Reproduce “Embodied Natural Language Interaction (NLI): Speech Input Patterns in Immersive Analytics” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Hyemi Song, Matthew Johnson, Kirsten Whitley, Eric Krokos, Amitabh Varshney
The authors study how people phrase chart tasks using spatial language in immersive data analysis. In a Wizard-of-Oz study, 15 participants produced 734 utterances and 1,280 speech acts, classified by task, phase, embodiment cues, and estimated uncertainty. Patterns varied across tasks and phases: Foraging’s Navigate task had 97% embodiment reliance. This measures cue use, not gesture frequency or system accuracy.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.