PulseAugur
LIVE 15:21:27
research · [2 sources] ·
0
research

New research models dialogue production using surprisal minimization over alternatives

Researchers have developed a new computational model for predicting how humans choose words when speaking. This model treats utterance production as a probabilistic choice among alternatives, using information-theoretic costs. It distinguishes between alternatives that serve a specific communicative goal and those that are simply plausible in context. The study found that minimizing "surprisal" relative to goal-directed alternatives best predicts actual production choices in dialogue. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT This research offers a new framework for understanding natural language production, potentially improving dialogue systems and human-computer interaction.

RANK_REASON The cluster contains an academic paper published on arXiv.

Read on arXiv cs.CL →

COVERAGE [2]

  1. arXiv cs.CL TIER_1 · Tom Utting, Mario Giulianelli, Arabella Sinclair ·

    Surprisal Minimisation over Goal-directed Alternatives Predicts Production Choice in Dialogue

    arXiv:2605.00506v1 Announce Type: new Abstract: We model utterance production as probabilistic cost-sensitive choice over contextual alternatives, using information-theoretic notions of cost. We distinguish between goal-directed alternatives that realise a fixed communicative int…

  2. arXiv cs.CL TIER_1 · Arabella Sinclair ·

    Surprisal Minimisation over Goal-directed Alternatives Predicts Production Choice in Dialogue

    We model utterance production as probabilistic cost-sensitive choice over contextual alternatives, using information-theoretic notions of cost. We distinguish between goal-directed alternatives that realise a fixed communicative intent and goal-agnostic alternatives defined only …