This research explores context-aware and multi-perspective summarization by integrating techniques
from retrieval-augmented generation (RAG), large language models (LLMs), machine learning, and
computer vision. It aims to enhance information retrieval and summarization across various applications,
including event timeline generation, legal document analysis, cross-lingual case retrieval, and stance-
aware news summarization. By leveraging intelligent retrieval mechanisms, the system ensures accurate,
context-rich, and multi-viewpoint summaries. Its applications span legal, medical, and industrial
specifications, enabling structured knowledge extraction from large, unstructured datasets while
improving efficiency, interpretability, and decision-making support.
- Tz-Huan Hsu, Li-Hsuan Chin, Yen-Hao Huang, Yi-Shin Chen (2024, Oct). PIECE:
Protagonist Identification and Event Chronology Extraction for Enhanced Timeline
Summarization. Proceedings of the 33rd ACM International Conference on Information
and Knowledge Management (CIKM 2024), Boise, Idaho, USA.
- Yen-Hao Huang, Yi-Hsin Chen, Yi-Shin Chen (2022). ConTextING: Granting Document-
Wise Contextual Embeddings to Graph Neural Networks for Inductive Text Classification. COLING 2022: 1163-1168.
- Yen-Hao Huang, Hsiao-Yen Lan, Yi-Shin Chen (2022). Unsupervised Text
Summarization of Long Documents using Dependency-based Noun Phrases and
Contextual Order Arrangement. ROCLING 2022: 15-24.
- Yen-Hao Huang, Tzu-Yun Lee, Fernando H. Calderon, Yi-Shin Chen (2021).
Dynamic Span Selection for Mandarin Articles Using Contextual Relations and
Orthography. International Conference on Technologies and Applications of Artificial
Intelligence (TAAI 2021).
- Yen-Hao Huang, Ratana Pornvattanavichai, Fernando Henrique Calderon
Alvarado, Yi-Shin Chen* (2021). Unsupervised Multi-document Summarization for
News Corpus with Key Synonyms and Contextual Embeddings. Proceedings of the
33rd Conference on Computational Linguistics and Speech Processing (ROCLING
2021).