English

Human-machine cooperation for semantic feature listing

Computation and Language 2023-04-12 v1 Artificial Intelligence

Abstract

Semantic feature norms, lists of features that concepts do and do not possess, have played a central role in characterizing human conceptual knowledge, but require extensive human labor. Large language models (LLMs) offer a novel avenue for the automatic generation of such feature lists, but are prone to significant error. Here, we present a new method for combining a learned model of human lexical-semantics from limited data with LLM-generated data to efficiently generate high-quality feature norms.

Keywords

Cite

@article{arxiv.2304.05012,
  title  = {Human-machine cooperation for semantic feature listing},
  author = {Kushin Mukherjee and Siddharth Suresh and Timothy T. Rogers},
  journal= {arXiv preprint arXiv:2304.05012},
  year   = {2023}
}

Comments

To be published in the ICLR TinyPaper track

R2 v1 2026-06-28T09:58:58.101Z