Human-machine cooperation for semantic feature listing

Autor:	Mukherjee, Kushin, Suresh, Siddharth, Rogers, Timothy T.
Rok vydání:	2023
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	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. Comment: To be published in the ICLR TinyPaper track
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2304.05012 Zobrazit plný text záznamu View this record from Arxiv