and multimodal nature of scientific publications

Recommended citation: Kashyap, Abhinav Ramesh, Yajing Yang, and Min-Yen Kan. (2023). "Scientific document processing: challenges for modern learning methods." International Journal on Digital Libraries. 24, 283–309.
Download Paper

DataTales: A Benchmark for Real-World Intelligent Data Narration

Published in Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024

A benchmark for real-world intelligent data narration using financial reports and market data

Recommended citation: Yang, Yajing, Qian Liu, and Min-Yen Kan. (2024). "DataTales: A Benchmark for Real-World Intelligent Data Narration." Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. Miami, FL, USA.
Download Paper

KAHAN: Knowledge-Augmented Hierarchical Analysis and Narration for Financial Data Narration

Published in Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

A knowledge-augmented hierarchical framework for financial data narration that leverages LLMs as domain experts

Recommended citation: Yang, Yajing, Tony Deng, and Min-Yen Kan. (2025). "KAHAN: Knowledge-Augmented Hierarchical Analysis and Narration for Financial Data Narration." Findings of the Association for Computational Linguistics: EMNLP 2025. Suzhou, China.
Download Paper

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.