Word learning as Bayesian inference.
نویسندگان
چکیده
منابع مشابه
Word learning as Bayesian inference.
The authors present a Bayesian framework for understanding how adults and children learn the meanings of words. The theory explains how learners can generalize meaningfully from just one or a few positive examples of a novel word's referents, by making rational inductive inferences that integrate prior knowledge about plausible word meanings with the statistical structure of the observed exampl...
متن کاملBayesian Inference for Bilingual Word Learning
The indeterminacy problem describes the challenge that infants face in deciding which words refer to which objects in their environment. Bayesian models use probabilistic inferences to resolve this induction problem and show improved performance over other computational models in constructing potential lexicons and inferring speakers’ referential intentions. In this study we investigate a Bayes...
متن کاملModeling Word Learning As Communicative Inference
How do children learn their first words? I describe a model that makes joint inferences about what speakers are trying to talk about and the meanings of the words they use. This model provides a principled framework for integrating a wide variety of non-linguistic information sources into the process of word learning.
متن کاملAn Introduction to Inference and Learning in Bayesian Networks
Bayesian networks (BNs) are modern tools for modeling phenomena in dynamic and static systems and are used in different subjects such as disease diagnosis, weather forecasting, decision making and clustering. A BN is a graphical-probabilistic model which represents causal relations among random variables and consists of a directed acyclic graph and a set of conditional probabilities. Structure...
متن کاملBayesian inference as a cross-linguistic word segmentation strategy: Always learning useful things
Statistical learning has been proposed as one of the earliest strategies infants could use to segment words out of their native language because it does not rely on language-specific cues that must be derived from existing knowledge of the words in the language. Statistical word segmentation strategies using Bayesian inference have been shown to be quite successful for English (Goldwater et al....
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Psychological Review
سال: 2007
ISSN: 1939-1471,0033-295X
DOI: 10.1037/0033-295x.114.2.245