Acquiring a Single New Word

By Susan Carey, E. Bartlett. 1978

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Linguistics

Citations in the corpus

Language Models are Few-Shot Learners (2020, background): “l size and training time, suggesting that most of the gap comes from a difference in difﬁculty rather than overﬁtting. 3.9.5 Learning and Using Novel Words A task studied in developmental linguistics [CB78] is the ability to learn and utilize new words, for example using a word in a sentence after s”
Meta-learning with differentiable closed-form solvers (2018, background): “Humans can efﬁciently perform fast mapping (Carey, 1978; Carey & Bartlett, 1978), i.e. learning a new concept after a single exposure.”
Few-Shot Learning with Metric-Agnostic Conditional Embeddings (2018, background): “A key insight from psychology is that human few-shot generalization only occurs when new classes can be understood in the context of old ones (Carey & Bartlett, 1978; Swing-ley, 2010).”
TADAM: Task dependent adaptive metric for improved few-shot learning (2018, background): “Humans can learn to identify new categories from few examples, even from a single one [2].”
Learning Like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images (2015, background): “In particular, it is known that children can form quick and rough hypotheses about the meaning of new words in a sentence based on their knowledge of previous learned words [5, 21], associate these words to the objects or their properties, and describe novel concepts using sentences with the new wor”
Inferring word meanings by assuming that speakers are informative (2014, unknown): “Studies have shown that they can accurately infer and remember the meanings of novel words on the basis of a single exposure (e.g. Carey and Bartlett (1978), Heibeck and Markman (1987), Spiegel and Halberda (2011)).”
PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World (2021, background): “However, this has unintended consequences (Bender et al., 2021) and it is unlike how children learn language, with children learning novel words from experience (Carey and Bartlett, 1978).”
Discovering linguistic structures in speech: models and applications (2014, background): “One-shot learning is an ability to acquire and generalize new concepts from one or just a few examples [15, 186].”
One-shot learning by inverting a compositional causal process (2013, background): “These new larger datasets have developed along with larger and “deeper” model architectures, and while performance has steadily (and even spectacularly [15]) improved in this big data setting, it is unknown how this progress translates to the “one-shot” setting that is a hallmark of human learning [”
Do Both Pictures and Words Function as Symbols for 18- and 24-Month-Old Children? (2004, background): “Our participants were quickly able to learn a mapping between the novel word andnovelpictureinthetrainingphase,whichisnotsurprising,consideringtheabun-danceofevidenceforfastmapping(Carey&Bartlett,1978;Markson&Bloom, 1997).”
Mindreading, Communication and the Learning of Names for Things (2002, unknown): “This ability to successfully learn words under conditions of minimal exposure has been dubbed ‘fast mapping’ (Carey and Bartlett, 1978), and this capacity has been found in 2-year-olds (e.”
The effect of probabilistic phonotactics on lexical acquisition (2000, background): “Models of long-term-memory assume two separate storage systems: semantic and phonologic (e.g. Dell, 1986; 1988; Butterworth, 1992; Levelt and Wheeldon, 1994).”
One-shot learning of generative speech concepts (2014, background): “Previous work has shown that children can do one-shot spoken word learning (Carey & Bartlett, 1978).”
One-Shot Learning in Discriminative Neural Networks (2017, background): “Children are well-practised in this task, learning roughly ten new words a day after beginning to speak until the end of high school [Bloom, 2001]; largely grasping the meaning of words after just one or two examples [Carey and Bartlett, 1978].”