A Discerning Several Thousand Judgments: GPT-3 Rates the Article + Adjective + Numeral + Noun Construction
–arXiv.org Artificial Intelligence
Knowledge of syntax includes knowledge of rare, idiosyncratic constructions. LLMs must overcome frequency biases in order to master such constructions. In this study, I prompt GPT-3 to give acceptability judgments on the English-language Article + Adjective + Numeral + Noun construction (e.g., "a lovely five days"). I validate the prompt using the CoLA corpus of acceptability judgments and then zero in on the AANN construction. I compare GPT- 3's judgments to crowdsourced human judgments on a subset of sentences. GPT-3's judgments are broadly similar to human judgments and generally align with proposed constraints in the literature but, in some cases, GPT-3's judgments and human judgments diverge from the literature and from each other.
arXiv.org Artificial Intelligence
Feb-3-2023
- Country:
- Oceania > Papua New Guinea (0.04)
- North America > United States
- Pennsylvania (0.04)
- Massachusetts (0.04)
- Louisiana (0.04)
- Texas > Travis County
- Austin (0.04)
- New York > New York County
- New York City (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Europe
- Spain (0.04)
- Italy > Tuscany
- Florence (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- France > Provence-Alpes-Côte d'Azur
- Bouches-du-Rhône > Marseille (0.04)
- Africa > Kenya
- Nairobi City County > Nairobi (0.04)
- Genre:
- Research Report > New Finding (0.34)
- Technology: