2 papers
cs.CL2026
Rethinking Human-Aligned Evaluation: An Analysis of Semantic Metrics Beyond WER
Hritika Sharma, Thibault Bañeras-Roux, Alessandra Pinto +4
Word Error Rate (WER), the most commonly used metric for Automatic Speech Recognition (ASR), treats every lexical deviation from the reference as equally costly, regardless of whet…
cs.HC2026
"I Should Know, But I Dare Not Ask": From Understanding Challenges in Patient Journeys to Deriving Design Implications for North Korean Defectors' Adaptation
Hyungwoo Song, Jeongha Kim, Minju Kim +4
While it is known that North Korean defectors (NKDs) struggle with South Korea's healthcare system, the specific challenges of their patient journey remain underexplored. To invest…