Distributional Modeling on a Diet: One-shot Word Learning from Text Only
Not on the map. Why?
Abstract (arXiv)
We test whether distributional models can do one-shot learning of definitional properties from text only. Using Bayesian models, we find that first learning overarching structure in the known data, regularities in textual contexts and in properties, helps one-shot learning, and that individual context items can be highly informative. Our experiments show that our model can learn properties from a single exposure when given an informative utterance.
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Apr 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2022: 2; 2023: 1; 2024: 0; 2025: 2.
5 papers.
- 2023MAGNIFICo: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretationscited by 7
- 2025Slot Attention-based Feature Filtering for Few-Shot Learningcited by 1
- 2022An Attention-Based Model for Predicting Contextual Informativeness and Curriculum Learning Applicationscited by 0
- 2022Semantic Novelty Detection and Characterization in Factual Text Involving Named Entitiescited by 0
- 2025Stochastic-based Patch Filtering for Few-Shot Learningcited by 0
- 2025Stochastic-based Patch Filtering for Few-Shot Learning13 Aug 2025
- 2025Slot Attention-based Feature Filtering for Few-Shot Learning13 Aug 2025
- 2023MAGNIFICo: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretations18 Oct 2023
- 2022Semantic Novelty Detection and Characterization in Factual Text Involving Named Entities31 Oct 2022
- 2022An Attention-Based Model for Predicting Contextual Informativeness and Curriculum Learning Applications21 Apr 2022