作者位次 #3/6ACL 2026Poster· Natural Language Processing
Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Models
Yu Wang · Leyi Lao · Langchu Huang · Gabriel Skantze · Yang Xu · Hendrik Buschmeier
摘要
Backchannels and fillers are important linguistic expressions in dialogue, but often treated as “noise” to be bypassed in modern transformer-based language models. Our work studies the representation of them in language models using three fine-tuning strategies. The models are trained on three di...