Papers by Chun Kang

2 papers
EASE: Entity-Aware Sub-table Generation for Real-world Multi-table QA (2026.acl-long)

Copied to clipboard

Challenge: Table-based question answering (table QA) is a powerful tool for analyzing large language models.
Approach: They propose to use noisy multi-table sets to generate sub-tables for table-based question answering.
Outcome: The proposed framework efficiently filters out irrelevant information while incorporating pertinent table values.
COAS2W: A Chinese Older-Adults Spoken-to-Written Transformation Corpus with Context Awareness (2025.emnlp-main)

Copied to clipboard

Challenge: Existing work on spoken-to-written transformations from older adults' language is limited by omission, disordered syntax, constituent errors, and redundancy.
Approach: They propose to combine a spoken-to-written corpus of 10,004 utterances from older adults with a written version, fine-grained error labels, and four-sentence context.
Outcome: The proposed model outperforms closed-source models on Chinese spoken-to-written corpus and shows that multi-sentence input is more efficient.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations